Compare commits
No commits in common. "main" and "fix/issue173-inline-aws-ecr-login" have entirely different histories.
main
...
fix/issue1
@ -1,118 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# audit-force-merge — detect a §SOP-6 force-merge after PR close, emit
|
||||
# `incident.force_merge` to stdout as structured JSON.
|
||||
#
|
||||
# Vector's docker_logs source picks up runner stdout; the JSON gets
|
||||
# shipped to Loki on molecule-canonical-obs, indexable by event_type.
|
||||
# Query example:
|
||||
#
|
||||
# {host="operator"} |= "event_type" |= "incident.force_merge" | json
|
||||
#
|
||||
# A force-merge is detected when a PR closed-with-merged=true had at
|
||||
# least one of the repo's required-status-check contexts in a state
|
||||
# other than "success" at the merge commit's SHA. That's exactly what
|
||||
# the Gitea force_merge:true API call lets through, so it's a faithful
|
||||
# detector of the override path.
|
||||
#
|
||||
# Triggers on `pull_request_target: closed` (loaded from base branch
|
||||
# per §SOP-6 security model). No-op when merged=false.
|
||||
#
|
||||
# Required env (set by the workflow):
|
||||
# GITEA_TOKEN, GITEA_HOST, REPO, PR_NUMBER, REQUIRED_CHECKS
|
||||
#
|
||||
# REQUIRED_CHECKS is a newline-separated list of status-check context
|
||||
# names that branch protection requires. Declared in the workflow YAML
|
||||
# rather than fetched from /branch_protections (which needs admin
|
||||
# scope — sop-tier-bot has read-only). Trade dynamism for simplicity:
|
||||
# when the required-check set changes, update both branch protection
|
||||
# AND this env. Keeping them in sync is less complexity than granting
|
||||
# the audit bot admin perms on every repo.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
: "${GITEA_TOKEN:?required}"
|
||||
: "${GITEA_HOST:?required}"
|
||||
: "${REPO:?required}"
|
||||
: "${PR_NUMBER:?required}"
|
||||
: "${REQUIRED_CHECKS:?required (newline-separated context names)}"
|
||||
|
||||
OWNER="${REPO%%/*}"
|
||||
NAME="${REPO##*/}"
|
||||
API="https://${GITEA_HOST}/api/v1"
|
||||
AUTH="Authorization: token ${GITEA_TOKEN}"
|
||||
|
||||
# 1. Fetch the PR. If not merged, no-op.
|
||||
PR=$(curl -sS -H "$AUTH" "${API}/repos/${OWNER}/${NAME}/pulls/${PR_NUMBER}")
|
||||
MERGED=$(echo "$PR" | jq -r '.merged // false')
|
||||
if [ "$MERGED" != "true" ]; then
|
||||
echo "::notice::PR #${PR_NUMBER} closed without merge — no audit emission."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
MERGE_SHA=$(echo "$PR" | jq -r '.merge_commit_sha // empty')
|
||||
MERGED_BY=$(echo "$PR" | jq -r '.merged_by.login // "unknown"')
|
||||
TITLE=$(echo "$PR" | jq -r '.title // ""')
|
||||
BASE_BRANCH=$(echo "$PR" | jq -r '.base.ref // "main"')
|
||||
HEAD_SHA=$(echo "$PR" | jq -r '.head.sha // empty')
|
||||
|
||||
if [ -z "$MERGE_SHA" ]; then
|
||||
echo "::warning::PR #${PR_NUMBER} merged=true but no merge_commit_sha — cannot evaluate force-merge."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# 2. Required status checks declared in the workflow env.
|
||||
REQUIRED="$REQUIRED_CHECKS"
|
||||
if [ -z "${REQUIRED//[[:space:]]/}" ]; then
|
||||
echo "::notice::REQUIRED_CHECKS empty — force-merge not applicable."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# 3. Status-check state at the PR HEAD (where checks ran). The merge
|
||||
# commit doesn't get its own checks; we evaluate the PR's last
|
||||
# commit, which is what branch protection compared against.
|
||||
STATUS=$(curl -sS -H "$AUTH" \
|
||||
"${API}/repos/${OWNER}/${NAME}/commits/${HEAD_SHA}/status")
|
||||
declare -A CHECK_STATE
|
||||
while IFS=$'\t' read -r ctx state; do
|
||||
[ -n "$ctx" ] && CHECK_STATE[$ctx]="$state"
|
||||
done < <(echo "$STATUS" | jq -r '.statuses // [] | .[] | "\(.context)\t\(.status)"')
|
||||
|
||||
# 4. For each required check, was it green at merge? YAML block scalars
|
||||
# (`|`) leave a trailing newline; skip blank/whitespace-only lines.
|
||||
FAILED_CHECKS=()
|
||||
while IFS= read -r req; do
|
||||
trimmed="${req#"${req%%[![:space:]]*}"}" # ltrim
|
||||
trimmed="${trimmed%"${trimmed##*[![:space:]]}"}" # rtrim
|
||||
[ -z "$trimmed" ] && continue
|
||||
state="${CHECK_STATE[$trimmed]:-missing}"
|
||||
if [ "$state" != "success" ]; then
|
||||
FAILED_CHECKS+=("${trimmed}=${state}")
|
||||
fi
|
||||
done <<< "$REQUIRED"
|
||||
|
||||
if [ "${#FAILED_CHECKS[@]}" -eq 0 ]; then
|
||||
echo "::notice::PR #${PR_NUMBER} merged with all required checks green — not a force-merge."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# 5. Emit structured audit event.
|
||||
NOW=$(date -u +%Y-%m-%dT%H:%M:%SZ)
|
||||
FAILED_JSON=$(printf '%s\n' "${FAILED_CHECKS[@]}" | jq -R . | jq -s .)
|
||||
|
||||
# Print as a single-line JSON so Vector's parse_json transform can pick
|
||||
# it up cleanly from docker_logs.
|
||||
jq -nc \
|
||||
--arg event_type "incident.force_merge" \
|
||||
--arg ts "$NOW" \
|
||||
--arg repo "$REPO" \
|
||||
--argjson pr "$PR_NUMBER" \
|
||||
--arg title "$TITLE" \
|
||||
--arg base "$BASE_BRANCH" \
|
||||
--arg merged_by "$MERGED_BY" \
|
||||
--arg merge_sha "$MERGE_SHA" \
|
||||
--argjson failed_checks "$FAILED_JSON" \
|
||||
'{event_type: $event_type, ts: $ts, repo: $repo, pr: $pr, title: $title,
|
||||
base_branch: $base, merged_by: $merged_by, merge_sha: $merge_sha,
|
||||
failed_checks: $failed_checks}'
|
||||
|
||||
echo "::warning::FORCE-MERGE detected on PR #${PR_NUMBER} by ${MERGED_BY}: ${#FAILED_CHECKS[@]} required check(s) not green at merge time."
|
||||
@ -1,149 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# sop-tier-check — verify a Gitea PR satisfies the §SOP-6 approval gate.
|
||||
#
|
||||
# Reads the PR's tier label, walks approving reviewers, and checks each
|
||||
# approver's Gitea team membership against the tier's eligible-team set.
|
||||
# Marks pass only when at least one non-author approver is in an eligible
|
||||
# team.
|
||||
#
|
||||
# Invoked from `.gitea/workflows/sop-tier-check.yml`. The workflow sets
|
||||
# the env vars below; this script does no IO outside of stdout/stderr +
|
||||
# the Gitea API.
|
||||
#
|
||||
# Required env:
|
||||
# GITEA_TOKEN — bot PAT with read:organization,read:user,
|
||||
# read:issue,read:repository scopes
|
||||
# GITEA_HOST — e.g. git.moleculesai.app
|
||||
# REPO — owner/name (from github.repository)
|
||||
# PR_NUMBER — int (from github.event.pull_request.number)
|
||||
# PR_AUTHOR — login (from github.event.pull_request.user.login)
|
||||
#
|
||||
# Optional:
|
||||
# SOP_DEBUG=1 — print per-API-call diagnostic lines (HTTP codes,
|
||||
# raw response bodies). Default: off.
|
||||
#
|
||||
# Stale-status caveat: Gitea Actions does not always re-fire workflows
|
||||
# on `labeled` / `pull_request_review:submitted` events. If the
|
||||
# sop-tier-check status is stale (e.g. red after labels/approvals were
|
||||
# added), push an empty commit to the PR branch to force a synchronize
|
||||
# event, OR re-request reviews. Tracked: internal#46.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
debug() {
|
||||
if [ "${SOP_DEBUG:-}" = "1" ]; then
|
||||
echo " [debug] $*" >&2
|
||||
fi
|
||||
}
|
||||
|
||||
# Validate env
|
||||
: "${GITEA_TOKEN:?GITEA_TOKEN required}"
|
||||
: "${GITEA_HOST:?GITEA_HOST required}"
|
||||
: "${REPO:?REPO required (owner/name)}"
|
||||
: "${PR_NUMBER:?PR_NUMBER required}"
|
||||
: "${PR_AUTHOR:?PR_AUTHOR required}"
|
||||
|
||||
OWNER="${REPO%%/*}"
|
||||
NAME="${REPO##*/}"
|
||||
API="https://${GITEA_HOST}/api/v1"
|
||||
AUTH="Authorization: token ${GITEA_TOKEN}"
|
||||
echo "::notice::tier-check start: repo=$OWNER/$NAME pr=$PR_NUMBER author=$PR_AUTHOR"
|
||||
|
||||
# Sanity: token resolves to a user
|
||||
WHOAMI=$(curl -sS -H "$AUTH" "${API}/user" | jq -r '.login // ""')
|
||||
if [ -z "$WHOAMI" ]; then
|
||||
echo "::error::GITEA_TOKEN cannot resolve a user via /api/v1/user — check the token scope and that the secret is wired correctly."
|
||||
exit 1
|
||||
fi
|
||||
echo "::notice::token resolves to user: $WHOAMI"
|
||||
|
||||
# 1. Read tier label
|
||||
LABELS=$(curl -sS -H "$AUTH" "${API}/repos/${OWNER}/${NAME}/issues/${PR_NUMBER}/labels" | jq -r '.[].name')
|
||||
TIER=""
|
||||
for L in $LABELS; do
|
||||
case "$L" in
|
||||
tier:low|tier:medium|tier:high)
|
||||
if [ -n "$TIER" ]; then
|
||||
echo "::error::Multiple tier labels: $TIER + $L. Apply exactly one."
|
||||
exit 1
|
||||
fi
|
||||
TIER="$L"
|
||||
;;
|
||||
esac
|
||||
done
|
||||
if [ -z "$TIER" ]; then
|
||||
echo "::error::PR has no tier:low|tier:medium|tier:high label. Apply one before merge."
|
||||
exit 1
|
||||
fi
|
||||
debug "tier=$TIER"
|
||||
|
||||
# 2. Tier → eligible teams
|
||||
case "$TIER" in
|
||||
tier:low) ELIGIBLE="engineers managers ceo" ;;
|
||||
tier:medium) ELIGIBLE="managers ceo" ;;
|
||||
tier:high) ELIGIBLE="ceo" ;;
|
||||
esac
|
||||
debug "eligible_teams=$ELIGIBLE"
|
||||
|
||||
# Resolve team-name → team-id once. /orgs/{org}/teams/{slug}/... endpoints
|
||||
# don't exist on Gitea 1.22; we have to use /teams/{id}.
|
||||
ORG_TEAMS_FILE=$(mktemp)
|
||||
trap 'rm -f "$ORG_TEAMS_FILE"' EXIT
|
||||
HTTP_CODE=$(curl -sS -o "$ORG_TEAMS_FILE" -w '%{http_code}' -H "$AUTH" \
|
||||
"${API}/orgs/${OWNER}/teams")
|
||||
debug "teams-list HTTP=$HTTP_CODE size=$(wc -c <"$ORG_TEAMS_FILE")"
|
||||
if [ "${SOP_DEBUG:-}" = "1" ]; then
|
||||
echo " [debug] teams-list body (first 300 chars):" >&2
|
||||
head -c 300 "$ORG_TEAMS_FILE" >&2; echo >&2
|
||||
fi
|
||||
if [ "$HTTP_CODE" != "200" ]; then
|
||||
echo "::error::GET /orgs/${OWNER}/teams returned HTTP $HTTP_CODE — token likely lacks read:org scope. Add a SOP_TIER_CHECK_TOKEN secret with read:organization scope at the org level."
|
||||
exit 1
|
||||
fi
|
||||
declare -A TEAM_ID
|
||||
for T in $ELIGIBLE; do
|
||||
ID=$(jq -r --arg t "$T" '.[] | select(.name==$t) | .id' <"$ORG_TEAMS_FILE" | head -1)
|
||||
if [ -z "$ID" ] || [ "$ID" = "null" ]; then
|
||||
VISIBLE=$(jq -r '.[]?.name? // empty' <"$ORG_TEAMS_FILE" 2>/dev/null | tr '\n' ' ')
|
||||
echo "::error::Team \"$T\" not found in org $OWNER. Teams visible: $VISIBLE"
|
||||
exit 1
|
||||
fi
|
||||
TEAM_ID[$T]="$ID"
|
||||
debug "team-id: $T → $ID"
|
||||
done
|
||||
|
||||
# 3. Read approving reviewers
|
||||
REVIEWS=$(curl -sS -H "$AUTH" "${API}/repos/${OWNER}/${NAME}/pulls/${PR_NUMBER}/reviews")
|
||||
APPROVERS=$(echo "$REVIEWS" | jq -r '[.[] | select(.state=="APPROVED") | .user.login] | unique | .[]')
|
||||
if [ -z "$APPROVERS" ]; then
|
||||
echo "::error::No approving reviews. Tier $TIER requires approval from {$ELIGIBLE} (non-author)."
|
||||
exit 1
|
||||
fi
|
||||
debug "approvers: $(echo "$APPROVERS" | tr '\n' ' ')"
|
||||
|
||||
# 4. For each approver: check non-author + team membership (by id)
|
||||
OK=""
|
||||
for U in $APPROVERS; do
|
||||
if [ "$U" = "$PR_AUTHOR" ]; then
|
||||
debug "skip self-review by $U"
|
||||
continue
|
||||
fi
|
||||
for T in $ELIGIBLE; do
|
||||
ID="${TEAM_ID[$T]}"
|
||||
CODE=$(curl -sS -o /dev/null -w '%{http_code}' -H "$AUTH" \
|
||||
"${API}/teams/${ID}/members/${U}")
|
||||
debug "probe: $U in team $T (id=$ID) → HTTP $CODE"
|
||||
if [ "$CODE" = "200" ] || [ "$CODE" = "204" ]; then
|
||||
echo "::notice::approver $U is in team $T (eligible for $TIER)"
|
||||
OK="yes"
|
||||
break
|
||||
fi
|
||||
done
|
||||
[ -n "$OK" ] && break
|
||||
done
|
||||
|
||||
if [ -z "$OK" ]; then
|
||||
echo "::error::Tier $TIER requires approval from a non-author member of {$ELIGIBLE}. Got approvers: $APPROVERS — none of them satisfied team membership. Set SOP_DEBUG=1 to see per-probe HTTP codes."
|
||||
exit 1
|
||||
fi
|
||||
echo "::notice::sop-tier-check passed: $TIER, approver in {$ELIGIBLE}"
|
||||
@ -1,58 +0,0 @@
|
||||
# audit-force-merge — emit `incident.force_merge` to runner stdout when
|
||||
# a PR is merged with required-status-checks not green. Vector picks
|
||||
# the JSON line off docker_logs and ships to Loki on
|
||||
# molecule-canonical-obs (per `reference_obs_stack_phase1`); query as:
|
||||
#
|
||||
# {host="operator"} |= "event_type" |= "incident.force_merge" | json
|
||||
#
|
||||
# Closes the §SOP-6 audit gap (the doc says force-merges write to
|
||||
# `structure_events`, but that table lives in the platform DB, not
|
||||
# Gitea-side; Loki is the practical equivalent for Gitea Actions
|
||||
# events). When the credential / observability stack converges later,
|
||||
# this can sync into structure_events from Loki via a backfill job —
|
||||
# the structured JSON shape is forward-compatible.
|
||||
#
|
||||
# Logic in `.gitea/scripts/audit-force-merge.sh` per the same script-
|
||||
# extract pattern as sop-tier-check.
|
||||
|
||||
name: audit-force-merge
|
||||
|
||||
# pull_request_target loads from the base branch — same security model
|
||||
# as sop-tier-check. Without this, an attacker could rewrite the
|
||||
# workflow on a PR and skip the audit emission for their own
|
||||
# force-merge. See `.gitea/workflows/sop-tier-check.yml` for the full
|
||||
# rationale.
|
||||
on:
|
||||
pull_request_target:
|
||||
types: [closed]
|
||||
|
||||
jobs:
|
||||
audit:
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: read
|
||||
# Skip when PR is closed without merge — saves a runner.
|
||||
if: github.event.pull_request.merged == true
|
||||
steps:
|
||||
- name: Check out base branch (for the script)
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
ref: ${{ github.event.pull_request.base.sha }}
|
||||
- name: Detect force-merge + emit audit event
|
||||
env:
|
||||
# Same org-level secret the sop-tier-check workflow uses.
|
||||
GITEA_TOKEN: ${{ secrets.SOP_TIER_CHECK_TOKEN || secrets.GITHUB_TOKEN }}
|
||||
GITEA_HOST: git.moleculesai.app
|
||||
REPO: ${{ github.repository }}
|
||||
PR_NUMBER: ${{ github.event.pull_request.number }}
|
||||
# Required-status-check contexts to evaluate at merge time.
|
||||
# Newline-separated. Mirror this against branch protection
|
||||
# (settings → branches → protected branch → required checks).
|
||||
# Declared here rather than fetched from /branch_protections
|
||||
# because that endpoint requires admin write — sop-tier-bot is
|
||||
# read-only by design (least-privilege).
|
||||
REQUIRED_CHECKS: |
|
||||
sop-tier-check / tier-check (pull_request)
|
||||
Secret scan / Scan diff for credential-shaped strings (pull_request)
|
||||
run: bash .gitea/scripts/audit-force-merge.sh
|
||||
@ -1,191 +0,0 @@
|
||||
name: Secret scan
|
||||
|
||||
# Hard CI gate. Refuses any PR / push whose diff additions contain a
|
||||
# recognisable credential. Defense-in-depth for the #2090-class incident
|
||||
# (2026-04-24): GitHub's hosted Copilot Coding Agent leaked a ghs_*
|
||||
# installation token into tenant-proxy/package.json via `npm init`
|
||||
# slurping the URL from a token-embedded origin remote. We can't fix
|
||||
# upstream's clone hygiene, so we gate here.
|
||||
#
|
||||
# Same regex set as the runtime's bundled pre-commit hook
|
||||
# (molecule-ai-workspace-runtime: molecule_runtime/scripts/pre-commit-checks.sh).
|
||||
# Keep the two sides aligned when adding patterns.
|
||||
#
|
||||
# Ported from .github/workflows/secret-scan.yml so the gate actually
|
||||
# fires on Gitea Actions. Differences from the GitHub version:
|
||||
# - drops `merge_group` event (Gitea has no merge queue)
|
||||
# - drops `workflow_call` (no cross-repo reusable invocation on Gitea)
|
||||
# - SELF path updated to .gitea/workflows/secret-scan.yml
|
||||
# The job name + step name are identical to the GitHub workflow so the
|
||||
# status-check context (`Secret scan / Scan diff for credential-shaped
|
||||
# strings (pull_request)`) matches branch protection on molecule-core/main.
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
types: [opened, synchronize, reopened]
|
||||
push:
|
||||
branches: [main, staging]
|
||||
|
||||
jobs:
|
||||
scan:
|
||||
name: Scan diff for credential-shaped strings
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
fetch-depth: 2 # need previous commit to diff against on push events
|
||||
|
||||
# For pull_request events the diff base may be many commits behind
|
||||
# HEAD and absent from the shallow clone. Fetch it explicitly.
|
||||
- name: Fetch PR base SHA (pull_request events only)
|
||||
if: github.event_name == 'pull_request'
|
||||
run: git fetch --depth=1 origin ${{ github.event.pull_request.base.sha }}
|
||||
|
||||
- name: Refuse if credential-shaped strings appear in diff additions
|
||||
env:
|
||||
# Plumb event-specific SHAs through env so the script doesn't
|
||||
# need conditional `${{ ... }}` interpolation per event type.
|
||||
# github.event.before/after only exist on push events;
|
||||
# pull_request has pull_request.base.sha / pull_request.head.sha.
|
||||
PR_BASE_SHA: ${{ github.event.pull_request.base.sha }}
|
||||
PR_HEAD_SHA: ${{ github.event.pull_request.head.sha }}
|
||||
PUSH_BEFORE: ${{ github.event.before }}
|
||||
PUSH_AFTER: ${{ github.event.after }}
|
||||
run: |
|
||||
# Pattern set covers GitHub family (the actual #2090 vector),
|
||||
# Anthropic / OpenAI / Slack / AWS. Anchored on prefixes with low
|
||||
# false-positive rates against agent-generated content. Mirror of
|
||||
# molecule-ai-workspace-runtime/molecule_runtime/scripts/pre-commit-checks.sh
|
||||
# — keep aligned.
|
||||
SECRET_PATTERNS=(
|
||||
'ghp_[A-Za-z0-9]{36,}' # GitHub PAT (classic)
|
||||
'ghs_[A-Za-z0-9]{36,}' # GitHub App installation token
|
||||
'gho_[A-Za-z0-9]{36,}' # GitHub OAuth user-to-server
|
||||
'ghu_[A-Za-z0-9]{36,}' # GitHub OAuth user
|
||||
'ghr_[A-Za-z0-9]{36,}' # GitHub OAuth refresh
|
||||
'github_pat_[A-Za-z0-9_]{82,}' # GitHub fine-grained PAT
|
||||
'sk-ant-[A-Za-z0-9_-]{40,}' # Anthropic API key
|
||||
'sk-proj-[A-Za-z0-9_-]{40,}' # OpenAI project key
|
||||
'sk-svcacct-[A-Za-z0-9_-]{40,}' # OpenAI service-account key
|
||||
'sk-cp-[A-Za-z0-9_-]{60,}' # MiniMax API key (F1088 vector — caught only after the fact)
|
||||
'xox[baprs]-[A-Za-z0-9-]{20,}' # Slack tokens
|
||||
'AKIA[0-9A-Z]{16}' # AWS access key ID
|
||||
'ASIA[0-9A-Z]{16}' # AWS STS temp access key ID
|
||||
)
|
||||
|
||||
# Determine the diff base. Each event type stores its SHAs in
|
||||
# a different place — see the env block above.
|
||||
case "${{ github.event_name }}" in
|
||||
pull_request)
|
||||
BASE="$PR_BASE_SHA"
|
||||
HEAD="$PR_HEAD_SHA"
|
||||
;;
|
||||
*)
|
||||
BASE="$PUSH_BEFORE"
|
||||
HEAD="$PUSH_AFTER"
|
||||
;;
|
||||
esac
|
||||
|
||||
# On push events with shallow clones, BASE may be present in
|
||||
# the event payload but absent from the local object DB
|
||||
# (fetch-depth=2 doesn't always reach the previous commit
|
||||
# across true merges). Try fetching it on demand. If the
|
||||
# fetch fails — e.g. the SHA was force-overwritten — we fall
|
||||
# through to the empty-BASE branch below, which scans the
|
||||
# entire tree as if every file were new. Correct, just slow.
|
||||
if [ -n "$BASE" ] && ! echo "$BASE" | grep -qE '^0+$'; then
|
||||
if ! git cat-file -e "$BASE" 2>/dev/null; then
|
||||
git fetch --depth=1 origin "$BASE" 2>/dev/null || true
|
||||
fi
|
||||
fi
|
||||
|
||||
# Files added or modified in this change.
|
||||
if [ -z "$BASE" ] || echo "$BASE" | grep -qE '^0+$' || ! git cat-file -e "$BASE" 2>/dev/null; then
|
||||
# New branch / no previous SHA / BASE unreachable — check the
|
||||
# entire tree as added content. Slower, but correct on first
|
||||
# push.
|
||||
CHANGED=$(git ls-tree -r --name-only HEAD)
|
||||
DIFF_RANGE=""
|
||||
else
|
||||
CHANGED=$(git diff --name-only --diff-filter=AM "$BASE" "$HEAD")
|
||||
DIFF_RANGE="$BASE $HEAD"
|
||||
fi
|
||||
|
||||
if [ -z "$CHANGED" ]; then
|
||||
echo "No changed files to inspect."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Self-exclude: this workflow file legitimately contains the
|
||||
# pattern strings as regex literals. Without an exclude it would
|
||||
# block its own merge. Both the .github/ original and this
|
||||
# .gitea/ port are excluded so a sync between them stays clean.
|
||||
SELF_GITHUB=".github/workflows/secret-scan.yml"
|
||||
SELF_GITEA=".gitea/workflows/secret-scan.yml"
|
||||
|
||||
OFFENDING=""
|
||||
# `while IFS= read -r` (not `for f in $CHANGED`) so filenames
|
||||
# containing whitespace don't word-split silently — a path
|
||||
# with a space would otherwise produce two iterations on
|
||||
# tokens that aren't real filenames, breaking the
|
||||
# self-exclude + diff lookup.
|
||||
while IFS= read -r f; do
|
||||
[ -z "$f" ] && continue
|
||||
[ "$f" = "$SELF_GITHUB" ] && continue
|
||||
[ "$f" = "$SELF_GITEA" ] && continue
|
||||
if [ -n "$DIFF_RANGE" ]; then
|
||||
ADDED=$(git diff --no-color --unified=0 "$BASE" "$HEAD" -- "$f" 2>/dev/null | grep -E '^\+[^+]' || true)
|
||||
else
|
||||
# No diff range (new branch first push) — scan the full file
|
||||
# contents as if every line were new.
|
||||
ADDED=$(cat "$f" 2>/dev/null || true)
|
||||
fi
|
||||
[ -z "$ADDED" ] && continue
|
||||
for pattern in "${SECRET_PATTERNS[@]}"; do
|
||||
if echo "$ADDED" | grep -qE "$pattern"; then
|
||||
OFFENDING="${OFFENDING}${f} (matched: ${pattern})\n"
|
||||
break
|
||||
fi
|
||||
done
|
||||
done <<< "$CHANGED"
|
||||
|
||||
if [ -n "$OFFENDING" ]; then
|
||||
echo "::error::Credential-shaped strings detected in diff additions:"
|
||||
# `printf '%b' "$OFFENDING"` interprets backslash escapes
|
||||
# (the literal `\n` we appended above becomes a newline)
|
||||
# WITHOUT treating OFFENDING as a format string. Plain
|
||||
# `printf "$OFFENDING"` is a format-string sink: a filename
|
||||
# containing `%` would be interpreted as a conversion
|
||||
# specifier, corrupting the error message (or printing
|
||||
# `%(missing)` artifacts).
|
||||
printf '%b' "$OFFENDING"
|
||||
echo ""
|
||||
echo "The actual matched values are NOT echoed here, deliberately —"
|
||||
echo "round-tripping a leaked credential into CI logs widens the blast"
|
||||
echo "radius (logs are searchable + retained)."
|
||||
echo ""
|
||||
echo "Recovery:"
|
||||
echo " 1. Remove the secret from the file. Replace with an env var"
|
||||
echo " reference (e.g. \${{ secrets.GITHUB_TOKEN }} in workflows,"
|
||||
echo " process.env.X in code)."
|
||||
echo " 2. If the credential was already pushed (this PR's commit"
|
||||
echo " history reaches a public ref), treat it as compromised —"
|
||||
echo " ROTATE it immediately, do not just remove it. The token"
|
||||
echo " remains valid in git history forever and may be in any"
|
||||
echo " log/cache that consumed this branch."
|
||||
echo " 3. Force-push the cleaned commit (or stack a revert) and"
|
||||
echo " re-run CI."
|
||||
echo ""
|
||||
echo "If the match is a false positive (test fixture, docs example,"
|
||||
echo "or this workflow's own regex literals): use a clearly-fake"
|
||||
echo "placeholder like ghs_EXAMPLE_DO_NOT_USE that doesn't satisfy"
|
||||
echo "the length suffix, OR add the file path to the SELF exclude"
|
||||
echo "list in this workflow with a short reason."
|
||||
echo ""
|
||||
echo "Mirror of the regex set lives in the runtime's bundled"
|
||||
echo "pre-commit hook (molecule-ai-workspace-runtime:"
|
||||
echo "molecule_runtime/scripts/pre-commit-checks.sh) — keep aligned."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✓ No credential-shaped strings in this change."
|
||||
@ -1,81 +0,0 @@
|
||||
# sop-tier-check — canonical Gitea Actions workflow for §SOP-6 enforcement.
|
||||
#
|
||||
# Logic lives in `.gitea/scripts/sop-tier-check.sh` (extracted 2026-05-09
|
||||
# from the previous inline-bash version). The script is the single source
|
||||
# of truth; this workflow file just sets env + invokes it.
|
||||
#
|
||||
# Copy BOTH files (`.gitea/workflows/sop-tier-check.yml` +
|
||||
# `.gitea/scripts/sop-tier-check.sh`) into any repo that wants the
|
||||
# §SOP-6 PR gate enforced. Pair with branch protection on the protected
|
||||
# branch:
|
||||
# required_status_checks: ["sop-tier-check / tier-check (pull_request)"]
|
||||
# required_approving_reviews: 1
|
||||
# approving_review_teams: ["ceo", "managers", "engineers"]
|
||||
#
|
||||
# Tier → eligible-team mapping (mirror of dev-sop §SOP-6):
|
||||
# tier:low → engineers, managers, ceo
|
||||
# tier:medium → managers, ceo
|
||||
# tier:high → ceo
|
||||
#
|
||||
# Force-merge: Owners-team override remains available out-of-band via
|
||||
# the Gitea merge API; force-merge writes `incident.force_merge` to
|
||||
# `structure_events` per §Persistent structured logging gate (Phase 3).
|
||||
#
|
||||
# Set `SOP_DEBUG: '1'` in the env block to enable per-API-call diagnostic
|
||||
# lines — useful when diagnosing token-scope or team-id-resolution
|
||||
# issues. Default off.
|
||||
|
||||
name: sop-tier-check
|
||||
|
||||
# SECURITY: triggers MUST use `pull_request_target`, not `pull_request`.
|
||||
# `pull_request_target` loads the workflow definition from the BASE
|
||||
# branch (i.e. `main`), not the PR's HEAD. With `pull_request`, anyone
|
||||
# with write access to a feature branch could rewrite this file in
|
||||
# their PR to dump SOP_TIER_CHECK_TOKEN (org-read scope) to logs and
|
||||
# exfiltrate it. Verified 2026-05-09 against Gitea 1.22.6 —
|
||||
# `pull_request_target` (added in Gitea 1.21 via go-gitea/gitea#25229)
|
||||
# is the documented mitigation.
|
||||
#
|
||||
# This workflow does NOT call `actions/checkout` of PR HEAD code, so no
|
||||
# untrusted code is ever executed in the runner — we only HTTP-call the
|
||||
# Gitea API. If a future change adds a checkout step, it MUST pin to
|
||||
# `${{ github.event.pull_request.base.sha }}` (NOT `head.sha`) to keep
|
||||
# the trust boundary.
|
||||
on:
|
||||
pull_request_target:
|
||||
types: [opened, edited, synchronize, reopened, labeled, unlabeled]
|
||||
pull_request_review:
|
||||
types: [submitted, dismissed, edited]
|
||||
|
||||
jobs:
|
||||
tier-check:
|
||||
runs-on: ubuntu-latest
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: read
|
||||
steps:
|
||||
- name: Check out base branch (for the script)
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
# Pin to base.sha — pull_request_target's protection only
|
||||
# works if we never check out PR HEAD. Same SHA the workflow
|
||||
# itself was loaded from.
|
||||
ref: ${{ github.event.pull_request.base.sha }}
|
||||
- name: Verify tier label + reviewer team membership
|
||||
env:
|
||||
# SOP_TIER_CHECK_TOKEN is the org-level secret for the
|
||||
# sop-tier-bot PAT (read:organization,read:user,read:issue,
|
||||
# read:repository). Stored at the org level
|
||||
# (/api/v1/orgs/molecule-ai/actions/secrets) so per-repo
|
||||
# configuration is unnecessary — every repo in the org
|
||||
# picks it up automatically.
|
||||
# Falls back to GITHUB_TOKEN with a clear error if missing.
|
||||
GITEA_TOKEN: ${{ secrets.SOP_TIER_CHECK_TOKEN || secrets.GITHUB_TOKEN }}
|
||||
GITEA_HOST: git.moleculesai.app
|
||||
REPO: ${{ github.repository }}
|
||||
PR_NUMBER: ${{ github.event.pull_request.number }}
|
||||
PR_AUTHOR: ${{ github.event.pull_request.user.login }}
|
||||
# Set to '1' for diagnostic per-API-call output. Off by default
|
||||
# so production logs aren't noisy.
|
||||
SOP_DEBUG: '0'
|
||||
run: bash .gitea/scripts/sop-tier-check.sh
|
||||
2
.github/scripts/lint_secret_pattern_drift.py
vendored
2
.github/scripts/lint_secret_pattern_drift.py
vendored
@ -37,7 +37,7 @@ CANONICAL_FILE = Path(".github/workflows/secret-scan.yml")
|
||||
CONSUMERS: list[tuple[str, str]] = [
|
||||
(
|
||||
"molecule-ai-workspace-runtime/molecule_runtime/scripts/pre-commit-checks.sh",
|
||||
"https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime/raw/branch/main/molecule_runtime/scripts/pre-commit-checks.sh",
|
||||
"https://raw.githubusercontent.com/Molecule-AI/molecule-ai-workspace-runtime/main/molecule_runtime/scripts/pre-commit-checks.sh",
|
||||
),
|
||||
]
|
||||
|
||||
|
||||
429
.github/workflows/auto-promote-on-e2e.yml
vendored
Normal file
429
.github/workflows/auto-promote-on-e2e.yml
vendored
Normal file
@ -0,0 +1,429 @@
|
||||
name: Auto-promote :latest after main image build
|
||||
|
||||
# Retags `ghcr.io/molecule-ai/{platform,platform-tenant}:staging-<sha>`
|
||||
# → `:latest` after either the image build or E2E completes on a `main`
|
||||
# push, gated on E2E Staging SaaS not being red for that SHA.
|
||||
#
|
||||
# Why two triggers:
|
||||
#
|
||||
# `publish-workspace-server-image` and `e2e-staging-saas` are both
|
||||
# paths-filtered, but with DIFFERENT path sets:
|
||||
#
|
||||
# publish-workspace-server-image:
|
||||
# workspace-server/**, canvas/**, manifest.json
|
||||
#
|
||||
# e2e-staging-saas (full lifecycle):
|
||||
# workspace-server/internal/handlers/{registry,workspace_provision,
|
||||
# a2a_proxy}.go, workspace-server/internal/middleware/**,
|
||||
# workspace-server/internal/provisioner/**, tests/e2e/test_staging_full_saas.sh
|
||||
#
|
||||
# The E2E set is a strict SUBSET of the publish set. So:
|
||||
# - canvas/** changes → publish fires, E2E does not
|
||||
# - workspace-server/cmd/** changes → publish fires, E2E does not
|
||||
# - workspace-server/internal/sweep/** → publish fires, E2E does not
|
||||
#
|
||||
# The previous version triggered ONLY on E2E completion, which meant
|
||||
# non-E2E-path changes (canvas, cmd, sweep, etc.) rebuilt the image
|
||||
# but never advanced `:latest`. Result: as of 2026-04-28 this workflow
|
||||
# had run zero times since merge despite eight main pushes — `:latest`
|
||||
# was ~7 hours / 9 PRs behind main with no human realising. See
|
||||
# `molecule-core` Slack discussion 2026-04-28.
|
||||
#
|
||||
# Adding `publish-workspace-server-image` as a second trigger closes
|
||||
# the gap: any image rebuild on main eligibly advances `:latest`.
|
||||
#
|
||||
# Why E2E remains a kill-switch (not the trigger):
|
||||
#
|
||||
# When E2E DID run for this SHA and ended red, we abort — `:latest`
|
||||
# stays on the prior known-good digest. When E2E didn't run (paths
|
||||
# filtered out), we proceed: pre-merge gates already validated this
|
||||
# SHA on staging via auto-promote-staging requiring CI + E2E Canvas +
|
||||
# E2E API + CodeQL all green. Image content for non-E2E-paths
|
||||
# (canvas, cmd, sweep) is exercised by those staging gates.
|
||||
#
|
||||
# Why `main` only:
|
||||
#
|
||||
# `:latest` is what prod tenants pull. We only want SHAs that have
|
||||
# reached main (via auto-promote-staging) to advance `:latest`.
|
||||
# Triggering on staging would let a staging-only revert advance
|
||||
# `:latest` to a SHA that never reaches main, breaking the "production
|
||||
# runs what's on main" invariant.
|
||||
#
|
||||
# Idempotency:
|
||||
#
|
||||
# When a SHA touches paths that match BOTH publish and E2E, both
|
||||
# workflows fire and complete. Both trigger this workflow on
|
||||
# completion → two runs race. Both retag `:staging-<sha>` →
|
||||
# `:latest`. crane tag is idempotent (re-tagging the same digest is a
|
||||
# no-op), so the second run is harmless. concurrency group serializes
|
||||
# them anyway.
|
||||
|
||||
on:
|
||||
workflow_run:
|
||||
workflows:
|
||||
- 'E2E Staging SaaS (full lifecycle)'
|
||||
- 'publish-workspace-server-image'
|
||||
types: [completed]
|
||||
branches: [main]
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
sha:
|
||||
description: 'Short sha to promote (override; defaults to upstream workflow_run head_sha)'
|
||||
required: false
|
||||
type: string
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
packages: write
|
||||
|
||||
concurrency:
|
||||
# Serialize promotes per-SHA so the publish+E2E both-fired race lands
|
||||
# cleanly. Different SHAs can promote in parallel.
|
||||
group: auto-promote-latest-${{ github.event.workflow_run.head_sha || github.event.inputs.sha || github.sha }}
|
||||
cancel-in-progress: false
|
||||
|
||||
env:
|
||||
IMAGE_NAME: ghcr.io/molecule-ai/platform
|
||||
TENANT_IMAGE_NAME: ghcr.io/molecule-ai/platform-tenant
|
||||
|
||||
jobs:
|
||||
promote:
|
||||
# Proceed if upstream succeeded OR manual dispatch. Upstream-failure
|
||||
# paths are filtered here; the E2E-was-red kill-switch lives in the
|
||||
# gate-check step below (covers the case where upstream is publish
|
||||
# success but E2E for the same SHA failed).
|
||||
if: |
|
||||
github.event_name == 'workflow_dispatch' ||
|
||||
(github.event_name == 'workflow_run' && github.event.workflow_run.conclusion == 'success')
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Compute short sha
|
||||
id: sha
|
||||
run: |
|
||||
set -euo pipefail
|
||||
if [ -n "${{ github.event.inputs.sha }}" ]; then
|
||||
FULL="${{ github.event.inputs.sha }}"
|
||||
else
|
||||
FULL="${{ github.event.workflow_run.head_sha }}"
|
||||
fi
|
||||
echo "short=${FULL:0:7}" >> "$GITHUB_OUTPUT"
|
||||
echo "full=${FULL}" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Gate — E2E Staging SaaS state for this SHA
|
||||
# When upstream IS E2E success, we know it's green (filtered by
|
||||
# the job-level `if` already). When upstream is publish, look up
|
||||
# E2E state for the same SHA. Four buckets:
|
||||
#
|
||||
# - completed/success: E2E confirmed safe → proceed
|
||||
# - completed/failure|cancelled|timed_out: E2E found a
|
||||
# regression → ABORT (exit 1), `:latest` stays put
|
||||
# - in_progress|queued|requested: E2E is RACING with publish
|
||||
# for a runtime-touching SHA. publish typically completes
|
||||
# ~5-10min before E2E (~10-15min). If we promote on the
|
||||
# publish signal here, a later E2E failure can't roll back
|
||||
# `:latest` — it'd already be wrongly advanced. So we DEFER:
|
||||
# skip subsequent steps (proceed=false) and let E2E's own
|
||||
# completion event re-fire this workflow, which then takes
|
||||
# the upstream-is-E2E path. exit 0 so the run shows as
|
||||
# success rather than a noisy fake-failure.
|
||||
# - none/none: E2E was paths-filtered out for this SHA (the
|
||||
# change touched canvas/cmd/sweep/etc. — paths covered by
|
||||
# publish but not by E2E). pre-merge gates on staging
|
||||
# already validated this SHA → proceed.
|
||||
#
|
||||
# Manual dispatch skips this check — operator override.
|
||||
id: gate
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
REPO: ${{ github.repository }}
|
||||
SHA: ${{ steps.sha.outputs.full }}
|
||||
UPSTREAM_NAME: ${{ github.event.workflow_run.name }}
|
||||
EVENT_NAME: ${{ github.event_name }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
if [ "$EVENT_NAME" = "workflow_dispatch" ]; then
|
||||
echo "proceed=true" >> "$GITHUB_OUTPUT"
|
||||
echo "::notice::Manual dispatch — skipping E2E gate (operator override)"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if [ "$UPSTREAM_NAME" = "E2E Staging SaaS (full lifecycle)" ]; then
|
||||
echo "proceed=true" >> "$GITHUB_OUTPUT"
|
||||
echo "::notice::Upstream is E2E itself (success per job-level if) — gate trivially satisfied"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Upstream is publish-workspace-server-image. Check E2E state.
|
||||
# The jq filter must defend against TWO empty cases that gh
|
||||
# CLI emits indistinguishably:
|
||||
# 1. gh exits non-zero (network blip, auth issue) → handled
|
||||
# by the `|| echo "none/none"` fallback below.
|
||||
# 2. gh exits zero but returns `[]` (no E2E run on this
|
||||
# main SHA — the common case for canvas-only / cmd-only
|
||||
# / sweep-only changes whose paths don't trigger E2E).
|
||||
# Without `(.[0] // {})`, jq sees `null` and emits
|
||||
# "null/none" — which the case statement below has no
|
||||
# branch for, so it falls into *) → exit 1.
|
||||
# Surfaced 2026-04-30 the first time the App-token chain
|
||||
# (#2389) actually fired auto-promote-on-e2e from a publish
|
||||
# upstream — every prior run was E2E-upstream which
|
||||
# short-circuits before this gate.
|
||||
RESULT=$(gh run list \
|
||||
--repo "$REPO" \
|
||||
--workflow e2e-staging-saas.yml \
|
||||
--branch main \
|
||||
--commit "$SHA" \
|
||||
--limit 1 \
|
||||
--json status,conclusion \
|
||||
--jq '(.[0] // {}) | "\(.status // "none")/\(.conclusion // "none")"' \
|
||||
2>/dev/null || echo "none/none")
|
||||
|
||||
echo "E2E Staging SaaS for ${SHA:0:7}: $RESULT"
|
||||
|
||||
case "$RESULT" in
|
||||
completed/success)
|
||||
echo "proceed=true" >> "$GITHUB_OUTPUT"
|
||||
echo "::notice::E2E green for this SHA — proceeding with promote"
|
||||
;;
|
||||
completed/failure|completed/timed_out)
|
||||
echo "proceed=false" >> "$GITHUB_OUTPUT"
|
||||
{
|
||||
echo "## ❌ Auto-promote aborted — E2E Staging SaaS failed"
|
||||
echo
|
||||
echo "E2E Staging SaaS for \`${SHA:0:7}\`: \`$RESULT\`"
|
||||
echo "\`:latest\` stays on the prior known-good digest."
|
||||
echo
|
||||
echo "If the failure was a flake, manually dispatch this workflow with the same sha to override."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
exit 1
|
||||
;;
|
||||
completed/cancelled)
|
||||
# cancelled ≠ failure. Per-SHA concurrency cancels older E2E
|
||||
# runs when a newer push lands (memory:
|
||||
# feedback_concurrency_group_per_sha) — the newer SHA will
|
||||
# have its own E2E + promote chain. Treat the same as
|
||||
# in_progress: defer without aborting, let the next E2E run
|
||||
# promote when it lands.
|
||||
#
|
||||
# Caught 2026-05-05 02:03 on sha 31f9a5e — auto-promote
|
||||
# blocked the whole chain because this case fell through to
|
||||
# exit 1 instead of clean defer.
|
||||
echo "proceed=false" >> "$GITHUB_OUTPUT"
|
||||
{
|
||||
echo "## ⏭ Auto-promote deferred — E2E Staging SaaS was cancelled"
|
||||
echo
|
||||
echo "E2E Staging SaaS for \`${SHA:0:7}\`: \`$RESULT\`"
|
||||
echo "Likely per-SHA concurrency (newer push superseded this E2E run)."
|
||||
echo "The newer SHA's E2E will fire its own promote when it lands."
|
||||
echo "If you need this specific SHA promoted, manually dispatch."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
;;
|
||||
in_progress/*|queued/*|requested/*|waiting/*|pending/*)
|
||||
echo "proceed=false" >> "$GITHUB_OUTPUT"
|
||||
{
|
||||
echo "## ⏳ Auto-promote deferred — E2E Staging SaaS still running"
|
||||
echo
|
||||
echo "Publish completed before E2E for \`${SHA:0:7}\` (state: \`$RESULT\`)."
|
||||
echo "Skipping retag here — E2E's own completion event will re-fire this workflow."
|
||||
echo "If E2E ends green, that run promotes \`:latest\`. If red, it aborts."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
;;
|
||||
none/none)
|
||||
echo "proceed=true" >> "$GITHUB_OUTPUT"
|
||||
echo "::notice::E2E paths-filtered out for this SHA — pre-merge staging gates carry"
|
||||
;;
|
||||
*)
|
||||
echo "proceed=false" >> "$GITHUB_OUTPUT"
|
||||
{
|
||||
echo "## ❓ Auto-promote aborted — unexpected E2E state"
|
||||
echo
|
||||
echo "E2E Staging SaaS for \`${SHA:0:7}\`: \`$RESULT\` (unhandled)"
|
||||
echo "Manual investigation needed; re-dispatch with the same sha once resolved."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
||||
- if: steps.gate.outputs.proceed == 'true'
|
||||
uses: imjasonh/setup-crane@6da1ae018866400525525ce74ff892880c099987 # v0.5
|
||||
|
||||
- name: GHCR login
|
||||
if: steps.gate.outputs.proceed == 'true'
|
||||
run: |
|
||||
echo "${{ secrets.GITHUB_TOKEN }}" | \
|
||||
crane auth login ghcr.io -u "${{ github.actor }}" --password-stdin
|
||||
|
||||
- name: Verify :staging-<sha> exists for both images
|
||||
# Better to fail fast with a clear message than to half-tag
|
||||
# (platform retagged but platform-tenant missing → tenants pull
|
||||
# a stale image).
|
||||
if: steps.gate.outputs.proceed == 'true'
|
||||
run: |
|
||||
set -euo pipefail
|
||||
for img in "${IMAGE_NAME}" "${TENANT_IMAGE_NAME}"; do
|
||||
tag="${img}:staging-${{ steps.sha.outputs.short }}"
|
||||
if ! crane manifest "$tag" >/dev/null 2>&1; then
|
||||
echo "::error::Missing tag: $tag"
|
||||
echo "::error::publish-workspace-server-image must complete on this SHA before auto-promote can retag :latest."
|
||||
exit 1
|
||||
fi
|
||||
echo " ok: $tag exists"
|
||||
done
|
||||
|
||||
- name: Ancestry check — refuse to promote :latest backwards
|
||||
# #2244: workflow_run completions arrive in arbitrary order. If
|
||||
# SHA-A and SHA-B both reach main within ~10 min and SHA-B's E2E
|
||||
# completes before SHA-A's, this workflow can fire for SHA-A
|
||||
# AFTER it already promoted SHA-B → :latest goes backwards. The
|
||||
# orphan-reconciler "next run corrects it" doesn't apply: there's
|
||||
# no auto-corrective re-promote, :latest stays wrong until the
|
||||
# next main push lands.
|
||||
#
|
||||
# Detection: read current :latest's `org.opencontainers.image.revision`
|
||||
# label (set by publish-workspace-server-image.yml at build time)
|
||||
# and ask the GitHub compare API whether the candidate SHA is
|
||||
# ahead-of / identical-to / behind / diverged-from current.
|
||||
# Hard-fail on `behind` and `diverged` per the approved design —
|
||||
# silent-bypass is the class we're moving away from. Workflow
|
||||
# goes red, oncall sees it, operator decides how to recover
|
||||
# (manual dispatch with the right SHA, force-promote, etc.).
|
||||
#
|
||||
# Manual dispatch skips this check — operator override semantics
|
||||
# match the gate-check step above.
|
||||
#
|
||||
# Backward-compat: when current :latest carries no revision
|
||||
# label (legacy image pre-publish-with-label), skip-with-warning.
|
||||
# All :latest images on main are post-label as of 2026-04-29, so
|
||||
# this branch will be dead within 90 days; remove then.
|
||||
if: steps.gate.outputs.proceed == 'true' && github.event_name != 'workflow_dispatch'
|
||||
id: ancestry
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
REPO: ${{ github.repository }}
|
||||
TARGET_SHA: ${{ steps.sha.outputs.full }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
# Read the current :latest config and pull the revision label.
|
||||
# `crane config` returns the OCI image config blob (not the manifest);
|
||||
# labels live under `.config.Labels`. `// empty` makes jq return ""
|
||||
# rather than the literal "null" so the test below works.
|
||||
CURRENT_REVISION=$(crane config "${IMAGE_NAME}:latest" 2>/dev/null \
|
||||
| jq -r '.config.Labels["org.opencontainers.image.revision"] // empty' \
|
||||
|| true)
|
||||
|
||||
if [ -z "$CURRENT_REVISION" ]; then
|
||||
echo "decision=skip-no-label" >> "$GITHUB_OUTPUT"
|
||||
{
|
||||
echo "## ⚠ Ancestry check skipped — current :latest has no revision label"
|
||||
echo
|
||||
echo "Likely a legacy image built before \`org.opencontainers.image.revision\` was set."
|
||||
echo "Falling through to retag. After all \`:latest\` images are post-label (TODO 90 days), this branch is dead and should be removed."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
echo "::warning::Current :latest carries no revision label — skipping ancestry check (legacy image)"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if [ "$CURRENT_REVISION" = "$TARGET_SHA" ]; then
|
||||
echo "decision=identical" >> "$GITHUB_OUTPUT"
|
||||
echo "::notice:::latest already at ${TARGET_SHA:0:7} — retag will be a no-op"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Ask GitHub which side of the merge graph TARGET_SHA sits on
|
||||
# relative to CURRENT_REVISION. Returns one of: ahead | identical
|
||||
# | behind | diverged. Network or auth errors collapse to "error"
|
||||
# via the explicit fallback so the case below always matches.
|
||||
STATUS=$(gh api \
|
||||
"repos/${REPO}/compare/${CURRENT_REVISION}...${TARGET_SHA}" \
|
||||
--jq '.status' 2>/dev/null || echo "error")
|
||||
|
||||
echo "ancestry compare ${CURRENT_REVISION:0:7} → ${TARGET_SHA:0:7}: $STATUS"
|
||||
|
||||
case "$STATUS" in
|
||||
ahead)
|
||||
echo "decision=ahead" >> "$GITHUB_OUTPUT"
|
||||
echo "::notice::Target ${TARGET_SHA:0:7} is ahead of current :latest (${CURRENT_REVISION:0:7}) — proceeding with retag"
|
||||
;;
|
||||
identical)
|
||||
echo "decision=identical" >> "$GITHUB_OUTPUT"
|
||||
echo "::notice::Target identical to :latest — retag will be a no-op"
|
||||
;;
|
||||
behind)
|
||||
echo "decision=behind" >> "$GITHUB_OUTPUT"
|
||||
{
|
||||
echo "## ❌ Auto-promote refused — target is BEHIND current :latest"
|
||||
echo
|
||||
echo "| Field | Value |"
|
||||
echo "|---|---|"
|
||||
echo "| Target SHA | \`$TARGET_SHA\` |"
|
||||
echo "| Current :latest revision | \`$CURRENT_REVISION\` |"
|
||||
echo "| GitHub compare status | \`behind\` |"
|
||||
echo
|
||||
echo "This guard catches the workflow_run-completion-order race (#2244):"
|
||||
echo "two rapid main pushes whose E2Es complete out-of-order can otherwise"
|
||||
echo "promote \`:latest\` backwards. \`:latest\` stays on \`${CURRENT_REVISION:0:7}\`."
|
||||
echo
|
||||
echo "**Recovery:** if this is a legitimate revert that should land on \`:latest\`,"
|
||||
echo "manually dispatch this workflow with the target sha as input — the manual-dispatch"
|
||||
echo "path skips the ancestry check (operator override)."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
exit 1
|
||||
;;
|
||||
diverged)
|
||||
echo "decision=diverged" >> "$GITHUB_OUTPUT"
|
||||
{
|
||||
echo "## ❓ Auto-promote refused — history diverged"
|
||||
echo
|
||||
echo "| Field | Value |"
|
||||
echo "|---|---|"
|
||||
echo "| Target SHA | \`$TARGET_SHA\` |"
|
||||
echo "| Current :latest revision | \`$CURRENT_REVISION\` |"
|
||||
echo "| GitHub compare status | \`diverged\` |"
|
||||
echo
|
||||
echo "Likely cause: force-push rewrote main's history, leaving the previous"
|
||||
echo "\`:latest\` revision orphaned. Needs human review before \`:latest\` advances."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
exit 1
|
||||
;;
|
||||
error|*)
|
||||
echo "decision=error" >> "$GITHUB_OUTPUT"
|
||||
{
|
||||
echo "## ❌ Auto-promote aborted — ancestry-check API error"
|
||||
echo
|
||||
echo "\`gh api repos/${REPO}/compare/${CURRENT_REVISION}...${TARGET_SHA}\` returned unexpected status: \`$STATUS\`"
|
||||
echo
|
||||
echo "Manual dispatch with the target sha bypasses this check."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
|
||||
- name: Retag platform :staging-<sha> → :latest
|
||||
if: steps.gate.outputs.proceed == 'true'
|
||||
run: |
|
||||
crane tag "${IMAGE_NAME}:staging-${{ steps.sha.outputs.short }}" latest
|
||||
|
||||
- name: Retag tenant :staging-<sha> → :latest
|
||||
if: steps.gate.outputs.proceed == 'true'
|
||||
run: |
|
||||
crane tag "${TENANT_IMAGE_NAME}:staging-${{ steps.sha.outputs.short }}" latest
|
||||
|
||||
- name: Summary
|
||||
if: steps.gate.outputs.proceed == 'true'
|
||||
run: |
|
||||
{
|
||||
echo "## :latest promoted to ${{ steps.sha.outputs.short }}"
|
||||
echo
|
||||
if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
|
||||
echo "- Trigger: manual dispatch"
|
||||
else
|
||||
echo "- Upstream: \`${{ github.event.workflow_run.name }}\` ([run](${{ github.event.workflow_run.html_url }}))"
|
||||
fi
|
||||
echo "- platform:staging-${{ steps.sha.outputs.short }} → :latest"
|
||||
echo "- platform-tenant:staging-${{ steps.sha.outputs.short }} → :latest"
|
||||
echo
|
||||
echo "Tenant fleet auto-pulls within 5 min via IMAGE_AUTO_REFRESH=true."
|
||||
echo "Force immediate fanout: dispatch redeploy-tenants-on-main.yml."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
434
.github/workflows/auto-promote-staging.yml
vendored
Normal file
434
.github/workflows/auto-promote-staging.yml
vendored
Normal file
@ -0,0 +1,434 @@
|
||||
name: Auto-promote staging → main
|
||||
|
||||
# Fires after any of the staging-branch quality gates complete. When ALL
|
||||
# required gates are green on the same staging SHA, opens (or re-uses)
|
||||
# a PR `staging → main` and enables auto-merge so the merge queue lands
|
||||
# it. Closes the gap that historically let features sit on staging for
|
||||
# weeks waiting for a bulk promotion PR (see molecule-core#1496 for the
|
||||
# 1172-commit example).
|
||||
#
|
||||
# 2026-04-28 rewrite (PR #142): the previous version did a direct
|
||||
# `git merge --ff-only origin staging && git push origin main`. That
|
||||
# breaks against main's branch-protection ruleset, which requires
|
||||
# status checks "set by the expected GitHub apps" — direct pushes
|
||||
# can't satisfy that condition (only PR merges through the queue can).
|
||||
# The workflow was failing every tick with:
|
||||
# remote: error: GH006: Protected branch update failed for refs/heads/main.
|
||||
# remote: - Required status checks ... were not set by the expected GitHub apps.
|
||||
# Fix: mirror the PR-based pattern from auto-sync-main-to-staging.yml
|
||||
# (the reverse-direction sync, fixed in #2234 for the same reason).
|
||||
# Both directions now use the same merge-queue path that humans use,
|
||||
# no special-case bypass.
|
||||
#
|
||||
# Safety model:
|
||||
# - Runs ONLY on workflow_run events for the staging branch.
|
||||
# - Requires EVERY named gate workflow to have the same head_sha and
|
||||
# all be `conclusion == success`. If any of them is red, skipped,
|
||||
# cancelled, or pending, we abort (stay on the current main).
|
||||
# - The PR base=main head=staging path lets GitHub itself enforce
|
||||
# branch protection. If main has diverged from staging or required
|
||||
# checks aren't satisfied, the merge queue declines the PR — no
|
||||
# need for a manual ff-only ancestry check here.
|
||||
# - Loop safety: the auto-sync-main-to-staging workflow fires when
|
||||
# main lands the auto-promote PR, but its merge into staging is by
|
||||
# GITHUB_TOKEN which doesn't trigger downstream workflow_run events
|
||||
# (GitHub Actions safety). So this workflow doesn't re-fire from
|
||||
# its own promote landing.
|
||||
#
|
||||
# Toggle via repo variable AUTO_PROMOTE_ENABLED (true/unset). When
|
||||
# unset, the workflow logs what it would have done but doesn't open
|
||||
# the PR — useful for dry-running the gate logic without surfacing
|
||||
# a noisy PR while staging CI is still flaky.
|
||||
#
|
||||
# **One-time repo setting (load-bearing):** this workflow opens the
|
||||
# staging→main PR via `gh pr create` using the default GITHUB_TOKEN.
|
||||
# Since GitHub's 2022 default change, that token cannot create or
|
||||
# approve PRs unless the repo opts in. The toggle is at:
|
||||
#
|
||||
# Settings → Actions → General → Workflow permissions
|
||||
# → ✅ Allow GitHub Actions to create and approve pull requests
|
||||
#
|
||||
# Without it, every workflow_run fails with:
|
||||
#
|
||||
# pull request create failed: GraphQL: GitHub Actions is not
|
||||
# permitted to create or approve pull requests (createPullRequest)
|
||||
#
|
||||
# Observed 2026-04-29 01:43 UTC blocking promotion of fcd87b9 (PRs
|
||||
# #2248 + #2249); manually bridged via PR #2252. Re-check this
|
||||
# setting if auto-promote starts failing with createPullRequest
|
||||
# errors after a repo or org admin change.
|
||||
|
||||
on:
|
||||
workflow_run:
|
||||
workflows:
|
||||
- CI
|
||||
- E2E Staging Canvas (Playwright)
|
||||
- E2E API Smoke Test
|
||||
- CodeQL
|
||||
types: [completed]
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
force:
|
||||
description: "Force promote even when AUTO_PROMOTE_ENABLED is unset (manual override)"
|
||||
required: false
|
||||
default: "false"
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
pull-requests: write
|
||||
# actions: write is needed by the post-merge dispatch tail step
|
||||
# (#2358 / #2357) — `gh workflow run publish-workspace-server-image.yml`
|
||||
# POSTs to /actions/workflows/.../dispatches which requires this scope.
|
||||
# Without it the call 403s and the publish/canary/redeploy chain still
|
||||
# doesn't run on staging→main promotions, undoing #2358.
|
||||
actions: write
|
||||
|
||||
# Serialize auto-promote runs. Multiple staging gate completions can land
|
||||
# in quick succession (CI + E2E + CodeQL all finish within seconds of
|
||||
# each other on a green PR) — without this, two parallel runs both:
|
||||
# 1. Open / re-use the same promote PR.
|
||||
# 2. Both call `gh pr merge --auto` (idempotent — fine).
|
||||
# 3. Both poll for the same mergedAt and both `gh workflow run` publish
|
||||
# → 2× redundant publish builds racing for the same `:staging-latest`
|
||||
# retag, and 2× canary-verify chains.
|
||||
# cancel-in-progress: false because we don't want a brand-new run to kill
|
||||
# a polling-tail that's about to dispatch — the polling tail's 30 min cap
|
||||
# is the right backstop, not workflow-level cancel.
|
||||
concurrency:
|
||||
group: auto-promote-staging
|
||||
cancel-in-progress: false
|
||||
|
||||
jobs:
|
||||
check-all-gates-green:
|
||||
# Only consider staging pushes. PRs into staging don't promote.
|
||||
if: >
|
||||
(github.event_name == 'workflow_run' &&
|
||||
github.event.workflow_run.head_branch == 'staging' &&
|
||||
github.event.workflow_run.event == 'push')
|
||||
|| github.event_name == 'workflow_dispatch'
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
all_green: ${{ steps.gates.outputs.all_green }}
|
||||
head_sha: ${{ steps.gates.outputs.head_sha }}
|
||||
steps:
|
||||
# Skip empty-tree promotes (the perpetual auto-promote↔auto-sync cycle
|
||||
# observed 2026-05-03). Sequence: auto-promote merges via the staging
|
||||
# merge-queue's MERGE strategy, creating a merge commit on main that
|
||||
# staging doesn't have. auto-sync then merges main back into staging
|
||||
# via another merge commit (the queue's MERGE strategy applies on
|
||||
# the staging side too, even when the workflow's local FF would
|
||||
# have sufficed). Now staging has a new merge-commit SHA whose
|
||||
# tree == main's tree — but auto-promote sees "staging ahead of
|
||||
# main by 1" and opens YET another empty promote PR. Each round
|
||||
# costs ~30-40 min wallclock, ~2 manual approvals, and burns a
|
||||
# full CodeQL Go run (~15 min). Without this guard the cycle
|
||||
# repeats indefinitely.
|
||||
#
|
||||
# Long-term fix is to switch the merge_queue ruleset's
|
||||
# `merge_method` away from MERGE so FF-able PRs land cleanly,
|
||||
# but that's a broader change affecting every staging PR's
|
||||
# commit shape. This guard is the one-line surgical fix that
|
||||
# breaks the cycle without touching merge-queue config.
|
||||
#
|
||||
# Fail-open: if `git diff` errors for any reason, fall through
|
||||
# to the gate check (preserve existing behavior). Only skip
|
||||
# when the diff is DEFINITIVELY empty.
|
||||
- name: Checkout for tree-diff check
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
fetch-depth: 0
|
||||
ref: staging
|
||||
- name: Skip if staging tree == main tree (perpetual-cycle break)
|
||||
id: tree-diff
|
||||
env:
|
||||
HEAD_SHA: ${{ github.event.workflow_run.head_sha || github.sha }}
|
||||
run: |
|
||||
set -eu
|
||||
git fetch origin main --depth=50 || { echo "::warning::git fetch main failed — proceeding (fail-open)"; exit 0; }
|
||||
# Compare staging tip's tree against main's tree. `git diff
|
||||
# --quiet` exits 0 if no differences, 1 if there are.
|
||||
if git diff --quiet origin/main "$HEAD_SHA" -- 2>/dev/null; then
|
||||
{
|
||||
echo "## ⏭ Skipped — no code to promote"
|
||||
echo
|
||||
echo "staging tip (\`${HEAD_SHA:0:8}\`) and \`main\` have identical trees."
|
||||
echo "This is the auto-promote↔auto-sync merge-commit cycle: staging has a"
|
||||
echo "new SHA (a sync-back merge commit) but the underlying file tree is"
|
||||
echo "already on main, so there's no real code to ship."
|
||||
echo
|
||||
echo "Skipping to avoid opening an empty promote PR. Cycle terminates here."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
echo "::notice::auto-promote: staging tree == main tree — no code to promote, skipping"
|
||||
echo "skip=true" >> "$GITHUB_OUTPUT"
|
||||
else
|
||||
echo "skip=false" >> "$GITHUB_OUTPUT"
|
||||
fi
|
||||
- name: Check all required gates on this SHA
|
||||
if: steps.tree-diff.outputs.skip != 'true'
|
||||
id: gates
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
HEAD_SHA: ${{ github.event.workflow_run.head_sha || github.sha }}
|
||||
REPO: ${{ github.repository }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
# Required gate workflow files. Use file paths (relative to
|
||||
# .github/workflows/) rather than display names because:
|
||||
#
|
||||
# 1. `gh run list --workflow=<name>` is ambiguous when two
|
||||
# workflows have the same `name:` — observed 2026-04-28
|
||||
# with "CodeQL" matching both `codeql.yml` (explicit) and
|
||||
# GitHub's UI-configured Code-quality default setup
|
||||
# (internal "codeql"). gh CLI returns "could not resolve
|
||||
# to a unique workflow" → empty result → gate evaluated
|
||||
# as missing/none → auto-promote dead-locked despite all
|
||||
# checks actually passing.
|
||||
#
|
||||
# 2. File paths are the unique identifier for workflows;
|
||||
# `name:` is just a display string and can collide.
|
||||
#
|
||||
# When adding/removing a gate, update this list AND the
|
||||
# branch-protection required-checks list (which uses check-run
|
||||
# display names, not workflow names; the two are decoupled and
|
||||
# should be kept in sync manually).
|
||||
GATES=(
|
||||
"ci.yml"
|
||||
"e2e-staging-canvas.yml"
|
||||
"e2e-api.yml"
|
||||
"codeql.yml"
|
||||
)
|
||||
|
||||
echo "head_sha=${HEAD_SHA}" >> "$GITHUB_OUTPUT"
|
||||
echo "Checking gates on SHA ${HEAD_SHA}"
|
||||
|
||||
ALL_GREEN=true
|
||||
for gate in "${GATES[@]}"; do
|
||||
# Query the most recent run of this workflow on this SHA.
|
||||
# event=push to avoid picking up PR runs. branch=staging to
|
||||
# guard against someone dispatching the gate on a non-staging
|
||||
# branch at the same SHA.
|
||||
RESULT=$(gh run list \
|
||||
--repo "$REPO" \
|
||||
--workflow "$gate" \
|
||||
--branch staging \
|
||||
--event push \
|
||||
--commit "$HEAD_SHA" \
|
||||
--limit 1 \
|
||||
--json status,conclusion \
|
||||
--jq '.[0] | "\(.status)/\(.conclusion // "none")"' \
|
||||
2>/dev/null || echo "missing/none")
|
||||
|
||||
echo " $gate → $RESULT"
|
||||
|
||||
# Only completed/success counts. completed/failure or
|
||||
# in_progress/anything or no record at all = abort.
|
||||
if [ "$RESULT" != "completed/success" ]; then
|
||||
ALL_GREEN=false
|
||||
fi
|
||||
done
|
||||
|
||||
echo "all_green=${ALL_GREEN}" >> "$GITHUB_OUTPUT"
|
||||
if [ "$ALL_GREEN" != "true" ]; then
|
||||
echo "::notice::auto-promote: not all gates are green on ${HEAD_SHA} — staying on current main"
|
||||
fi
|
||||
|
||||
promote:
|
||||
needs: check-all-gates-green
|
||||
if: needs.check-all-gates-green.outputs.all_green == 'true'
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Check rollout gate
|
||||
env:
|
||||
AUTO_PROMOTE_ENABLED: ${{ vars.AUTO_PROMOTE_ENABLED }}
|
||||
FORCE_INPUT: ${{ github.event.inputs.force }}
|
||||
run: |
|
||||
set -eu
|
||||
# Repo variable AUTO_PROMOTE_ENABLED=true flips this on. While
|
||||
# it's unset, the workflow dry-runs (logs what it would have
|
||||
# done) but doesn't open the promote PR. Set the variable in
|
||||
# Settings → Secrets and variables → Actions → Variables.
|
||||
if [ "${AUTO_PROMOTE_ENABLED:-}" != "true" ] && [ "${FORCE_INPUT:-false}" != "true" ]; then
|
||||
{
|
||||
echo "## ⏸ Auto-promote disabled"
|
||||
echo
|
||||
echo "Repo variable \`AUTO_PROMOTE_ENABLED\` is not set to \`true\`."
|
||||
echo "All gates are green on staging; would have opened a promote PR to \`main\`."
|
||||
echo
|
||||
echo "To enable: Settings → Secrets and variables → Actions → Variables → \`AUTO_PROMOTE_ENABLED=true\`."
|
||||
echo "To test once manually: workflow_dispatch with \`force=true\`."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
echo "::notice::auto-promote disabled — dry run only"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Mint the App token BEFORE the promote-PR step so the auto-merge
|
||||
# call can use it. GITHUB_TOKEN-initiated merges suppress the
|
||||
# downstream `push` event on main, breaking the
|
||||
# publish-workspace-server-image → canary-verify → redeploy-tenants
|
||||
# chain (issue #2357). Using the App token here means the
|
||||
# merge-queue-landed merge IS able to fire the cascade naturally;
|
||||
# the polling tail below stays as defense-in-depth.
|
||||
- name: Mint App token for promote-PR + downstream dispatch
|
||||
if: ${{ vars.AUTO_PROMOTE_ENABLED == 'true' || github.event.inputs.force == 'true' }}
|
||||
id: app-token
|
||||
uses: actions/create-github-app-token@1b10c78c7865c340bc4f6099eb2f838309f1e8c3 # v3.1.1
|
||||
with:
|
||||
app-id: ${{ secrets.MOLECULE_AI_APP_ID }}
|
||||
private-key: ${{ secrets.MOLECULE_AI_APP_PRIVATE_KEY }}
|
||||
|
||||
- name: Open (or reuse) staging → main promote PR + enable auto-merge
|
||||
if: ${{ vars.AUTO_PROMOTE_ENABLED == 'true' || github.event.inputs.force == 'true' }}
|
||||
env:
|
||||
GH_TOKEN: ${{ steps.app-token.outputs.token }}
|
||||
REPO: ${{ github.repository }}
|
||||
TARGET_SHA: ${{ needs.check-all-gates-green.outputs.head_sha }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
# Look for an existing open promote PR (idempotent on re-run
|
||||
# of the workflow). The PR's head IS the staging branch — the
|
||||
# whole point is "advance main to staging's tip", so we don't
|
||||
# need a per-SHA branch like auto-sync-main-to-staging uses.
|
||||
PR_NUM=$(gh pr list --repo "$REPO" \
|
||||
--base main --head staging --state open \
|
||||
--json number --jq '.[0].number // ""')
|
||||
|
||||
if [ -z "$PR_NUM" ]; then
|
||||
TITLE="staging → main: auto-promote ${TARGET_SHA:0:7}"
|
||||
BODY_FILE=$(mktemp)
|
||||
cat > "$BODY_FILE" <<EOFBODY
|
||||
Automated promotion of \`staging\` (\`${TARGET_SHA:0:8}\`) to \`main\`. All required staging gates green at this SHA: CI, E2E Staging Canvas, E2E API Smoke, CodeQL.
|
||||
|
||||
This PR is auto-generated by \`.github/workflows/auto-promote-staging.yml\` whenever every required gate completes green on the same staging SHA. It exists because main's branch protection requires status checks "set by the expected GitHub apps" — direct \`git push\` from a workflow can't satisfy that, only PR merges through the queue can.
|
||||
|
||||
Merge queue lands this; no human action needed unless gates fail. Reverse-direction sync (the merge commit on main → staging) is handled by \`auto-sync-main-to-staging.yml\`.
|
||||
EOFBODY
|
||||
PR_URL=$(gh pr create --repo "$REPO" \
|
||||
--base main --head staging \
|
||||
--title "$TITLE" \
|
||||
--body-file "$BODY_FILE")
|
||||
PR_NUM=$(echo "$PR_URL" | grep -oE '[0-9]+$' | tail -1)
|
||||
rm -f "$BODY_FILE"
|
||||
echo "::notice::Opened PR #${PR_NUM}"
|
||||
else
|
||||
echo "::notice::Re-using existing promote PR #${PR_NUM}"
|
||||
fi
|
||||
|
||||
# Enable auto-merge — the merge queue picks it up once
|
||||
# required gates are green on the merge_group ref.
|
||||
if ! gh pr merge "$PR_NUM" --repo "$REPO" --auto --merge 2>&1; then
|
||||
echo "::warning::Failed to enable auto-merge on PR #${PR_NUM} — operator may need to merge manually."
|
||||
fi
|
||||
|
||||
{
|
||||
echo "## ✅ Auto-promote PR opened"
|
||||
echo
|
||||
echo "- Source: staging at \`${TARGET_SHA:0:8}\`"
|
||||
echo "- PR: #${PR_NUM}"
|
||||
echo
|
||||
echo "Merge queue lands the PR once required gates are green; no human action needed unless gates fail."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
|
||||
# Hand the PR number to the next step so we can dispatch the
|
||||
# tenant-redeploy chain after the merge queue lands the merge.
|
||||
echo "promote_pr_num=${PR_NUM}" >> "$GITHUB_OUTPUT"
|
||||
id: promote_pr
|
||||
|
||||
# The App token minted above (before the promote-PR step) is
|
||||
# also used by the polling tail below. Defense-in-depth: with
|
||||
# the merge-queue-landed merge now using the App token, the
|
||||
# main-branch push event SHOULD fire the publish/canary/redeploy
|
||||
# cascade naturally — but if for any reason it doesn't (e.g. an
|
||||
# unrelated event-suppression edge case), the explicit dispatches
|
||||
# below still wake the chain.
|
||||
- name: Wait for promote merge, then dispatch publish + redeploy (#2357)
|
||||
# Defense-in-depth dispatch. With the auto-merge call above
|
||||
# now using the App token (this commit), the merge-queue-landed
|
||||
# merge SHOULD fire publish-workspace-server-image naturally
|
||||
# via on:push:[main] — App-token-initiated pushes DO trigger
|
||||
# workflow_run cascades, unlike GITHUB_TOKEN-initiated ones
|
||||
# (the documented "no recursion" rule —
|
||||
# https://docs.github.com/en/actions/using-workflows/triggering-a-workflow#triggering-a-workflow-from-a-workflow).
|
||||
#
|
||||
# This explicit dispatch stays as belt-and-suspenders for any
|
||||
# edge case where the natural cascade misfires. If it never
|
||||
# observably fires after this token swap (i.e. the publish
|
||||
# workflow has already started by the time we get here), the
|
||||
# second dispatch is a harmless no-op (publish-workspace-server-image
|
||||
# has its own concurrency group that dedupes).
|
||||
#
|
||||
# See PR for #2357: pre-fix the merge action was via
|
||||
# GITHUB_TOKEN, suppressing the cascade and forcing this tail
|
||||
# to be the SOLE chain trigger. With the auto-merge token swap
|
||||
# the tail becomes redundant in the happy path; keep until
|
||||
# we've observed >=10 successful natural cascades, then drop.
|
||||
if: steps.promote_pr.outputs.promote_pr_num != ''
|
||||
env:
|
||||
GH_TOKEN: ${{ steps.app-token.outputs.token }}
|
||||
REPO: ${{ github.repository }}
|
||||
PR_NUM: ${{ steps.promote_pr.outputs.promote_pr_num }}
|
||||
run: |
|
||||
# Poll for merge — max 30 min (60 × 30s). The merge queue
|
||||
# typically lands within 5-10 min when gates are green. Break
|
||||
# early if the PR is closed without merging (operator action,
|
||||
# gates flipped red post-approval, branch-protection rejection)
|
||||
# so we don't tie up a runner for the full 30 min on a dead PR.
|
||||
MERGED=""
|
||||
STATE=""
|
||||
for _ in $(seq 1 60); do
|
||||
VIEW=$(gh pr view "$PR_NUM" --repo "$REPO" --json mergedAt,state)
|
||||
MERGED=$(echo "$VIEW" | jq -r '.mergedAt // ""')
|
||||
STATE=$(echo "$VIEW" | jq -r '.state // ""')
|
||||
if [ -n "$MERGED" ] && [ "$MERGED" != "null" ]; then
|
||||
echo "::notice::Promote PR #${PR_NUM} merged at ${MERGED}"
|
||||
break
|
||||
fi
|
||||
if [ "$STATE" = "CLOSED" ]; then
|
||||
echo "::warning::Promote PR #${PR_NUM} was closed without merging — skipping deploy dispatch."
|
||||
exit 0
|
||||
fi
|
||||
sleep 30
|
||||
done
|
||||
|
||||
if [ -z "$MERGED" ] || [ "$MERGED" = "null" ]; then
|
||||
echo "::warning::Promote PR #${PR_NUM} didn't merge within 30min — skipping deploy dispatch (manually run \`gh workflow run publish-workspace-server-image.yml --ref main\` once it lands)."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Dispatch publish on main using the App token. App-initiated
|
||||
# workflow_dispatch DOES propagate the workflow_run cascade,
|
||||
# unlike GITHUB_TOKEN-initiated dispatch.
|
||||
# publish completes → canary-verify chains via workflow_run →
|
||||
# redeploy-tenants-on-main chains via workflow_run + branches:[main].
|
||||
if gh workflow run publish-workspace-server-image.yml \
|
||||
--repo "$REPO" --ref main 2>&1; then
|
||||
echo "::notice::Dispatched publish-workspace-server-image on ref=main as molecule-ai App — canary-verify and redeploy-tenants-on-main will chain via workflow_run."
|
||||
{
|
||||
echo "## 🚀 Tenant redeploy chain dispatched"
|
||||
echo
|
||||
echo "- publish-workspace-server-image (workflow_dispatch on \`main\`, actor: \`molecule-ai[bot]\`)"
|
||||
echo "- canary-verify will chain on completion"
|
||||
echo "- redeploy-tenants-on-main will chain on canary green"
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
else
|
||||
echo "::error::Failed to dispatch publish-workspace-server-image. Run manually: gh workflow run publish-workspace-server-image.yml --ref main"
|
||||
fi
|
||||
|
||||
# ALSO dispatch auto-sync-main-to-staging.yml. Same root cause as
|
||||
# publish above (issue #2357): the merge-queue-initiated push to
|
||||
# main is by GITHUB_TOKEN → no `on: push` triggers fire downstream.
|
||||
# Without this dispatch, every staging→main promote leaves staging
|
||||
# one merge commit BEHIND main, which silently dead-locks the NEXT
|
||||
# promote PR as `mergeStateStatus: BEHIND` because main's
|
||||
# branch-protection has `strict: true`. Verified empirically on
|
||||
# 2026-05-02 against PR #2442 (Phase 2 promote): only the explicit
|
||||
# publish-workspace-server-image dispatch fired on the previous
|
||||
# promote SHA 76c604fb, while auto-sync silently no-op'd, leaving
|
||||
# staging behind for ~24h until manually bridged.
|
||||
if gh workflow run auto-sync-main-to-staging.yml \
|
||||
--repo "$REPO" --ref main 2>&1; then
|
||||
echo "::notice::Dispatched auto-sync-main-to-staging on ref=main as molecule-ai App — staging will absorb the new main merge commit via PR + merge queue."
|
||||
else
|
||||
echo "::error::Failed to dispatch auto-sync-main-to-staging. Run manually: gh workflow run auto-sync-main-to-staging.yml --ref main"
|
||||
fi
|
||||
83
.github/workflows/auto-promote-stale-alarm.yml
vendored
Normal file
83
.github/workflows/auto-promote-stale-alarm.yml
vendored
Normal file
@ -0,0 +1,83 @@
|
||||
name: auto-promote-stale-alarm
|
||||
|
||||
# Hourly cron + on-demand alarm for the silent-block failure mode that
|
||||
# motivated issue #2975:
|
||||
# - The auto-promote-staging.yml workflow opened a PR + armed
|
||||
# auto-merge, but main's branch protection requires a human review
|
||||
# (reviewDecision=REVIEW_REQUIRED). The PR sat BLOCKED with no
|
||||
# surface-up-the-stack for 12+ hours, holding 25 commits hostage
|
||||
# including the Memory v2 redesign and a reno-stars data-loss fix.
|
||||
#
|
||||
# This workflow runs `scripts/check-stale-promote-pr.sh` against the
|
||||
# repo's open auto-promote PRs (base=main head=staging). When a PR has
|
||||
# been BLOCKED on REVIEW_REQUIRED for >4h, it:
|
||||
# 1. Emits a workflow-level warning (visible in run summary + the
|
||||
# Actions UI feed).
|
||||
# 2. Posts a comment on the PR (idempotent — one alarm per PR).
|
||||
#
|
||||
# The detection logic lives in scripts/check-stale-promote-pr.sh so
|
||||
# it's unit-testable with stubbed `gh` (see test-check-stale-promote-pr.sh).
|
||||
# This file is the schedule + invocation surface only — SSOT for the
|
||||
# detector itself.
|
||||
|
||||
on:
|
||||
schedule:
|
||||
# Hourly. Cheap (one `gh pr list` + jq), and 1h granularity is
|
||||
# plenty for a 4h staleness threshold — operators see the alarm
|
||||
# within at most 1h of crossing the threshold.
|
||||
- cron: "27 * * * *" # at :27 to dodge the cron herd at :00
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
stale_hours:
|
||||
description: "Hours after which a BLOCKED+REVIEW_REQUIRED PR is stale (default 4)"
|
||||
required: false
|
||||
default: "4"
|
||||
post_comment:
|
||||
description: "Post a comment on stale PRs (default true)"
|
||||
required: false
|
||||
default: "true"
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
pull-requests: write # post comments on stale PRs
|
||||
|
||||
# Serialize so the on-demand and scheduled runs don't double-comment
|
||||
# the same PR. cancel-in-progress=false because the script is idempotent
|
||||
# (existing comment marker prevents dupes), but a scheduled run firing
|
||||
# while a manual one runs would just re-list the same PR set.
|
||||
concurrency:
|
||||
group: auto-promote-stale-alarm
|
||||
cancel-in-progress: false
|
||||
|
||||
jobs:
|
||||
scan:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout (need scripts/ only)
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
sparse-checkout: |
|
||||
scripts/check-stale-promote-pr.sh
|
||||
sparse-checkout-cone-mode: false
|
||||
- name: Run stale-PR detector
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
GITHUB_REPOSITORY: ${{ github.repository }}
|
||||
STALE_HOURS: ${{ inputs.stale_hours || '4' }}
|
||||
POST_COMMENT: ${{ inputs.post_comment || 'true' }}
|
||||
run: |
|
||||
# The script's exit code reflects the count of stale PRs.
|
||||
# We don't want a stale finding to fail the workflow run —
|
||||
# the warning + comment are the signal, the green/red is
|
||||
# noise. So convert any non-zero exit to a workflow notice
|
||||
# and exit 0.
|
||||
set +e
|
||||
bash scripts/check-stale-promote-pr.sh
|
||||
rc=$?
|
||||
set -e
|
||||
if [ "$rc" -ne 0 ]; then
|
||||
echo "::notice::Stale PR detector found $rc PR(s) needing attention. See warnings above + comments on the PRs."
|
||||
fi
|
||||
# Always succeed — operator-facing surface is the warning,
|
||||
# not the workflow status.
|
||||
exit 0
|
||||
237
.github/workflows/auto-sync-main-to-staging.yml
vendored
Normal file
237
.github/workflows/auto-sync-main-to-staging.yml
vendored
Normal file
@ -0,0 +1,237 @@
|
||||
name: Auto-sync main → staging
|
||||
|
||||
# Reflects every push to `main` back onto `staging` so the
|
||||
# staging-as-superset-of-main invariant holds.
|
||||
#
|
||||
# Background:
|
||||
#
|
||||
# `auto-promote-staging.yml` advances main via `git merge --ff-only`
|
||||
# + `git push origin main` — that's a clean fast-forward, no merge
|
||||
# commit. But manual merges of `staging → main` PRs through the
|
||||
# GitHub UI / API create a merge commit on main that staging
|
||||
# doesn't have. The next `staging → main` PR then evaluates as
|
||||
# "BEHIND" because staging is missing that merge commit, requiring
|
||||
# a manual `gh pr update-branch` round-trip.
|
||||
#
|
||||
# This happened twice on 2026-04-28 (PRs #2202, #2205, both manual
|
||||
# bridges). Each time the bridge needed update-branch + a re-CI
|
||||
# round before merging. Operationally annoying and avoidable.
|
||||
#
|
||||
# Architecture:
|
||||
#
|
||||
# This repo's `staging` branch is protected by a `merge_queue`
|
||||
# ruleset (id 15500102) that blocks ALL direct pushes — no bypass
|
||||
# even for org admins or the GitHub Actions integration. Direct
|
||||
# `git push origin staging` returns GH013. So instead of pushing
|
||||
# directly, this workflow:
|
||||
#
|
||||
# 1. Checks if main is already in staging's ancestry → no-op.
|
||||
# 2. Creates an `auto-sync/main-<sha>` branch from staging.
|
||||
# 3. Tries `git merge --ff-only origin/main` → if staging hasn't
|
||||
# diverged this is a clean ff.
|
||||
# 4. Otherwise `git merge --no-ff origin/main` to absorb main's
|
||||
# tip while keeping staging's history.
|
||||
# 5. Pushes the auto-sync branch.
|
||||
# 6. Opens a PR (base=staging, head=auto-sync/main-<sha>) and
|
||||
# enables auto-merge so the merge queue lands it.
|
||||
#
|
||||
# This mirrors the path human PRs take through staging — same
|
||||
# rules, same gates, no special-case bypass.
|
||||
#
|
||||
# Loop safety:
|
||||
#
|
||||
# `GITHUB_TOKEN`-authored merges (including the merge queue's land
|
||||
# of the auto-sync PR) do NOT trigger downstream workflow runs
|
||||
# (GitHub Actions safety). So when the auto-sync PR lands on
|
||||
# staging, `auto-promote-staging.yml` is NOT triggered by that
|
||||
# push. The next developer push to staging triggers auto-promote
|
||||
# normally. No loop possible.
|
||||
#
|
||||
# Concurrency:
|
||||
#
|
||||
# Two pushes to main in quick succession (e.g., manual UI merge
|
||||
# immediately followed by auto-promote-staging's ff-merge) could
|
||||
# otherwise open two overlapping auto-sync PRs. The concurrency
|
||||
# group serializes runs; the second waits for the first to exit.
|
||||
# (The first run exits after opening + auto-merge-queueing the PR,
|
||||
# not after the merge actually completes — so multiple PRs can be
|
||||
# open simultaneously, but the merge queue handles them serially.)
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
# workflow_dispatch lets:
|
||||
# 1. Operators manually backfill a missed sync (e.g. after a manual
|
||||
# UI merge that the runner missed).
|
||||
# 2. auto-promote-staging.yml's polling tail explicitly invoke us
|
||||
# after the promote PR lands. This is load-bearing: when the
|
||||
# merge queue lands a promote-PR merge, the resulting push to
|
||||
# `main` is "by GITHUB_TOKEN", and per GitHub's no-recursion
|
||||
# rule (https://docs.github.com/en/actions/using-workflows/triggering-a-workflow#triggering-a-workflow-from-a-workflow)
|
||||
# that push event does NOT fire any downstream workflows. The
|
||||
# `on: push` trigger above is silently dead for the very pattern
|
||||
# we exist to handle. Verified empirically 2026-05-02 against
|
||||
# SHA 76c604fb (PR #2437 staging→main): only ONE workflow fired
|
||||
# (publish-workspace-server-image, dispatched explicitly by
|
||||
# auto-promote's polling tail with an App token). Every other
|
||||
# `on: push: branches: [main]` workflow — including this one —
|
||||
# was suppressed. Until the underlying merge call moves to an
|
||||
# App token, an explicit dispatch is the only reliable path.
|
||||
workflow_dispatch:
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
pull-requests: write
|
||||
|
||||
concurrency:
|
||||
group: auto-sync-main-to-staging
|
||||
cancel-in-progress: false
|
||||
|
||||
jobs:
|
||||
sync-staging:
|
||||
# ubuntu-latest matches every other workflow in this repo. The
|
||||
# earlier `[self-hosted, macos, arm64]` was a copy-paste artefact
|
||||
# from the molecule-controlplane repo (which IS private and uses a
|
||||
# Mac runner) — molecule-core has no Mac runner registered, so the
|
||||
# job sat unassigned whenever the trigger fired. Verified 2026-05-02:
|
||||
# this is the ONLY workflow in molecule-core/.github/workflows/ with
|
||||
# a non-ubuntu runs-on.
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout staging
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
with:
|
||||
fetch-depth: 0
|
||||
ref: staging
|
||||
token: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Configure git author
|
||||
run: |
|
||||
git config user.name "github-actions[bot]"
|
||||
git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
|
||||
|
||||
- name: Check if staging already contains main
|
||||
id: check
|
||||
run: |
|
||||
set -euo pipefail
|
||||
git fetch origin main
|
||||
if git merge-base --is-ancestor origin/main HEAD; then
|
||||
echo "needs_sync=false" >> "$GITHUB_OUTPUT"
|
||||
{
|
||||
echo "## ✅ No-op"
|
||||
echo
|
||||
echo "staging already contains \`origin/main\` ($(git rev-parse --short=8 origin/main))."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
else
|
||||
echo "needs_sync=true" >> "$GITHUB_OUTPUT"
|
||||
MAIN_SHORT=$(git rev-parse --short=8 origin/main)
|
||||
echo "main_short=${MAIN_SHORT}" >> "$GITHUB_OUTPUT"
|
||||
echo "branch=auto-sync/main-${MAIN_SHORT}" >> "$GITHUB_OUTPUT"
|
||||
echo "::notice::staging is missing main's tip (${MAIN_SHORT}) — opening sync PR"
|
||||
fi
|
||||
|
||||
- name: Create auto-sync branch + merge main
|
||||
if: steps.check.outputs.needs_sync == 'true'
|
||||
id: prep
|
||||
run: |
|
||||
set -euo pipefail
|
||||
BRANCH="${{ steps.check.outputs.branch }}"
|
||||
|
||||
# If a previous auto-sync run already opened a branch for the
|
||||
# same main sha, prefer reusing it (idempotent behavior on
|
||||
# workflow restart). Force-update from latest staging anyway
|
||||
# so it absorbs any staging-side commits that landed since.
|
||||
git checkout -B "$BRANCH"
|
||||
|
||||
if git merge --ff-only origin/main; then
|
||||
echo "did_ff=true" >> "$GITHUB_OUTPUT"
|
||||
echo "::notice::Fast-forwarded ${BRANCH} to origin/main"
|
||||
else
|
||||
echo "did_ff=false" >> "$GITHUB_OUTPUT"
|
||||
if ! git merge --no-ff origin/main -m "chore: sync main → staging (auto)"; then
|
||||
# Hygiene: leave the work tree clean before failing.
|
||||
git merge --abort || true
|
||||
{
|
||||
echo "## ❌ Conflict"
|
||||
echo
|
||||
echo "Auto-merge \`main → staging\` failed with conflicts."
|
||||
echo "A human needs to resolve manually."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
|
||||
- name: Push auto-sync branch
|
||||
if: steps.check.outputs.needs_sync == 'true'
|
||||
run: |
|
||||
set -euo pipefail
|
||||
# Force-with-lease so a concurrent auto-sync run can't
|
||||
# silently clobber an in-flight branch we just updated. If a
|
||||
# different writer touched the branch, we abort and the next
|
||||
# run picks up the latest state.
|
||||
git push --force-with-lease origin "${{ steps.check.outputs.branch }}"
|
||||
|
||||
- name: Open auto-sync PR + enable auto-merge
|
||||
if: steps.check.outputs.needs_sync == 'true'
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
BRANCH: ${{ steps.check.outputs.branch }}
|
||||
MAIN_SHORT: ${{ steps.check.outputs.main_short }}
|
||||
DID_FF: ${{ steps.prep.outputs.did_ff }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
# Find existing PR for this branch (idempotent on workflow
|
||||
# restart) before creating a new one.
|
||||
PR_NUM=$(gh pr list --head "$BRANCH" --base staging --state open --json number --jq '.[0].number // ""')
|
||||
|
||||
if [ -z "$PR_NUM" ]; then
|
||||
# Body lives in a temp file to keep the multi-line content
|
||||
# out of the YAML block scalar (un-indented newlines inside
|
||||
# an inline shell string break YAML parsing).
|
||||
BODY_FILE=$(mktemp)
|
||||
if [ "$DID_FF" = "true" ]; then
|
||||
TITLE="chore: sync main → staging (auto, ff to ${MAIN_SHORT})"
|
||||
cat > "$BODY_FILE" <<EOFBODY
|
||||
Automated fast-forward of \`staging\` to \`origin/main\` (\`${MAIN_SHORT}\`). Staging has no in-flight commits that diverge from main. Merge queue lands this; no human action needed.
|
||||
|
||||
This PR is auto-generated by \`.github/workflows/auto-sync-main-to-staging.yml\` on every push to \`main\`. It exists because this repo's \`staging\` branch has a \`merge_queue\` ruleset that blocks direct pushes — even from the GitHub Actions integration.
|
||||
EOFBODY
|
||||
else
|
||||
TITLE="chore: sync main → staging (auto, merge ${MAIN_SHORT})"
|
||||
cat > "$BODY_FILE" <<EOFBODY
|
||||
Automated merge of \`origin/main\` (\`${MAIN_SHORT}\`) into \`staging\`. Staging has commits main doesn't, so this is a non-ff merge that absorbs main's tip. Merge queue lands this.
|
||||
|
||||
This PR is auto-generated by \`.github/workflows/auto-sync-main-to-staging.yml\` on every push to \`main\`.
|
||||
EOFBODY
|
||||
fi
|
||||
|
||||
# gh pr create prints the URL on stdout; extract the PR number.
|
||||
PR_URL=$(gh pr create \
|
||||
--base staging \
|
||||
--head "$BRANCH" \
|
||||
--title "$TITLE" \
|
||||
--body-file "$BODY_FILE")
|
||||
PR_NUM=$(echo "$PR_URL" | grep -oE '[0-9]+$' | tail -1)
|
||||
rm -f "$BODY_FILE"
|
||||
echo "::notice::Opened PR #${PR_NUM}"
|
||||
else
|
||||
echo "::notice::Re-using existing PR #${PR_NUM} for ${BRANCH}"
|
||||
fi
|
||||
|
||||
# Enable auto-merge — the merge queue picks it up once
|
||||
# required gates are green. Use --merge for merge commits
|
||||
# (matches the rest of this repo's PR convention).
|
||||
if ! gh pr merge "$PR_NUM" --auto --merge 2>&1; then
|
||||
echo "::warning::Failed to enable auto-merge on PR #${PR_NUM} — operator may need to merge manually."
|
||||
fi
|
||||
|
||||
{
|
||||
echo "## ✅ Auto-sync PR opened"
|
||||
echo
|
||||
echo "- Branch: \`$BRANCH\`"
|
||||
echo "- PR: #$PR_NUM"
|
||||
echo "- Strategy: $([ "$DID_FF" = "true" ] && echo "ff" || echo "merge commit")"
|
||||
echo
|
||||
echo "Merge queue lands the PR once required gates are green; no human action needed unless gates fail."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
37
.github/workflows/auto-tag-runtime.yml
vendored
37
.github/workflows/auto-tag-runtime.yml
vendored
@ -57,42 +57,17 @@ jobs:
|
||||
id: bump
|
||||
if: steps.skip.outputs.skip != 'true'
|
||||
env:
|
||||
# Gitea-shape token (act_runner forwards GITHUB_TOKEN as a
|
||||
# short-lived per-run secret with read access to this repo).
|
||||
# We hit `/api/v1/repos/.../pulls?state=closed` directly
|
||||
# because `gh pr list` calls Gitea's GraphQL endpoint, which
|
||||
# returns HTTP 405 (issue #75 / post-#66 sweep).
|
||||
GITEA_TOKEN: ${{ github.token }}
|
||||
REPO: ${{ github.repository }}
|
||||
GITEA_API_URL: ${{ github.server_url }}/api/v1
|
||||
PUSH_SHA: ${{ github.sha }}
|
||||
GH_TOKEN: ${{ github.token }}
|
||||
run: |
|
||||
# Find the merged PR whose merge_commit_sha matches this push.
|
||||
# Gitea's `/repos/{owner}/{repo}/pulls?state=closed` returns
|
||||
# PRs sorted newest-first; we paginate up to 50 and jq-filter
|
||||
# on `merge_commit_sha == PUSH_SHA`. Bounded — auto-tag fires
|
||||
# per push to main, so the matching PR is always among the
|
||||
# most recent closures. 50 is comfortably more than the
|
||||
# ~10-20 staging→main promotes that close in any reasonable
|
||||
# window.
|
||||
set -euo pipefail
|
||||
PRS_JSON=$(curl --fail-with-body -sS \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Accept: application/json" \
|
||||
"${GITEA_API_URL}/repos/${REPO}/pulls?state=closed&sort=newest&limit=50" \
|
||||
2>/dev/null || echo "[]")
|
||||
PR=$(printf '%s' "$PRS_JSON" \
|
||||
| jq -c --arg sha "$PUSH_SHA" \
|
||||
'[.[] | select(.merged_at != null and .merge_commit_sha == $sha)] | .[0] // empty')
|
||||
# The merged PR for this push commit. `gh pr list --search` finds
|
||||
# closed PRs whose merge commit matches; we take the first.
|
||||
PR=$(gh pr list --state merged --search "${{ github.sha }}" --json number,labels --jq '.[0]' 2>/dev/null || echo "")
|
||||
if [ -z "$PR" ] || [ "$PR" = "null" ]; then
|
||||
echo "No merged PR found for ${PUSH_SHA} — defaulting to patch bump."
|
||||
echo "No merged PR found for ${{ github.sha }} — defaulting to patch bump."
|
||||
echo "kind=patch" >> "$GITHUB_OUTPUT"
|
||||
exit 0
|
||||
fi
|
||||
# Gitea returns labels under `.labels[].name`, same shape as
|
||||
# GitHub's REST. The previous `gh pr list --json number,labels`
|
||||
# output was identical; jq filter unchanged.
|
||||
LABELS=$(printf '%s' "$PR" | jq -r '.labels[]?.name // empty')
|
||||
LABELS=$(echo "$PR" | jq -r '.labels[].name')
|
||||
if echo "$LABELS" | grep -qx 'release:major'; then
|
||||
echo "kind=major" >> "$GITHUB_OUTPUT"
|
||||
elif echo "$LABELS" | grep -qx 'release:minor'; then
|
||||
|
||||
30
.github/workflows/branch-protection-drift.yml
vendored
30
.github/workflows/branch-protection-drift.yml
vendored
@ -19,7 +19,6 @@ on:
|
||||
branches: [staging, main]
|
||||
paths:
|
||||
- 'tools/branch-protection/**'
|
||||
- '.github/workflows/**'
|
||||
- '.github/workflows/branch-protection-drift.yml'
|
||||
|
||||
permissions:
|
||||
@ -80,32 +79,3 @@ jobs:
|
||||
# Repo-admin scope, needed for /branches/:b/protection.
|
||||
GH_TOKEN: ${{ secrets.GH_TOKEN_FOR_ADMIN_API }}
|
||||
run: bash tools/branch-protection/drift_check.sh
|
||||
|
||||
# Self-test the parity script before running it on the real
|
||||
# workflows — pins the script's classification logic against
|
||||
# synthetic safe/unsafe/missing/unsafe-mix/matrix fixtures so a
|
||||
# regression in the script can't false-pass on the production
|
||||
# workflow audit. Cheap (~0.5s); always runs.
|
||||
- name: Self-test check-name parity script
|
||||
run: bash tools/branch-protection/test_check_name_parity.sh
|
||||
|
||||
# Check-name parity gate (#144 / saved memory
|
||||
# feedback_branch_protection_check_name_parity).
|
||||
#
|
||||
# drift_check.sh asserts the live branch protection matches what
|
||||
# apply.sh would set; check_name_parity.sh closes the orthogonal
|
||||
# gap: it asserts every required check name in apply.sh maps to a
|
||||
# workflow job whose "always emits this status" shape is intact.
|
||||
#
|
||||
# The two checks fail in different scenarios:
|
||||
#
|
||||
# - drift_check fails → live state was rewritten out-of-band
|
||||
# (UI click, manual PATCH).
|
||||
# - check_name_parity fails → an apply.sh required name has no
|
||||
# emitter, OR the emitting workflow has a top-level paths:
|
||||
# filter without per-step if-gates (the silent-block shape).
|
||||
#
|
||||
# Cheap (~1s); runs without the admin token because it only reads
|
||||
# apply.sh + .github/workflows/ from the checkout.
|
||||
- name: Run check-name parity gate
|
||||
run: bash tools/branch-protection/check_name_parity.sh
|
||||
|
||||
82
.github/workflows/canary-staging.yml
vendored
82
.github/workflows/canary-staging.yml
vendored
@ -20,19 +20,6 @@ on:
|
||||
# a few minutes under load — that's fine for a canary.
|
||||
- cron: '*/30 * * * *'
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
keep_on_failure:
|
||||
description: >-
|
||||
Skip teardown when the canary fails (debugging only). The
|
||||
tenant org + EC2 + CF tunnel + DNS stay alive so an operator
|
||||
can SSM into the workspace EC2 and capture docker logs of the
|
||||
failing claude-code container. REMEMBER to manually delete
|
||||
via DELETE /cp/admin/tenants/<slug> when done so the org
|
||||
doesn't accumulate cost. Only honored on workflow_dispatch;
|
||||
cron runs always tear down (we don't want unattended cron
|
||||
to leak resources).
|
||||
type: boolean
|
||||
default: false
|
||||
|
||||
# Serialise with the full-SaaS workflow so they don't contend for the
|
||||
# same org-create quota on staging. Different group key from
|
||||
@ -93,14 +80,6 @@ jobs:
|
||||
# is "Token Plan only" but cheap-per-token and fast.
|
||||
E2E_MODEL_SLUG: MiniMax-M2.7-highspeed
|
||||
E2E_RUN_ID: "canary-${{ github.run_id }}"
|
||||
# Debug-only: when an operator dispatches with keep_on_failure=true,
|
||||
# the canary script's E2E_KEEP_ORG=1 path skips teardown so the
|
||||
# tenant org + EC2 stay alive for SSM-based log capture. Cron runs
|
||||
# never set this (the input only exists on workflow_dispatch) so
|
||||
# unattended cron always tears down. See molecule-core#129
|
||||
# failure mode #1 — capturing the actual exception requires
|
||||
# docker logs from the live container.
|
||||
E2E_KEEP_ORG: ${{ github.event.inputs.keep_on_failure == 'true' && '1' || '0' }}
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
@ -158,28 +137,27 @@ jobs:
|
||||
id: canary
|
||||
run: bash tests/e2e/test_staging_full_saas.sh
|
||||
|
||||
# Alerting: open a sticky issue on the FIRST failure; comment on
|
||||
# subsequent failures; auto-close on next green. Comment-on-existing
|
||||
# de-duplicates so a single open issue accumulates the streak —
|
||||
# ops sees one issue with N comments rather than N issues.
|
||||
# Alerting: open an issue only after THREE consecutive failures so
|
||||
# transient flakes (Cloudflare DNS hiccup, AWS API blip) don't spam
|
||||
# the issue list. If an issue is already open, we still comment on
|
||||
# every failure so ops sees the streak. Auto-close on next green.
|
||||
#
|
||||
# Why no consecutive-failures threshold (e.g., wait 3 runs before
|
||||
# filing): the prior threshold check used
|
||||
# `github.rest.actions.listWorkflowRuns()` which Gitea 1.22.6 does
|
||||
# not expose (returns 404). On Gitea Actions the threshold call
|
||||
# ALWAYS failed, breaking the entire alerting step and going days
|
||||
# silent on real regressions (38h+ chronic red on 2026-05-07/08
|
||||
# before this fix; tracked in molecule-core#129). Filing on first
|
||||
# failure is also better UX — we want to know about the first red,
|
||||
# not wait 90 min for it to "count." Real flakes get one issue +
|
||||
# a quick close-on-green; persistent reds accumulate comments.
|
||||
# Threshold rationale: canary fires every 30 min, so 3 failures =
|
||||
# ~90 min of consecutive red — well past any single-run flake but
|
||||
# still tight enough that a real outage gets surfaced before the
|
||||
# next deploy window.
|
||||
- name: Open issue on failure
|
||||
if: failure()
|
||||
uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
|
||||
env:
|
||||
# Inject the workflow path explicitly — context.workflow is
|
||||
# the *name*, not the file path the actions API needs.
|
||||
WORKFLOW_PATH: '.github/workflows/canary-staging.yml'
|
||||
CONSECUTIVE_THRESHOLD: '3'
|
||||
with:
|
||||
script: |
|
||||
const title = '🔴 Canary failing: staging SaaS smoke';
|
||||
const runURL = `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
|
||||
const runURL = `https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
|
||||
|
||||
// Find an existing open canary issue (stable title match).
|
||||
// If one exists, this isn't a "first failure" — comment and exit.
|
||||
@ -199,12 +177,32 @@ jobs:
|
||||
return;
|
||||
}
|
||||
|
||||
// No open issue yet — file one on this first failure. The
|
||||
// comment-on-existing branch above means subsequent failures
|
||||
// accumulate as comments on this same issue, so we don't
|
||||
// spam new issues per run.
|
||||
// No open issue yet — check the last N-1 runs' conclusions.
|
||||
// We open the issue only if the last (THRESHOLD-1) runs ALSO
|
||||
// failed (so this is the 3rd consecutive red).
|
||||
const threshold = parseInt(process.env.CONSECUTIVE_THRESHOLD, 10);
|
||||
const { data: runs } = await github.rest.actions.listWorkflowRuns({
|
||||
owner: context.repo.owner, repo: context.repo.repo,
|
||||
workflow_id: process.env.WORKFLOW_PATH,
|
||||
status: 'completed',
|
||||
per_page: threshold,
|
||||
// Skip the current in-progress run; it isn't 'completed' yet.
|
||||
});
|
||||
// listWorkflowRuns returns recent first. We need (threshold-1)
|
||||
// prior failures (current run is the threshold-th).
|
||||
const priorFailures = (runs.workflow_runs || [])
|
||||
.slice(0, threshold - 1)
|
||||
.filter(r => r.id !== context.runId)
|
||||
.filter(r => r.conclusion === 'failure')
|
||||
.length;
|
||||
if (priorFailures < threshold - 1) {
|
||||
core.info(`Below threshold: ${priorFailures + 1}/${threshold} consecutive failures — not filing yet`);
|
||||
return;
|
||||
}
|
||||
|
||||
const body =
|
||||
`Canary run failed at ${new Date().toISOString()}.\n\n` +
|
||||
`Canary run failed at ${new Date().toISOString()}, ` +
|
||||
`${threshold} consecutive runs red.\n\n` +
|
||||
`Run: ${runURL}\n\n` +
|
||||
`This issue auto-closes on the next green canary run. ` +
|
||||
`Consecutive failures add a comment here rather than a new issue.`;
|
||||
@ -213,7 +211,7 @@ jobs:
|
||||
title, body,
|
||||
labels: ['canary-staging', 'bug'],
|
||||
});
|
||||
core.info('Opened canary failure issue (first red)');
|
||||
core.info(`Opened canary failure issue (${threshold} consecutive reds)`);
|
||||
|
||||
- name: Auto-close canary issue on success
|
||||
if: success()
|
||||
|
||||
2
.github/workflows/canary-verify.yml
vendored
2
.github/workflows/canary-verify.yml
vendored
@ -108,7 +108,7 @@ jobs:
|
||||
echo
|
||||
echo "One or more canary secrets are unset (\`CANARY_TENANT_URLS\`, \`CANARY_ADMIN_TOKENS\`, \`CANARY_CP_SHARED_SECRET\`)."
|
||||
echo "Phase 2 canary fleet has not been stood up yet —"
|
||||
echo "see [canary-tenants.md](https://git.moleculesai.app/molecule-ai/molecule-controlplane/blob/main/docs/canary-tenants.md)."
|
||||
echo "see [canary-tenants.md](https://github.com/molecule-ai/molecule-controlplane/blob/main/docs/canary-tenants.md)."
|
||||
echo
|
||||
echo "**Skipped — promote-to-latest will NOT auto-fire.** Dispatch \`promote-latest.yml\` manually when ready."
|
||||
} >> "$GITHUB_STEP_SUMMARY"
|
||||
|
||||
8
.github/workflows/ci.yml
vendored
8
.github/workflows/ci.yml
vendored
@ -235,13 +235,7 @@ jobs:
|
||||
run: npx vitest run --coverage
|
||||
- name: Upload coverage summary as artifact
|
||||
if: needs.changes.outputs.canvas == 'true' && always()
|
||||
# Pinned to v3 for Gitea act_runner v0.6 compatibility — v4+ uses
|
||||
# the GHES 3.10+ artifact protocol that Gitea 1.22.x does NOT
|
||||
# implement, surfacing as `GHESNotSupportedError: @actions/artifact
|
||||
# v2.0.0+, upload-artifact@v4+ and download-artifact@v4+ are not
|
||||
# currently supported on GHES`. Drop this pin when Gitea ships
|
||||
# the v4 protocol (tracked: post-Gitea-1.23 followup).
|
||||
uses: actions/upload-artifact@c6a366c94c3e0affe28c06c8df20a878f24da3cf # v3.2.2
|
||||
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
|
||||
with:
|
||||
name: canvas-coverage-${{ github.run_id }}
|
||||
path: canvas/coverage/
|
||||
|
||||
184
.github/workflows/codeql.yml
vendored
184
.github/workflows/codeql.yml
vendored
@ -1,92 +1,36 @@
|
||||
name: CodeQL
|
||||
|
||||
# Stub workflow — CodeQL Action is structurally incompatible with Gitea
|
||||
# Actions (post-2026-05-06 SCM migration off GitHub).
|
||||
# Controls CodeQL scan triggers for this repo.
|
||||
#
|
||||
# Why this is a stub, not a real CodeQL run:
|
||||
# GitHub's "Code quality" default setup (the UI-configured one) is
|
||||
# hardcoded to only scan the default branch — on this repo that's
|
||||
# `staging`, so PRs promoting staging→main would otherwise never be
|
||||
# scanned. This workflow fills that gap by explicitly scanning both
|
||||
# branches on push and PR.
|
||||
#
|
||||
# 1. github/codeql-action/init@v4 hits api.github.com endpoints
|
||||
# (CodeQL CLI bundle download + query-pack registry + telemetry)
|
||||
# that Gitea 1.22.x does NOT proxy. The act_runner has
|
||||
# GITHUB_SERVER_URL=https://git.moleculesai.app correctly set
|
||||
# (per saved memory feedback_act_runner_github_server_url and
|
||||
# /config.yaml on the operator host), but the Gitea API surface
|
||||
# simply does not implement the codeql-action bundle endpoints.
|
||||
# Observed in run 1d/3101 (2026-05-07): "::error::404 page not
|
||||
# found" inside the Initialize CodeQL step, before any analysis.
|
||||
#
|
||||
# 2. PR #35 attempted to mark `continue-on-error: true` at the JOB
|
||||
# level (correct YAML structure). Gitea 1.22.6 does NOT propagate
|
||||
# job-level continue-on-error to the commit-status API — every
|
||||
# matrix leg still posts `failure` to the status surface, which
|
||||
# keeps OVERALL=failure on every push to main + staging and
|
||||
# blocks visual auto-promote signals (#156).
|
||||
#
|
||||
# 3. Hongming policy decision (2026-05-07, task #156): CodeQL is
|
||||
# ADVISORY, not blocking, on Gitea Actions. We do not block PR
|
||||
# merge or staging→main promotion on CodeQL findings until we
|
||||
# have a Gitea-compatible static-analysis pipeline.
|
||||
#
|
||||
# What this stub preserves:
|
||||
#
|
||||
# - Workflow name `CodeQL` (referenced by auto-promote-staging.yml
|
||||
# line 67 as a workflow_run gate — must stay stable).
|
||||
# - Job name template `Analyze (${{ matrix.language }})` and the
|
||||
# 3-leg matrix (go, javascript-typescript, python). Branch
|
||||
# protection / required-check parity (#144) keys on these
|
||||
# exact context names.
|
||||
# - merge_group + push + pull_request + schedule triggers, so the
|
||||
# merge-queue check name still resolves (per saved memory
|
||||
# feedback_branch_protection_check_name_parity).
|
||||
#
|
||||
# Re-enabling real analysis (future work):
|
||||
#
|
||||
# - Option A: self-hosted Semgrep / OpenGrep via a custom action
|
||||
# that doesn't hit api.github.com. Tracked behind #156 follow-up.
|
||||
# - Option B: Sonatype Nexus IQ or similar, called from a step
|
||||
# that uses the Gitea-issued token only.
|
||||
# - Option C: re-host this workflow on a small GitHub mirror used
|
||||
# ONLY for SAST (push-mirrored from Gitea). Acceptable trade-off
|
||||
# if/when payment is restored on a non-suspended GitHub org —
|
||||
# but per saved memory feedback_no_single_source_of_truth, we
|
||||
# should design for multi-vendor backup, not GitHub-only SAST.
|
||||
#
|
||||
# Until one of those lands, this stub keeps commit-status green so
|
||||
# the auto-promote chain isn't permanently red on a tool we cannot
|
||||
# actually run.
|
||||
#
|
||||
# Security policy: ADVISORY. We accept the residual risk of un-scanned
|
||||
# pushes during this window. Compensating controls in place:
|
||||
# - secret-scan.yml runs on every push (active, blocks on hits)
|
||||
# - block-internal-paths.yml blocks forbidden file paths
|
||||
# - lint-curl-status-capture.yml catches one specific class of bug
|
||||
# - branch-protection-drift.yml + the merge_group required-checks
|
||||
# parity keep the gate surface stable
|
||||
# These are not equivalent to CodeQL coverage. Status of the
|
||||
# replacement plan is tracked in #156.
|
||||
# Runs on ubuntu-latest (GHA-hosted — public repo, free). GHAS is NOT
|
||||
# enabled on this repo, so results are not uploaded to the Security
|
||||
# tab — the scan fails the PR check on findings, and the SARIF is
|
||||
# kept as a workflow artifact for triage.
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main, staging]
|
||||
pull_request:
|
||||
branches: [main, staging]
|
||||
# Required so the matrix legs emit a real result on the queued
|
||||
# commit instead of a false-green when merge queue is enabled.
|
||||
# Per saved memory feedback_branch_protection_check_name_parity:
|
||||
# path-filtered / matrix workflows MUST emit the protected name
|
||||
# via a job that always runs.
|
||||
# GitHub merge queue fires `merge_group` for the queue's pre-merge CI run.
|
||||
# Required so CodeQL Analyze checks get a real result on the queued
|
||||
# commit instead of a false-green. Event only fires once merge queue is
|
||||
# enabled on the target branch — safe to add unconditionally.
|
||||
merge_group:
|
||||
types: [checks_requested]
|
||||
schedule:
|
||||
# Weekly heartbeat. Cheap on a stub (the no-op job is ~5s) but
|
||||
# keeps the workflow visible in Gitea's Actions UI so the next
|
||||
# operator notices it's a stub instead of a missing surface.
|
||||
# Weekly run picks up findings in code that hasn't been touched.
|
||||
- cron: '30 1 * * 0'
|
||||
|
||||
# Workflow-level concurrency: only one stub run per branch/PR at a
|
||||
# time. cancel-in-progress: false because a quick follow-up push
|
||||
# shouldn't kill an in-flight run — even though the stub is fast,
|
||||
# the contract should match a real CodeQL run for when we re-enable.
|
||||
# Workflow-level concurrency: only one CodeQL run per branch/PR at a time.
|
||||
# `cancel-in-progress: false` queues new runs so a quick follow-up push
|
||||
# doesn't nuke a 45-min analysis mid-flight.
|
||||
concurrency:
|
||||
group: codeql-${{ github.ref }}
|
||||
cancel-in-progress: false
|
||||
@ -94,17 +38,16 @@ concurrency:
|
||||
permissions:
|
||||
actions: read
|
||||
contents: read
|
||||
# No security-events: write — we don't call the upload API anyway,
|
||||
# GHAS isn't on Gitea.
|
||||
# No security-events: write — we don't call the upload API.
|
||||
|
||||
jobs:
|
||||
analyze:
|
||||
# Job NAME shape is load-bearing — auto-promote-staging.yml +
|
||||
# branch protection both key on `Analyze (${{ matrix.language }})`.
|
||||
# Do NOT rename without coordinating both surfaces.
|
||||
name: Analyze (${{ matrix.language }})
|
||||
# CodeQL set to advisory (non-blocking) on Gitea Actions — Hongming dec'''n 2026-05-07 (#156).
|
||||
# Findings still emit as SARIF artifacts; failing CodeQL run does not block PR merge.
|
||||
continue-on-error: true
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 5
|
||||
timeout-minutes: 45
|
||||
|
||||
strategy:
|
||||
fail-fast: false
|
||||
@ -112,25 +55,68 @@ jobs:
|
||||
language: [go, javascript-typescript, python]
|
||||
|
||||
steps:
|
||||
# Single-step stub: log the policy decision + emit success.
|
||||
# Exit 0 explicitly so the commit-status API records `success`
|
||||
# for each of the three matrix legs.
|
||||
- name: CodeQL stub (advisory, non-blocking on Gitea)
|
||||
- name: Checkout
|
||||
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
|
||||
|
||||
# github-app-auth sibling-checkout removed 2026-05-07 (#157):
|
||||
# plugin was dropped + the Dockerfile no longer needs it.
|
||||
# jq is pre-installed on ubuntu-latest — no setup step needed.
|
||||
|
||||
- name: Initialize CodeQL
|
||||
uses: github/codeql-action/init@95e58e9a2cdfd71adc6e0353d5c52f41a045d225 # v4.35.2
|
||||
with:
|
||||
languages: ${{ matrix.language }}
|
||||
# security-extended widens past the default to include the
|
||||
# full security-query set for a public SaaS surface.
|
||||
queries: security-extended
|
||||
|
||||
- name: Autobuild
|
||||
uses: github/codeql-action/autobuild@95e58e9a2cdfd71adc6e0353d5c52f41a045d225 # v4.35.2
|
||||
|
||||
- name: Perform CodeQL Analysis
|
||||
id: analyze
|
||||
uses: github/codeql-action/analyze@95e58e9a2cdfd71adc6e0353d5c52f41a045d225 # v4.35.2
|
||||
with:
|
||||
category: "/language:${{ matrix.language }}"
|
||||
# upload: never — GHAS isn't enabled on this repo, so the
|
||||
# upload API 403s. Write SARIF locally instead.
|
||||
upload: never
|
||||
output: sarif-results/${{ matrix.language }}
|
||||
|
||||
- name: Parse SARIF + fail on findings
|
||||
# The analyze step writes <database>.sarif into the output
|
||||
# directory — database name is the short CodeQL lang id, not
|
||||
# the matrix value (e.g. "javascript-typescript" →
|
||||
# javascript.sarif), so glob rather than hardcode.
|
||||
# Filter to error/warning severity: security-extended emits
|
||||
# "note" rows for informational findings we don't want to fail
|
||||
# the build over.
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
cat <<EOF
|
||||
CodeQL is currently ADVISORY on Gitea Actions (post-2026-05-06).
|
||||
Language matrix leg: ${{ matrix.language }}
|
||||
Reason: github/codeql-action/init@v4 calls api.github.com
|
||||
bundle endpoints that Gitea 1.22.x does not implement.
|
||||
Observed: "::error::404 page not found" in the Init
|
||||
CodeQL step on every prior run.
|
||||
Policy: per Hongming decision 2026-05-07 (#156), CodeQL is
|
||||
non-blocking until a Gitea-compatible SAST pipeline
|
||||
lands. See workflow file header for replacement
|
||||
options + compensating controls.
|
||||
Status: emitting success so auto-promote isn't permanently
|
||||
red on a tool we cannot actually run today.
|
||||
EOF
|
||||
echo "::notice::CodeQL ${{ matrix.language }} — advisory stub, success."
|
||||
dir="sarif-results/${{ matrix.language }}"
|
||||
sarif=$(ls "$dir"/*.sarif 2>/dev/null | head -1 || true)
|
||||
if [ -z "$sarif" ] || [ ! -f "$sarif" ]; then
|
||||
echo "::error::No SARIF file found under $dir"
|
||||
ls -la "$dir" 2>/dev/null || true
|
||||
exit 1
|
||||
fi
|
||||
echo "Parsing $sarif"
|
||||
count=$(jq '[.runs[].results[] | select(.level == "error" or .level == "warning")] | length' "$sarif")
|
||||
echo "CodeQL findings (error+warning) for ${{ matrix.language }}: $count"
|
||||
if [ "$count" -gt 0 ]; then
|
||||
echo "::error::CodeQL found $count issues. Details below; full SARIF in the artifact."
|
||||
jq -r '.runs[].results[] | select(.level == "error" or .level == "warning") | " - [\(.level)] \(.ruleId // "?"): \(.message.text // "(no message)") @ \(.locations[0].physicalLocation.artifactLocation.uri // "?"):\(.locations[0].physicalLocation.region.startLine // "?")"' "$sarif"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
- name: Upload SARIF artifact
|
||||
# Keep SARIF around on success + failure so triagers can diff.
|
||||
# 14-day retention — longer than default 3, short enough not
|
||||
# to bloat quota.
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v3 # pinned to v3 for Gitea act_runner v0.6 compatibility (internal#46)
|
||||
with:
|
||||
name: codeql-sarif-${{ matrix.language }}
|
||||
path: sarif-results/${{ matrix.language }}/
|
||||
retention-days: 14
|
||||
|
||||
130
.github/workflows/e2e-api.yml
vendored
130
.github/workflows/e2e-api.yml
vendored
@ -12,59 +12,6 @@ name: E2E API Smoke Test
|
||||
# spending CI cycles. See the in-job comment on the `e2e-api` job for
|
||||
# why this is one job (not two-jobs-sharing-name) and the 2026-04-29
|
||||
# PR #2264 incident that drove the consolidation.
|
||||
#
|
||||
# Parallel-safety (Class B Hongming-owned CICD red sweep, 2026-05-08)
|
||||
# -------------------------------------------------------------------
|
||||
# Same substrate hazard as PR #98 (handlers-postgres-integration). Our
|
||||
# Gitea act_runner runs with `container.network: host` (operator host
|
||||
# `/opt/molecule/runners/config.yaml`), which means:
|
||||
#
|
||||
# * Two concurrent runs both try to bind their `-p 15432:5432` /
|
||||
# `-p 16379:6379` host ports — the second postgres/redis FATALs
|
||||
# with `Address in use` and `docker run` returns exit 125 with
|
||||
# `Conflict. The container name "/molecule-ci-postgres" is already
|
||||
# in use by container ...`. Verified in run a7/2727 on 2026-05-07.
|
||||
# * The fixed container names `molecule-ci-postgres` / `-redis` (the
|
||||
# pre-fix shape) collide on name AS WELL AS port. The cleanup-with-
|
||||
# `docker rm -f` at the start of the second job KILLS the first
|
||||
# job's still-running postgres/redis.
|
||||
#
|
||||
# Fix shape (mirrors PR #98's bridge-net pattern, adapted because
|
||||
# platform-server is a Go binary on the host, not a containerised
|
||||
# step):
|
||||
#
|
||||
# 1. Unique container names per run:
|
||||
# pg-e2e-api-${RUN_ID}-${RUN_ATTEMPT}
|
||||
# redis-e2e-api-${RUN_ID}-${RUN_ATTEMPT}
|
||||
# `${RUN_ID}-${RUN_ATTEMPT}` is unique even across reruns of the
|
||||
# same run_id.
|
||||
# 2. Ephemeral host port per run (`-p 0:5432`), then read the actual
|
||||
# bound port via `docker port` and export DATABASE_URL/REDIS_URL
|
||||
# pointing at it. No fixed host-port → no port collision.
|
||||
# 3. `127.0.0.1` (NOT `localhost`) in URLs — IPv6 first-resolve was
|
||||
# the original flake fixed in #92 and the script's still IPv6-
|
||||
# enabled.
|
||||
# 4. `if: always()` cleanup so containers don't leak when test steps
|
||||
# fail.
|
||||
#
|
||||
# Issue #94 items #2 + #3 (also fixed here):
|
||||
# * Pre-pull `alpine:latest` so the platform-server's provisioner
|
||||
# (`internal/handlers/container_files.go`) can stand up its
|
||||
# ephemeral token-write helper without a daemon.io round-trip.
|
||||
# * Create `molecule-monorepo-net` bridge network if missing so the
|
||||
# provisioner's container.HostConfig {NetworkMode: ...} attach
|
||||
# succeeds.
|
||||
# Item #1 (timeouts) — evidence on recent runs (77/3191, ae/4270, 0e/
|
||||
# 2318) shows Postgres ready in 3s, Redis in 1s, Platform in 1s when
|
||||
# they DO come up. Timeouts are not the bottleneck; not bumped.
|
||||
#
|
||||
# Item explicitly NOT fixed here: failing test `Status back online`
|
||||
# fails because the platform's langgraph workspace template image
|
||||
# (ghcr.io/molecule-ai/workspace-template-langgraph:latest) returns
|
||||
# 403 Forbidden post-2026-05-06 GitHub org suspension. That is a
|
||||
# template-registry resolution issue (ADR-002 / local-build mode) and
|
||||
# belongs in a separate change that touches workspace-server, not
|
||||
# this workflow file.
|
||||
|
||||
on:
|
||||
push:
|
||||
@ -131,14 +78,11 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
timeout-minutes: 15
|
||||
env:
|
||||
# Unique per-run container names so concurrent runs on the host-
|
||||
# network act_runner don't collide on name OR port.
|
||||
# `${RUN_ID}-${RUN_ATTEMPT}` stays unique across reruns of the
|
||||
# same run_id. PORT is set later (after docker port lookup) since
|
||||
# we let Docker assign an ephemeral host port.
|
||||
PG_CONTAINER: pg-e2e-api-${{ github.run_id }}-${{ github.run_attempt }}
|
||||
REDIS_CONTAINER: redis-e2e-api-${{ github.run_id }}-${{ github.run_attempt }}
|
||||
DATABASE_URL: postgres://dev:dev@localhost:15432/molecule?sslmode=disable
|
||||
REDIS_URL: redis://localhost:16379
|
||||
PORT: "8080"
|
||||
PG_CONTAINER: molecule-ci-postgres
|
||||
REDIS_CONTAINER: molecule-ci-redis
|
||||
steps:
|
||||
- name: No-op pass (paths filter excluded this commit)
|
||||
if: needs.detect-changes.outputs.api != 'true'
|
||||
@ -153,53 +97,11 @@ jobs:
|
||||
go-version: 'stable'
|
||||
cache: true
|
||||
cache-dependency-path: workspace-server/go.sum
|
||||
- name: Pre-pull alpine + ensure provisioner network (Issue #94 items #2 + #3)
|
||||
if: needs.detect-changes.outputs.api == 'true'
|
||||
run: |
|
||||
# Provisioner uses alpine:latest for ephemeral token-write
|
||||
# containers (workspace-server/internal/handlers/container_files.go).
|
||||
# Pre-pull so the first provision in test_api.sh doesn't race
|
||||
# the daemon's pull cache. Idempotent — `docker pull` is a no-op
|
||||
# when the image is already present.
|
||||
docker pull alpine:latest >/dev/null
|
||||
# Provisioner attaches workspace containers to
|
||||
# molecule-monorepo-net (workspace-server/internal/provisioner/
|
||||
# provisioner.go::DefaultNetwork). The bridge already exists on
|
||||
# the operator host's docker daemon — `network create` is
|
||||
# idempotent via `|| true`.
|
||||
docker network create molecule-monorepo-net >/dev/null 2>&1 || true
|
||||
echo "alpine:latest pre-pulled; molecule-monorepo-net ensured."
|
||||
- name: Start Postgres (docker)
|
||||
if: needs.detect-changes.outputs.api == 'true'
|
||||
run: |
|
||||
# Defensive cleanup — only matches THIS run's container name,
|
||||
# so it cannot kill a sibling run's postgres. (Pre-fix the
|
||||
# name was static and this rm hit other runs' containers.)
|
||||
docker rm -f "$PG_CONTAINER" 2>/dev/null || true
|
||||
# `-p 0:5432` requests an ephemeral host port; we read it back
|
||||
# below and export DATABASE_URL.
|
||||
docker run -d --name "$PG_CONTAINER" \
|
||||
-e POSTGRES_USER=dev -e POSTGRES_PASSWORD=dev -e POSTGRES_DB=molecule \
|
||||
-p 0:5432 postgres:16 >/dev/null
|
||||
# Resolve the host-side port assignment. `docker port` prints
|
||||
# `0.0.0.0:NNNN` (and on host-net runners may also print an
|
||||
# IPv6 line — take the first IPv4 line).
|
||||
PG_PORT=$(docker port "$PG_CONTAINER" 5432/tcp | awk -F: '/^0\.0\.0\.0:/ {print $2; exit}')
|
||||
if [ -z "$PG_PORT" ]; then
|
||||
# Fallback: any first line. Some Docker versions print only
|
||||
# one line.
|
||||
PG_PORT=$(docker port "$PG_CONTAINER" 5432/tcp | head -1 | awk -F: '{print $NF}')
|
||||
fi
|
||||
if [ -z "$PG_PORT" ]; then
|
||||
echo "::error::Could not resolve host port for $PG_CONTAINER"
|
||||
docker port "$PG_CONTAINER" 5432/tcp || true
|
||||
docker logs "$PG_CONTAINER" || true
|
||||
exit 1
|
||||
fi
|
||||
# 127.0.0.1 (NOT localhost) — IPv6 first-resolve flake (#92).
|
||||
echo "PG_PORT=${PG_PORT}" >> "$GITHUB_ENV"
|
||||
echo "DATABASE_URL=postgres://dev:dev@127.0.0.1:${PG_PORT}/molecule?sslmode=disable" >> "$GITHUB_ENV"
|
||||
echo "Postgres host port: ${PG_PORT}"
|
||||
docker run -d --name "$PG_CONTAINER" -e POSTGRES_USER=dev -e POSTGRES_PASSWORD=dev -e POSTGRES_DB=molecule -p 15432:5432 postgres:16
|
||||
for i in $(seq 1 30); do
|
||||
if docker exec "$PG_CONTAINER" pg_isready -U dev >/dev/null 2>&1; then
|
||||
echo "Postgres ready after ${i}s"
|
||||
@ -214,20 +116,7 @@ jobs:
|
||||
if: needs.detect-changes.outputs.api == 'true'
|
||||
run: |
|
||||
docker rm -f "$REDIS_CONTAINER" 2>/dev/null || true
|
||||
docker run -d --name "$REDIS_CONTAINER" -p 0:6379 redis:7 >/dev/null
|
||||
REDIS_PORT=$(docker port "$REDIS_CONTAINER" 6379/tcp | awk -F: '/^0\.0\.0\.0:/ {print $2; exit}')
|
||||
if [ -z "$REDIS_PORT" ]; then
|
||||
REDIS_PORT=$(docker port "$REDIS_CONTAINER" 6379/tcp | head -1 | awk -F: '{print $NF}')
|
||||
fi
|
||||
if [ -z "$REDIS_PORT" ]; then
|
||||
echo "::error::Could not resolve host port for $REDIS_CONTAINER"
|
||||
docker port "$REDIS_CONTAINER" 6379/tcp || true
|
||||
docker logs "$REDIS_CONTAINER" || true
|
||||
exit 1
|
||||
fi
|
||||
echo "REDIS_PORT=${REDIS_PORT}" >> "$GITHUB_ENV"
|
||||
echo "REDIS_URL=redis://127.0.0.1:${REDIS_PORT}" >> "$GITHUB_ENV"
|
||||
echo "Redis host port: ${REDIS_PORT}"
|
||||
docker run -d --name "$REDIS_CONTAINER" -p 16379:6379 redis:7
|
||||
for i in $(seq 1 15); do
|
||||
if docker exec "$REDIS_CONTAINER" redis-cli ping 2>/dev/null | grep -q PONG; then
|
||||
echo "Redis ready after ${i}s"
|
||||
@ -246,15 +135,13 @@ jobs:
|
||||
if: needs.detect-changes.outputs.api == 'true'
|
||||
working-directory: workspace-server
|
||||
run: |
|
||||
# DATABASE_URL + REDIS_URL exported by the start-postgres /
|
||||
# start-redis steps point at this run's per-run host ports.
|
||||
./platform-server > platform.log 2>&1 &
|
||||
echo $! > platform.pid
|
||||
- name: Wait for /health
|
||||
if: needs.detect-changes.outputs.api == 'true'
|
||||
run: |
|
||||
for i in $(seq 1 30); do
|
||||
if curl -sf http://127.0.0.1:8080/health > /dev/null; then
|
||||
if curl -sf http://localhost:8080/health > /dev/null; then
|
||||
echo "Platform up after ${i}s"
|
||||
exit 0
|
||||
fi
|
||||
@ -298,9 +185,6 @@ jobs:
|
||||
kill "$(cat workspace-server/platform.pid)" 2>/dev/null || true
|
||||
fi
|
||||
- name: Stop service containers
|
||||
# always() so containers don't leak when test steps fail. The
|
||||
# cleanup is best-effort: if the container is already gone
|
||||
# (e.g. concurrent rerun race), don't fail the job.
|
||||
if: always() && needs.detect-changes.outputs.api == 'true'
|
||||
run: |
|
||||
docker rm -f "$PG_CONTAINER" 2>/dev/null || true
|
||||
|
||||
13
.github/workflows/e2e-staging-canvas.yml
vendored
13
.github/workflows/e2e-staging-canvas.yml
vendored
@ -22,9 +22,9 @@ on:
|
||||
# spending CI cycles. See e2e-api.yml for the rationale on why this
|
||||
# is a single job rather than two-jobs-sharing-name.
|
||||
push:
|
||||
branches: [main]
|
||||
branches: [main, staging]
|
||||
pull_request:
|
||||
branches: [main]
|
||||
branches: [main, staging]
|
||||
workflow_dispatch:
|
||||
schedule:
|
||||
# Weekly on Sunday 08:00 UTC — catches Chrome / Playwright / Next.js
|
||||
@ -139,11 +139,7 @@ jobs:
|
||||
|
||||
- name: Upload Playwright report on failure
|
||||
if: failure() && needs.detect-changes.outputs.canvas == 'true'
|
||||
# Pinned to v3 for Gitea act_runner v0.6 compatibility — v4+ uses
|
||||
# the GHES 3.10+ artifact protocol that Gitea 1.22.x does NOT
|
||||
# implement (see ci.yml upload step for the canonical error
|
||||
# cite). Drop this pin when Gitea ships the v4 protocol.
|
||||
uses: actions/upload-artifact@c6a366c94c3e0affe28c06c8df20a878f24da3cf # v3.2.2
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
|
||||
with:
|
||||
name: playwright-report-staging
|
||||
path: canvas/playwright-report-staging/
|
||||
@ -151,8 +147,7 @@ jobs:
|
||||
|
||||
- name: Upload screenshots on failure
|
||||
if: failure() && needs.detect-changes.outputs.canvas == 'true'
|
||||
# Pinned to v3 for Gitea act_runner v0.6 compatibility (see above).
|
||||
uses: actions/upload-artifact@c6a366c94c3e0affe28c06c8df20a878f24da3cf # v3.2.2
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
|
||||
with:
|
||||
name: playwright-screenshots
|
||||
path: canvas/test-results/
|
||||
|
||||
4
.github/workflows/e2e-staging-external.yml
vendored
4
.github/workflows/e2e-staging-external.yml
vendored
@ -32,7 +32,7 @@ name: E2E Staging External Runtime
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [main]
|
||||
branches: [staging, main]
|
||||
paths:
|
||||
- 'workspace-server/internal/handlers/workspace.go'
|
||||
- 'workspace-server/internal/handlers/registry.go'
|
||||
@ -44,7 +44,7 @@ on:
|
||||
- 'tests/e2e/test_staging_external_runtime.sh'
|
||||
- '.github/workflows/e2e-staging-external.yml'
|
||||
pull_request:
|
||||
branches: [main]
|
||||
branches: [staging, main]
|
||||
paths:
|
||||
- 'workspace-server/internal/handlers/workspace.go'
|
||||
- 'workspace-server/internal/handlers/registry.go'
|
||||
|
||||
13
.github/workflows/e2e-staging-saas.yml
vendored
13
.github/workflows/e2e-staging-saas.yml
vendored
@ -20,12 +20,13 @@ name: E2E Staging SaaS (full lifecycle)
|
||||
# via the same paths watcher that e2e-api.yml uses)
|
||||
|
||||
on:
|
||||
# Trunk-based (Phase 3 of internal#81): main is the only branch.
|
||||
# Previously this fired on staging push too because staging was a
|
||||
# superset of main and ran the gate ahead of auto-promote; with no
|
||||
# staging branch, main is where E2E gates the deploy.
|
||||
# Fire on staging push too — previously this only ran on main, which
|
||||
# meant the most thorough end-to-end test caught regressions AFTER
|
||||
# they shipped to staging (and then to the auto-promote PR). Running
|
||||
# on staging push catches them BEFORE the staging→main promotion
|
||||
# opens, so a green canary into auto-promote is more meaningful.
|
||||
push:
|
||||
branches: [main]
|
||||
branches: [staging, main]
|
||||
paths:
|
||||
- 'workspace-server/internal/handlers/registry.go'
|
||||
- 'workspace-server/internal/handlers/workspace_provision.go'
|
||||
@ -35,7 +36,7 @@ on:
|
||||
- 'tests/e2e/test_staging_full_saas.sh'
|
||||
- '.github/workflows/e2e-staging-saas.yml'
|
||||
pull_request:
|
||||
branches: [main]
|
||||
branches: [staging, main]
|
||||
paths:
|
||||
- 'workspace-server/internal/handlers/registry.go'
|
||||
- 'workspace-server/internal/handlers/workspace_provision.go'
|
||||
|
||||
139
.github/workflows/handlers-postgres-integration.yml
vendored
139
.github/workflows/handlers-postgres-integration.yml
vendored
@ -14,42 +14,12 @@ name: Handlers Postgres Integration
|
||||
# self-review caught it took 2 minutes to set up and would have caught
|
||||
# the bug at PR-time.
|
||||
#
|
||||
# Why this workflow does NOT use `services: postgres:` (Class B fix)
|
||||
# ------------------------------------------------------------------
|
||||
# Our act_runner config has `container.network: host` (operator host
|
||||
# /opt/molecule/runners/config.yaml), which act_runner applies to BOTH
|
||||
# the job container AND every service container. With host-net, two
|
||||
# concurrent runs of this workflow both try to bind 0.0.0.0:5432 — the
|
||||
# second postgres FATALs with `could not create any TCP/IP sockets:
|
||||
# Address in use`, and Docker auto-removes it (act_runner sets
|
||||
# AutoRemove:true on service containers). By the time the migrations
|
||||
# step runs `psql`, the postgres container is gone, hence
|
||||
# `Connection refused` then `failed to remove container: No such
|
||||
# container` at cleanup time.
|
||||
# This job spins a Postgres service container, applies the migration,
|
||||
# and runs `go test -tags=integration` against a live DB. Required
|
||||
# check on staging branch protection — backend handler PRs cannot
|
||||
# merge without a real-DB regression gate.
|
||||
#
|
||||
# Per-job `container.network` override is silently ignored by
|
||||
# act_runner — `--network and --net in the options will be ignored.`
|
||||
# appears in the runner log. Documented constraint.
|
||||
#
|
||||
# So we sidestep `services:` entirely. The job container still uses
|
||||
# host-net (inherited from runner config; required for cache server
|
||||
# discovery on the bridge IP 172.18.0.17:42631). We launch a sibling
|
||||
# postgres on the existing `molecule-monorepo-net` bridge with a
|
||||
# UNIQUE name per run — `pg-handlers-${RUN_ID}-${RUN_ATTEMPT}` — and
|
||||
# read its bridge IP via `docker inspect`. A host-net job container
|
||||
# can reach a bridge-net container directly via the bridge IP (verified
|
||||
# manually on operator host 2026-05-08).
|
||||
#
|
||||
# Trade-offs vs. the original `services:` shape:
|
||||
# + No host-port collision; N parallel runs share the bridge cleanly
|
||||
# + `if: always()` cleanup runs even on test-step failure
|
||||
# - One more step in the workflow (+~3 lines)
|
||||
# - Requires `molecule-monorepo-net` to exist on the operator host
|
||||
# (it does; declared in docker-compose.yml + docker-compose.infra.yml)
|
||||
#
|
||||
# Class B Hongming-owned CICD red sweep, 2026-05-08.
|
||||
#
|
||||
# Cost: ~30s job (postgres pull from cache + go build + 4 tests).
|
||||
# Cost: ~30s job (postgres pull from GH cache + go build + 4 tests).
|
||||
|
||||
on:
|
||||
push:
|
||||
@ -89,14 +59,20 @@ jobs:
|
||||
name: Handlers Postgres Integration
|
||||
needs: detect-changes
|
||||
runs-on: ubuntu-latest
|
||||
env:
|
||||
# Unique name per run so concurrent jobs don't collide on the
|
||||
# bridge network. ${RUN_ID}-${RUN_ATTEMPT} is unique even across
|
||||
# workflow_dispatch reruns of the same run_id.
|
||||
PG_NAME: pg-handlers-${{ github.run_id }}-${{ github.run_attempt }}
|
||||
# Bridge network already exists on the operator host (declared
|
||||
# in docker-compose.yml + docker-compose.infra.yml).
|
||||
PG_NETWORK: molecule-monorepo-net
|
||||
services:
|
||||
postgres:
|
||||
image: postgres:15-alpine
|
||||
env:
|
||||
POSTGRES_PASSWORD: test
|
||||
POSTGRES_DB: molecule
|
||||
ports:
|
||||
- 5432:5432
|
||||
# GHA spins this with --health-cmd built in for postgres images.
|
||||
options: >-
|
||||
--health-cmd pg_isready
|
||||
--health-interval 5s
|
||||
--health-timeout 5s
|
||||
--health-retries 10
|
||||
defaults:
|
||||
run:
|
||||
working-directory: workspace-server
|
||||
@ -113,57 +89,16 @@ jobs:
|
||||
with:
|
||||
go-version: 'stable'
|
||||
|
||||
- if: needs.detect-changes.outputs.handlers == 'true'
|
||||
name: Start sibling Postgres on bridge network
|
||||
working-directory: .
|
||||
run: |
|
||||
# Sanity: the bridge network must exist on the operator host.
|
||||
# Hard-fail loud if it doesn't — easier to spot than a silent
|
||||
# auto-create that diverges from the rest of the stack.
|
||||
if ! docker network inspect "${PG_NETWORK}" >/dev/null 2>&1; then
|
||||
echo "::error::Bridge network '${PG_NETWORK}' missing on operator host. Re-run docker-compose.infra.yml or check ops handbook."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# If a stale container with the same name exists (rerun on
|
||||
# the same run_id), wipe it first.
|
||||
docker rm -f "${PG_NAME}" >/dev/null 2>&1 || true
|
||||
|
||||
docker run -d \
|
||||
--name "${PG_NAME}" \
|
||||
--network "${PG_NETWORK}" \
|
||||
--health-cmd "pg_isready -U postgres" \
|
||||
--health-interval 5s \
|
||||
--health-timeout 5s \
|
||||
--health-retries 10 \
|
||||
-e POSTGRES_PASSWORD=test \
|
||||
-e POSTGRES_DB=molecule \
|
||||
postgres:15-alpine >/dev/null
|
||||
|
||||
# Read back the bridge IP. Always present immediately after
|
||||
# `docker run -d` for bridge networks.
|
||||
PG_HOST=$(docker inspect "${PG_NAME}" \
|
||||
--format "{{(index .NetworkSettings.Networks \"${PG_NETWORK}\").IPAddress}}")
|
||||
if [ -z "${PG_HOST}" ]; then
|
||||
echo "::error::Could not resolve PG_HOST for ${PG_NAME} on ${PG_NETWORK}"
|
||||
docker logs "${PG_NAME}" || true
|
||||
exit 1
|
||||
fi
|
||||
echo "PG_HOST=${PG_HOST}" >> "$GITHUB_ENV"
|
||||
echo "INTEGRATION_DB_URL=postgres://postgres:test@${PG_HOST}:5432/molecule?sslmode=disable" >> "$GITHUB_ENV"
|
||||
echo "Started ${PG_NAME} at ${PG_HOST}:5432"
|
||||
|
||||
- if: needs.detect-changes.outputs.handlers == 'true'
|
||||
name: Apply migrations to Postgres service
|
||||
env:
|
||||
PGPASSWORD: test
|
||||
run: |
|
||||
# Wait for postgres to actually accept connections. Docker's
|
||||
# health-cmd handles container-side readiness, but the wire
|
||||
# to the bridge IP is best-tested with pg_isready directly.
|
||||
# Wait for postgres to actually accept connections (the
|
||||
# GHA --health-cmd is best-effort but psql can still race).
|
||||
for i in {1..15}; do
|
||||
if pg_isready -h "${PG_HOST}" -p 5432 -U postgres -q; then break; fi
|
||||
echo "waiting for postgres at ${PG_HOST}:5432..."; sleep 2
|
||||
if pg_isready -h localhost -p 5432 -U postgres -q; then break; fi
|
||||
echo "waiting for postgres..."; sleep 2
|
||||
done
|
||||
|
||||
# Apply every .up.sql in lexicographic order with
|
||||
@ -196,7 +131,7 @@ jobs:
|
||||
# not fine once a cross-table atomicity test came in.
|
||||
set +e
|
||||
for migration in $(ls migrations/*.sql 2>/dev/null | grep -v '\.down\.sql$' | sort); do
|
||||
if psql -h "${PG_HOST}" -U postgres -d molecule -v ON_ERROR_STOP=1 \
|
||||
if psql -h localhost -U postgres -d molecule -v ON_ERROR_STOP=1 \
|
||||
-f "$migration" >/dev/null 2>&1; then
|
||||
echo "✓ $(basename "$migration")"
|
||||
else
|
||||
@ -210,7 +145,7 @@ jobs:
|
||||
# fail if any didn't land — that would be a real regression we
|
||||
# want loud.
|
||||
for tbl in delegations workspaces activity_logs pending_uploads; do
|
||||
if ! psql -h "${PG_HOST}" -U postgres -d molecule -tA \
|
||||
if ! psql -h localhost -U postgres -d molecule -tA \
|
||||
-c "SELECT 1 FROM information_schema.tables WHERE table_name = '$tbl'" \
|
||||
| grep -q 1; then
|
||||
echo "::error::$tbl table missing after migration replay — handler integration tests would be meaningless"
|
||||
@ -221,32 +156,16 @@ jobs:
|
||||
|
||||
- if: needs.detect-changes.outputs.handlers == 'true'
|
||||
name: Run integration tests
|
||||
env:
|
||||
INTEGRATION_DB_URL: postgres://postgres:test@localhost:5432/molecule?sslmode=disable
|
||||
run: |
|
||||
# INTEGRATION_DB_URL is exported by the start-postgres step;
|
||||
# points at the per-run bridge IP, not 127.0.0.1, so concurrent
|
||||
# workflow runs don't fight over a host-net 5432 port.
|
||||
go test -tags=integration -timeout 5m -v ./internal/handlers/ -run "^TestIntegration_"
|
||||
|
||||
- if: failure() && needs.detect-changes.outputs.handlers == 'true'
|
||||
- if: needs.detect-changes.outputs.handlers == 'true' && failure()
|
||||
name: Diagnostic dump on failure
|
||||
env:
|
||||
PGPASSWORD: test
|
||||
run: |
|
||||
echo "::group::postgres container status"
|
||||
docker ps -a --filter "name=${PG_NAME}" --format '{{.Status}} {{.Names}}' || true
|
||||
docker logs "${PG_NAME}" 2>&1 | tail -50 || true
|
||||
echo "::endgroup::"
|
||||
echo "::group::delegations table state"
|
||||
psql -h "${PG_HOST}" -U postgres -d molecule -c "SELECT * FROM delegations LIMIT 50;" || true
|
||||
psql -h localhost -U postgres -d molecule -c "SELECT * FROM delegations LIMIT 50;" || true
|
||||
echo "::endgroup::"
|
||||
|
||||
- if: always() && needs.detect-changes.outputs.handlers == 'true'
|
||||
name: Stop sibling Postgres
|
||||
working-directory: .
|
||||
run: |
|
||||
# always() so containers don't leak when migrations or tests
|
||||
# fail. The cleanup is best-effort: if the container is
|
||||
# already gone (e.g. concurrent rerun race), don't fail the job.
|
||||
docker rm -f "${PG_NAME}" >/dev/null 2>&1 || true
|
||||
echo "Cleaned up ${PG_NAME}"
|
||||
|
||||
|
||||
60
.github/workflows/harness-replays.yml
vendored
60
.github/workflows/harness-replays.yml
vendored
@ -98,66 +98,6 @@ jobs:
|
||||
# github-app-auth sibling-checkout removed 2026-05-07 (#157):
|
||||
# the plugin was dropped + Dockerfile.tenant no longer COPYs it.
|
||||
|
||||
# Pre-clone manifest deps before docker compose builds the tenant
|
||||
# image (Task #173 followup — same pattern as
|
||||
# publish-workspace-server-image.yml's "Pre-clone manifest deps"
|
||||
# step).
|
||||
#
|
||||
# Why pre-clone here too: tests/harness/compose.yml builds tenant-alpha
|
||||
# and tenant-beta from workspace-server/Dockerfile.tenant with
|
||||
# context=../.. (repo root). That Dockerfile expects
|
||||
# .tenant-bundle-deps/{workspace-configs-templates,org-templates,plugins}
|
||||
# to be present at build context root (post-#173 it COPYs from there
|
||||
# instead of running an in-image clone — the in-image clone failed
|
||||
# with "could not read Username for https://git.moleculesai.app"
|
||||
# because there's no auth path inside the build sandbox).
|
||||
#
|
||||
# Without this step harness-replays fails before any replay runs,
|
||||
# with `failed to calculate checksum of ref ...
|
||||
# "/.tenant-bundle-deps/plugins": not found`. Caught by run #892
|
||||
# (main, 2026-05-07T20:28:53Z) and run #964 (staging — same
|
||||
# symptom, different root cause: staging still has the in-image
|
||||
# clone path, hits the auth error directly).
|
||||
#
|
||||
# 2026-05-08 sub-finding (#192): the clone step ALSO fails when
|
||||
# any referenced workspace-template repo is private and the
|
||||
# AUTO_SYNC_TOKEN bearer (devops-engineer persona) lacks read
|
||||
# access. Root cause: 5 of 9 workspace-template repos
|
||||
# (openclaw, codex, crewai, deepagents, gemini-cli) had been
|
||||
# marked private with no team grant. Resolution: flipped them
|
||||
# to public per `feedback_oss_first_repo_visibility_default`
|
||||
# (the OSS surface should be public). Layer-3 (customer-private +
|
||||
# marketplace third-party repos) tracked separately in
|
||||
# internal#102.
|
||||
#
|
||||
# Token shape matches publish-workspace-server-image.yml: AUTO_SYNC_TOKEN
|
||||
# is the devops-engineer persona PAT, NOT the founder PAT (per
|
||||
# `feedback_per_agent_gitea_identity_default`). clone-manifest.sh
|
||||
# embeds it as basic-auth for the duration of the clones and strips
|
||||
# .git directories — the token never enters the resulting image.
|
||||
- name: Pre-clone manifest deps
|
||||
if: needs.detect-changes.outputs.run == 'true'
|
||||
env:
|
||||
MOLECULE_GITEA_TOKEN: ${{ secrets.AUTO_SYNC_TOKEN }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
if [ -z "${MOLECULE_GITEA_TOKEN}" ]; then
|
||||
echo "::error::AUTO_SYNC_TOKEN secret is empty — register the devops-engineer persona PAT in repo Actions secrets"
|
||||
exit 1
|
||||
fi
|
||||
mkdir -p .tenant-bundle-deps
|
||||
bash scripts/clone-manifest.sh \
|
||||
manifest.json \
|
||||
.tenant-bundle-deps/workspace-configs-templates \
|
||||
.tenant-bundle-deps/org-templates \
|
||||
.tenant-bundle-deps/plugins
|
||||
# Sanity-check counts so a silent partial clone fails fast
|
||||
# instead of producing a half-empty image.
|
||||
ws_count=$(find .tenant-bundle-deps/workspace-configs-templates -mindepth 1 -maxdepth 1 -type d | wc -l)
|
||||
org_count=$(find .tenant-bundle-deps/org-templates -mindepth 1 -maxdepth 1 -type d | wc -l)
|
||||
plugins_count=$(find .tenant-bundle-deps/plugins -mindepth 1 -maxdepth 1 -type d | wc -l)
|
||||
echo "Cloned: ws=$ws_count org=$org_count plugins=$plugins_count"
|
||||
|
||||
- name: Install Python deps for replays
|
||||
# peer-discovery-404 (and future replays) eval Python against the
|
||||
# running tenant — importing workspace/a2a_client.py pulls in
|
||||
|
||||
59
.github/workflows/pr-guards.yml
vendored
59
.github/workflows/pr-guards.yml
vendored
@ -1,25 +1,14 @@
|
||||
name: pr-guards
|
||||
|
||||
# PR-time guards. Today the only guard is "disable auto-merge when a
|
||||
# new commit is pushed after auto-merge was enabled" — added 2026-04-27
|
||||
# after PR #2174 auto-merged with only its first commit because the
|
||||
# second commit was pushed after the merge queue had locked the PR's
|
||||
# SHA.
|
||||
# Thin caller that delegates to the molecule-ci reusable guard. Today
|
||||
# the guard is just "disable auto-merge when a new commit is pushed
|
||||
# after auto-merge was enabled" — added 2026-04-27 after PR #2174
|
||||
# auto-merged with only its first commit because the second commit
|
||||
# was pushed after the merge queue had locked the PR's SHA.
|
||||
#
|
||||
# Why this is inlined (not delegated to molecule-ci's reusable
|
||||
# workflow): the reusable workflow uses `gh pr merge --disable-auto`,
|
||||
# which calls GitHub's GraphQL API. Gitea has no GraphQL endpoint and
|
||||
# returns HTTP 405 on /api/graphql, so the job failed on every Gitea
|
||||
# PR push since the 2026-05-06 migration. Gitea also has no `--auto`
|
||||
# merge primitive that this job could be acting on, so the right
|
||||
# behaviour on Gitea is "no-op + green status" — not a 405.
|
||||
#
|
||||
# Inlining (vs. an `if:` on the `uses:` line) keeps the job ALWAYS
|
||||
# running, which matters for branch protection: required-check names
|
||||
# need a job that emits SUCCESS terminal state, not SKIPPED. See
|
||||
# `feedback_branch_protection_check_name_parity` and `feedback_pr_merge_safety_guards`.
|
||||
#
|
||||
# Issue #88 item 1.
|
||||
# When more PR-time guards land in molecule-ci, add them here as
|
||||
# additional jobs that share the same pull_request:synchronize
|
||||
# trigger.
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
@ -30,34 +19,4 @@ permissions:
|
||||
|
||||
jobs:
|
||||
disable-auto-merge-on-push:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
# Detect Gitea Actions. act_runner sets GITEA_ACTIONS=true in the
|
||||
# step env on every job. Belt-and-suspenders: also check the repo
|
||||
# url's host, which is independent of any runner-side env config
|
||||
# (covers a future Gitea host where the env var is forgotten).
|
||||
- name: Detect runner host
|
||||
id: host
|
||||
run: |
|
||||
if [[ "${GITEA_ACTIONS:-}" == "true" ]] || [[ "${{ github.server_url }}" == *moleculesai.app* ]] || [[ "${{ github.event.repository.html_url }}" == *moleculesai.app* ]]; then
|
||||
echo "is_gitea=true" >> "$GITHUB_OUTPUT"
|
||||
echo "::notice::Gitea Actions detected — auto-merge gating is not applicable here (Gitea has no --auto merge primitive). Job will no-op."
|
||||
else
|
||||
echo "is_gitea=false" >> "$GITHUB_OUTPUT"
|
||||
fi
|
||||
|
||||
- name: Disable auto-merge (GitHub only)
|
||||
if: steps.host.outputs.is_gitea != 'true'
|
||||
env:
|
||||
GH_TOKEN: ${{ github.token }}
|
||||
PR: ${{ github.event.pull_request.number }}
|
||||
REPO: ${{ github.repository }}
|
||||
NEW_SHA: ${{ github.sha }}
|
||||
run: |
|
||||
set -eu
|
||||
gh pr merge "$PR" --disable-auto -R "$REPO" || true
|
||||
gh pr comment "$PR" -R "$REPO" --body "🔒 Auto-merge disabled — new commit (\`${NEW_SHA:0:7}\`) pushed after auto-merge was enabled. The merge queue locks SHAs at entry, so subsequent pushes can race. Verify the new commit and re-enable with \`gh pr merge --auto\`."
|
||||
|
||||
- name: Gitea no-op
|
||||
if: steps.host.outputs.is_gitea == 'true'
|
||||
run: echo "Gitea Actions — auto-merge gating not applicable; no-op (job intentionally green so branch protection's required-check name lands SUCCESS)."
|
||||
uses: molecule-ai/molecule-ci/.github/workflows/disable-auto-merge-on-push.yml@main
|
||||
|
||||
177
.github/workflows/publish-runtime.yml
vendored
177
.github/workflows/publish-runtime.yml
vendored
@ -282,33 +282,42 @@ jobs:
|
||||
echo "::error::Refusing to fan out cascade against stale or corrupt PyPI surfaces."
|
||||
exit 1
|
||||
|
||||
- name: Fan out via push to .runtime-version
|
||||
- name: Fan out repository_dispatch
|
||||
env:
|
||||
# Gitea PAT with write:repository scope on the 8 cascade-active
|
||||
# template repos. Used here for `git push` (NOT for an API
|
||||
# dispatch — Gitea 1.22.6 has no repository_dispatch endpoint;
|
||||
# empirically verified across 6 candidate paths in molecule-
|
||||
# core#20 issuecomment-913). The push trips each template's
|
||||
# existing `on: push: branches: [main]` trigger on
|
||||
# publish-image.yml, which then reads the updated
|
||||
# .runtime-version via its resolve-version job.
|
||||
DISPATCH_TOKEN: ${{ secrets.DISPATCH_TOKEN }}
|
||||
# Fine-grained PAT with `actions:write` on the 8 template repos.
|
||||
# GITHUB_TOKEN can't fire dispatches across repos — needs an explicit
|
||||
# token. Stored as a repo secret; rotate per the standard schedule.
|
||||
DISPATCH_TOKEN: ${{ secrets.TEMPLATE_DISPATCH_TOKEN }}
|
||||
# Single source of truth: the publish job's output, which handles
|
||||
# tag/manual-input/auto-bump uniformly. The previous fallback
|
||||
# (`steps.version.outputs.version` from inside the cascade job)
|
||||
# was a dead reference — different job, no shared step scope.
|
||||
RUNTIME_VERSION: ${{ needs.publish.outputs.version }}
|
||||
run: |
|
||||
set +e # don't abort on a single repo failure — collect them all
|
||||
|
||||
# Soft-skip on workflow_dispatch when the token is missing
|
||||
# (operator ad-hoc test); hard-fail on push so unattended
|
||||
# publishes can't silently skip the cascade. Same shape as
|
||||
# the original v1, intentional split per the schedule-vs-
|
||||
# dispatch hardening 2026-04-28.
|
||||
# Schedule-vs-dispatch behaviour split (hardened 2026-04-28
|
||||
# after the sweep-cf-orphans soft-skip incident — same class
|
||||
# of bug):
|
||||
#
|
||||
# The earlier "skipping cascade. templates will pick up the
|
||||
# new version on their own next rebuild" message was wrong —
|
||||
# templates only build on this dispatch trigger; without it
|
||||
# they stay pinned to whatever runtime version they last saw.
|
||||
# A silent skip here means "PyPI is current, templates are
|
||||
# not" and the gap is invisible until someone notices a
|
||||
# template still on the old version weeks later.
|
||||
#
|
||||
# - push → exit 1 (red CI surfaces the gap)
|
||||
# - workflow_dispatch → exit 0 with a warning (operator
|
||||
# ran this ad-hoc; let them rerun
|
||||
# after fixing the secret)
|
||||
if [ -z "$DISPATCH_TOKEN" ]; then
|
||||
if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
|
||||
echo "::warning::DISPATCH_TOKEN secret not set — skipping cascade."
|
||||
echo "::warning::TEMPLATE_DISPATCH_TOKEN secret not set — skipping cascade."
|
||||
echo "::warning::set it at Settings → Secrets and Variables → Actions, then rerun. Templates will stay on the prior runtime version until either this token is set or each template is rebuilt manually."
|
||||
exit 0
|
||||
fi
|
||||
echo "::error::DISPATCH_TOKEN secret missing — cascade cannot fan out."
|
||||
echo "::error::TEMPLATE_DISPATCH_TOKEN secret missing — cascade cannot fan out."
|
||||
echo "::error::PyPI was published, but the 8 template repos will NOT pick up the new version until this token is restored and a republish dispatches the cascade."
|
||||
echo "::error::set it at Settings → Secrets and Variables → Actions; then re-trigger publish-runtime via workflow_dispatch."
|
||||
exit 1
|
||||
@ -318,119 +327,37 @@ jobs:
|
||||
echo "::error::publish job did not expose a version output — cascade cannot fan out"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# All 9 workspace templates declared in manifest.json. The list
|
||||
# MUST stay aligned with manifest.json's workspace_templates —
|
||||
# cascade-list-drift-gate.yml enforces this in CI per the
|
||||
# codex-stuck-on-stale-runtime invariant from PR #2556.
|
||||
# Long-term goal: derive this list from manifest.json so it
|
||||
# can't drift even on a manifest edit (RFC #388 Phase-1).
|
||||
#
|
||||
# Per-template publish-image.yml presence is checked at
|
||||
# cascade-time below: codex doesn't ship one today, so the
|
||||
# cascade soft-skips it with an informational message rather
|
||||
# than dropping it from this list (which would re-introduce
|
||||
# the drift the gate exists to catch).
|
||||
GITEA_URL="${GITEA_URL:-https://git.moleculesai.app}"
|
||||
# All 9 active workspace template repos. The PR #2536 pruning
|
||||
# ("deprecated, no shipping images") was empirically wrong:
|
||||
# continuous-synth-e2e.yml defaults to langgraph as its primary
|
||||
# canary (line 44), and every excluded template had successful
|
||||
# publish-image runs as of 2026-05-03 — none were dormant.
|
||||
# Symptom of the prune: today's a2a-sdk strict-mode fix
|
||||
# (#2566 / commit e1628c4) cascaded to 4 templates but never
|
||||
# reached langgraph, so the synth-E2E correctly canary'd a fix
|
||||
# that had landed but not deployed. Re-added the 5 templates.
|
||||
# Long-term: derive this list from manifest.json so cascade
|
||||
# scope can't drift from E2E scope — tracked in RFC #388 as a
|
||||
# Phase-1 invariant.
|
||||
TEMPLATES="claude-code hermes openclaw codex langgraph crewai autogen deepagents gemini-cli"
|
||||
FAILED=""
|
||||
SKIPPED=""
|
||||
|
||||
# Configure git identity once. The persona owning DISPATCH_TOKEN
|
||||
# is the same identity that authored this commit on each
|
||||
# template; using a generic "publish-runtime cascade" co-author
|
||||
# trailer in the message keeps the audit trail honest about the
|
||||
# workflow-driven origin.
|
||||
git config --global user.name "publish-runtime cascade"
|
||||
git config --global user.email "publish-runtime@moleculesai.app"
|
||||
|
||||
WORKDIR="$(mktemp -d)"
|
||||
for tpl in $TEMPLATES; do
|
||||
REPO="molecule-ai/molecule-ai-workspace-template-$tpl"
|
||||
CLONE="$WORKDIR/$tpl"
|
||||
|
||||
# Pre-check: skip templates without a publish-image.yml.
|
||||
# The cascade's job is to trip the template's on-push
|
||||
# rebuild — if there's no rebuild workflow, pushing a
|
||||
# .runtime-version commit is just noise on the target
|
||||
# repo. Use the Gitea contents API (no clone required for
|
||||
# the probe). 200 = present; 404 = absent.
|
||||
HTTP=$(curl -sS -o /dev/null -w "%{http_code}" \
|
||||
-H "Authorization: token $DISPATCH_TOKEN" \
|
||||
"$GITEA_URL/api/v1/repos/$REPO/contents/.github/workflows/publish-image.yml")
|
||||
if [ "$HTTP" = "404" ]; then
|
||||
echo "↷ $tpl has no publish-image.yml — soft-skip (informational; manifest still tracks it)"
|
||||
SKIPPED="$SKIPPED $tpl"
|
||||
continue
|
||||
fi
|
||||
if [ "$HTTP" != "200" ]; then
|
||||
echo "::warning::$tpl publish-image.yml probe returned HTTP $HTTP — proceeding anyway, push will surface the real failure if any"
|
||||
fi
|
||||
|
||||
# Use a per-template attempt loop so a transient race (e.g.
|
||||
# human pushing to the same template at the same instant)
|
||||
# doesn't lose the cascade. Bounded retries (3) — beyond
|
||||
# that we surface the failure and let the operator retry.
|
||||
attempt=0
|
||||
success=false
|
||||
while [ $attempt -lt 3 ]; do
|
||||
attempt=$((attempt + 1))
|
||||
rm -rf "$CLONE"
|
||||
if ! git clone --depth=1 \
|
||||
"https://x-access-token:${DISPATCH_TOKEN}@${GITEA_URL#https://}/$REPO.git" \
|
||||
"$CLONE" >/tmp/clone.log 2>&1; then
|
||||
echo "::warning::clone $tpl attempt $attempt failed: $(tail -n3 /tmp/clone.log)"
|
||||
sleep 2
|
||||
continue
|
||||
fi
|
||||
|
||||
cd "$CLONE"
|
||||
echo "$VERSION" > .runtime-version
|
||||
|
||||
# Idempotency guard: if the file already matches, this
|
||||
# publish is a re-run for a version already cascaded.
|
||||
# Don't push a no-op commit (would spuriously re-trip the
|
||||
# template's on-push and rebuild for nothing).
|
||||
if git diff --quiet -- .runtime-version; then
|
||||
echo "✓ $tpl already at $VERSION — no commit needed (idempotent)"
|
||||
success=true
|
||||
cd - >/dev/null
|
||||
break
|
||||
fi
|
||||
|
||||
git add .runtime-version
|
||||
git commit -m "chore: pin runtime to $VERSION (publish-runtime cascade)" \
|
||||
-m "Co-Authored-By: publish-runtime cascade <publish-runtime@moleculesai.app>" \
|
||||
>/dev/null
|
||||
|
||||
if git push origin HEAD:main >/tmp/push.log 2>&1; then
|
||||
echo "✓ $tpl pushed $VERSION on attempt $attempt"
|
||||
success=true
|
||||
cd - >/dev/null
|
||||
break
|
||||
fi
|
||||
|
||||
# Likely a non-fast-forward — pull-rebase and retry.
|
||||
# Don't force-push: that would silently overwrite a racing
|
||||
# human/cascade commit.
|
||||
echo "::warning::push $tpl attempt $attempt failed, pull-rebasing: $(tail -n3 /tmp/push.log)"
|
||||
git pull --rebase origin main >/tmp/rebase.log 2>&1 || true
|
||||
cd - >/dev/null
|
||||
done
|
||||
|
||||
if [ "$success" != "true" ]; then
|
||||
STATUS=$(curl -sS -o /tmp/dispatch.out -w "%{http_code}" \
|
||||
-X POST "https://api.github.com/repos/$REPO/dispatches" \
|
||||
-H "Authorization: Bearer $DISPATCH_TOKEN" \
|
||||
-H "Accept: application/vnd.github+json" \
|
||||
-H "X-GitHub-Api-Version: 2022-11-28" \
|
||||
-d "{\"event_type\":\"runtime-published\",\"client_payload\":{\"runtime_version\":\"$VERSION\"}}")
|
||||
if [ "$STATUS" = "204" ]; then
|
||||
echo "✓ dispatched $tpl ($VERSION)"
|
||||
else
|
||||
echo "::warning::✗ failed to dispatch $tpl: HTTP $STATUS — $(cat /tmp/dispatch.out)"
|
||||
FAILED="$FAILED $tpl"
|
||||
fi
|
||||
done
|
||||
rm -rf "$WORKDIR"
|
||||
|
||||
if [ -n "$FAILED" ]; then
|
||||
echo "::error::Cascade incomplete after 3 retries each. Failed templates:$FAILED"
|
||||
echo "::error::PyPI publish succeeded; failed templates lag the new version. Re-run this workflow_dispatch with the same version to retry only the laggers (idempotent — already-cascaded templates skip)."
|
||||
exit 1
|
||||
fi
|
||||
if [ -n "$SKIPPED" ]; then
|
||||
echo "Cascade complete: pinned $VERSION on cascade-active templates. Soft-skipped (no publish-image.yml):$SKIPPED"
|
||||
else
|
||||
echo "Cascade complete: $VERSION pinned across all manifest workspace_templates."
|
||||
echo "::warning::Cascade incomplete. Failed templates:$FAILED"
|
||||
# Don't fail the whole job — PyPI publish already succeeded;
|
||||
# operators can retry the failed templates manually.
|
||||
fi
|
||||
|
||||
@ -181,7 +181,7 @@ jobs:
|
||||
# were running pre-RFC code. Adding the staging trigger above closes
|
||||
# that gap. Earlier 2026-04-24 incident: a static :staging-<sha> pin
|
||||
# drifted 10 days behind staging — same class of bug, different
|
||||
# mechanism. ECR repo molecule-ai/platform created 2026-05-07.
|
||||
# mechanism.
|
||||
# Build + push platform image with plain `docker` (no buildx).
|
||||
# GIT_SHA bakes into the Go binary via -ldflags so /buildinfo
|
||||
# returns it at runtime — see Dockerfile + buildinfo/buildinfo.go.
|
||||
|
||||
@ -36,7 +36,7 @@ on:
|
||||
workflow_run:
|
||||
workflows: ['publish-workspace-server-image']
|
||||
types: [completed]
|
||||
branches: [main]
|
||||
branches: [staging]
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
target_tag:
|
||||
|
||||
105
.github/workflows/retarget-main-to-staging.yml
vendored
Normal file
105
.github/workflows/retarget-main-to-staging.yml
vendored
Normal file
@ -0,0 +1,105 @@
|
||||
name: Retarget main PRs to staging
|
||||
|
||||
# Mechanical enforcement of SHARED_RULES rule 8 ("Staging-first workflow, no
|
||||
# exceptions"). When a bot opens a PR against main, retarget it to staging
|
||||
# automatically and leave an explanatory comment. Human CEO-authored PRs (the
|
||||
# staging→main promotion PR, etc.) are left alone — they're the authorised
|
||||
# exception to the rule.
|
||||
#
|
||||
# Why an Action instead of only a prompt rule: prompt rules depend on every
|
||||
# role's system-prompt.md staying in sync. Today 5 of 8 engineer roles
|
||||
# (core-be, core-fe, app-fe, app-qa, devops-engineer) don't have the
|
||||
# staging-first section — the bot keeps opening PRs to main. An Action
|
||||
# enforces the invariant regardless of prompt drift.
|
||||
|
||||
on:
|
||||
pull_request_target:
|
||||
types: [opened, reopened]
|
||||
branches: [main]
|
||||
|
||||
permissions:
|
||||
pull-requests: write
|
||||
|
||||
jobs:
|
||||
retarget:
|
||||
name: Retarget to staging
|
||||
runs-on: ubuntu-latest
|
||||
# Only fire for bot-authored PRs. Human CEO PRs (staging→main promotion)
|
||||
# are intentional and pass through.
|
||||
#
|
||||
# Head-ref guard: never retarget a PR whose head IS `staging` — those
|
||||
# are the auto-promote staging→main PRs (opened by molecule-ai[bot]
|
||||
# since #2586 switched to an App token, which now passes the bot
|
||||
# filter below). Retargeting head=staging onto base=staging fails
|
||||
# with HTTP 422 "no new commits between base 'staging' and head
|
||||
# 'staging'", which used to surface as a noisy red workflow run on
|
||||
# every auto-promote (caught 2026-05-03 on PR #2588).
|
||||
if: >-
|
||||
github.event.pull_request.head.ref != 'staging'
|
||||
&& (
|
||||
github.event.pull_request.user.type == 'Bot'
|
||||
|| endsWith(github.event.pull_request.user.login, '[bot]')
|
||||
|| github.event.pull_request.user.login == 'app/molecule-ai'
|
||||
|| github.event.pull_request.user.login == 'molecule-ai[bot]'
|
||||
)
|
||||
steps:
|
||||
- name: Retarget PR base to staging
|
||||
id: retarget
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
PR_NUMBER: ${{ github.event.pull_request.number }}
|
||||
PR_AUTHOR: ${{ github.event.pull_request.user.login }}
|
||||
# Issue #1884: when the bot opens a PR against main and there's
|
||||
# already another PR on the same head branch targeting staging,
|
||||
# GitHub's PATCH /pulls returns 422 with
|
||||
# "A pull request already exists for base branch 'staging' …".
|
||||
# The retarget can't proceed — but the right response is to
|
||||
# close the now-redundant main-PR, not to fail the workflow
|
||||
# noisily. Detect that specific 422 and close instead.
|
||||
run: |
|
||||
set +e
|
||||
echo "Retargeting PR #${PR_NUMBER} (author: ${PR_AUTHOR}) from main → staging"
|
||||
PATCH_OUTPUT=$(gh api -X PATCH \
|
||||
"repos/${{ github.repository }}/pulls/${PR_NUMBER}" \
|
||||
-f base=staging \
|
||||
--jq '.base.ref' 2>&1)
|
||||
PATCH_EXIT=$?
|
||||
set -e
|
||||
if [ "$PATCH_EXIT" -eq 0 ]; then
|
||||
echo "::notice::Retargeted PR #${PR_NUMBER} → staging"
|
||||
echo "outcome=retargeted" >> "$GITHUB_OUTPUT"
|
||||
exit 0
|
||||
fi
|
||||
# Specifically match the 422 duplicate-base/head error so
|
||||
# any OTHER PATCH failure (auth, deleted PR, etc.) still
|
||||
# surfaces as a real workflow failure.
|
||||
if echo "$PATCH_OUTPUT" | grep -q "pull request already exists for base branch 'staging'"; then
|
||||
echo "::notice::PR #${PR_NUMBER}: duplicate target-staging PR exists on same head — closing this main-PR as redundant."
|
||||
gh pr close "$PR_NUMBER" \
|
||||
--repo "${{ github.repository }}" \
|
||||
--comment "[retarget-bot] Closing — another PR on the same head branch already targets \`staging\`. This PR is redundant. See issue #1884 for the rationale."
|
||||
echo "outcome=closed-as-duplicate" >> "$GITHUB_OUTPUT"
|
||||
exit 0
|
||||
fi
|
||||
echo "::error::Retarget PATCH failed and was NOT a duplicate-base error:"
|
||||
echo "$PATCH_OUTPUT" >&2
|
||||
exit 1
|
||||
|
||||
- name: Post explainer comment
|
||||
if: steps.retarget.outputs.outcome == 'retargeted'
|
||||
env:
|
||||
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
PR_NUMBER: ${{ github.event.pull_request.number }}
|
||||
run: |
|
||||
gh pr comment "$PR_NUMBER" \
|
||||
--repo "${{ github.repository }}" \
|
||||
--body "$(cat <<'BODY'
|
||||
[retarget-bot] This PR was opened against `main` and has been retargeted to `staging` automatically.
|
||||
|
||||
**Why:** per [SHARED_RULES rule 8](https://github.com/molecule-ai/molecule-ai-org-template-molecule-dev/blob/main/SHARED_RULES.md), all feature work targets `staging` first; the CEO promotes `staging → main` separately.
|
||||
|
||||
**What changed:** just the base branch — no code change. CI will re-run against `staging`. If you get merge conflicts, rebase on `staging`.
|
||||
|
||||
**If this PR is the CEO's staging→main promotion:** the Action skipped you (only bot-authored PRs are retargeted). If you see this comment on your CEO PR, that's a bug — please tag @HongmingWang-Rabbit.
|
||||
BODY
|
||||
)"
|
||||
@ -22,7 +22,7 @@ development workflow, conventions, and how to get your changes merged.
|
||||
|
||||
```bash
|
||||
# Clone the repo
|
||||
git clone https://git.moleculesai.app/molecule-ai/molecule-core.git
|
||||
git clone https://github.com/Molecule-AI/molecule-core.git
|
||||
cd molecule-core
|
||||
|
||||
# Install git hooks
|
||||
@ -57,7 +57,7 @@ See `CLAUDE.md` for a full list of environment variables and their purposes.
|
||||
|
||||
This repo is scoped to **code** (canvas, workspace, workspace-server, related
|
||||
infra). Public content (blog posts, marketing copy, OG images, SEO briefs,
|
||||
DevRel demos) lives in [`Molecule-AI/docs`](https://git.moleculesai.app/molecule-ai/docs).
|
||||
DevRel demos) lives in [`Molecule-AI/docs`](https://github.com/Molecule-AI/docs).
|
||||
The `Block forbidden paths` CI gate fails any PR that writes to `marketing/`
|
||||
or other removed paths — open against `Molecule-AI/docs` instead.
|
||||
|
||||
@ -110,7 +110,7 @@ causing a render loop when any node position changed.
|
||||
|
||||
1. **Repo-wide:** "Automatically delete head branches" is on. Once a PR merges, the branch is deleted server-side. Any subsequent `git push` to that branch fails with `remote rejected — no such branch`.
|
||||
|
||||
2. **CI:** the `pr-guards` workflow (calling [molecule-ci `disable-auto-merge-on-push`](https://git.moleculesai.app/molecule-ai/molecule-ci/src/branch/main/.github/workflows/disable-auto-merge-on-push.yml)) fires on every push to an open PR. If auto-merge was already enabled, it's disabled and a comment is posted. You must explicitly re-enable after verifying the new commit.
|
||||
2. **CI:** the `pr-guards` workflow (calling [molecule-ci `disable-auto-merge-on-push`](https://github.com/Molecule-AI/molecule-ci/blob/main/.github/workflows/disable-auto-merge-on-push.yml)) fires on every push to an open PR. If auto-merge was already enabled, it's disabled and a comment is posted. You must explicitly re-enable after verifying the new commit.
|
||||
|
||||
**Workflow rules that follow from the guards:**
|
||||
- Push **all** commits before running `gh pr merge --auto`.
|
||||
@ -180,9 +180,9 @@ and run CI manually.
|
||||
Code in this repo lands in molecule-core. Some related runtime artifacts
|
||||
live in their own repos:
|
||||
|
||||
- [`Molecule-AI/molecule-ai-workspace-runtime`](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-runtime) — Python adapter SDK (`molecule_runtime`) that runs inside containerized Molecule workspaces. Bridges Claude Code SDK / hermes / langgraph / etc. → A2A queue.
|
||||
- [`Molecule-AI/molecule-sdk-python`](https://git.moleculesai.app/molecule-ai/molecule-sdk-python) — `A2AServer` + `RemoteAgentClient` for external agents that register over the public `/registry/register` flow.
|
||||
- [`Molecule-AI/molecule-mcp-claude-channel`](https://git.moleculesai.app/molecule-ai/molecule-mcp-claude-channel) — Claude Code channel plugin. Bridges A2A traffic into a running Claude Code session via MCP `notifications/claude/channel`. Polling-based (no tunnel required); install with `claude --channels plugin:molecule@Molecule-AI/molecule-mcp-claude-channel`.
|
||||
- [`Molecule-AI/molecule-ai-workspace-runtime`](https://github.com/Molecule-AI/molecule-ai-workspace-runtime) — Python adapter SDK (`molecule_runtime`) that runs inside containerized Molecule workspaces. Bridges Claude Code SDK / hermes / langgraph / etc. → A2A queue.
|
||||
- [`Molecule-AI/molecule-sdk-python`](https://github.com/Molecule-AI/molecule-sdk-python) — `A2AServer` + `RemoteAgentClient` for external agents that register over the public `/registry/register` flow.
|
||||
- [`Molecule-AI/molecule-mcp-claude-channel`](https://github.com/Molecule-AI/molecule-mcp-claude-channel) — Claude Code channel plugin. Bridges A2A traffic into a running Claude Code session via MCP `notifications/claude/channel`. Polling-based (no tunnel required); install with `claude --channels plugin:molecule@Molecule-AI/molecule-mcp-claude-channel`.
|
||||
|
||||
When extending the **A2A surface** in molecule-core (`workspace-server/internal/handlers/a2a_proxy.go` etc.), consider whether the change has a downstream impact on the runtime SDK or the channel plugin — they're versioned independently but share the wire shape.
|
||||
|
||||
|
||||
28
Makefile
28
Makefile
@ -1,28 +0,0 @@
|
||||
# Top-level Makefile — convenience wrappers around docker compose.
|
||||
#
|
||||
# Most molecule-core dev work happens via these shortcuts. CI doesn't
|
||||
# use this Makefile; CI calls docker compose / go test directly so the
|
||||
# Makefile can evolve without breaking the build.
|
||||
|
||||
.PHONY: help dev up down logs build test
|
||||
|
||||
help: ## Show this help.
|
||||
@grep -E '^[a-zA-Z_-]+:.*?## ' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-12s\033[0m %s\n", $$1, $$2}'
|
||||
|
||||
dev: ## Start the full stack with air hot-reload for the platform service.
|
||||
docker compose -f docker-compose.yml -f docker-compose.dev.yml up
|
||||
|
||||
up: ## Start the full stack in production-shape mode (no air, normal Dockerfile).
|
||||
docker compose up
|
||||
|
||||
down: ## Stop the stack and remove containers (volumes preserved).
|
||||
docker compose down
|
||||
|
||||
logs: ## Tail logs from all services (Ctrl-C to detach).
|
||||
docker compose logs -f
|
||||
|
||||
build: ## Force a fresh build of the platform image (no cache).
|
||||
docker compose build --no-cache platform
|
||||
|
||||
test: ## Run Go unit tests in workspace-server/.
|
||||
cd workspace-server && go test -race ./...
|
||||
75
README.md
75
README.md
@ -1,7 +1,7 @@
|
||||
<div align="center">
|
||||
|
||||
<p>
|
||||
<img src="./docs/assets/branding/molecule-icon.svg" alt="Molecule AI" width="160" />
|
||||
<img src="./docs/assets/branding/molecule-icon.png" alt="Molecule AI Icon Logo" width="160" />
|
||||
</p>
|
||||
|
||||
<p>
|
||||
@ -39,8 +39,8 @@
|
||||
<a href="./docs/agent-runtime/workspace-runtime.md"><strong>Workspace Runtime</strong></a>
|
||||
</p>
|
||||
|
||||
[](https://railway.app/new/template?template=https://git.moleculesai.app/molecule-ai/molecule-core)
|
||||
[](https://render.com/deploy?repo=https://git.moleculesai.app/molecule-ai/molecule-core)
|
||||
[](https://railway.app/new/template?template=https://github.com/Molecule-AI/molecule-monorepo)
|
||||
[](https://render.com/deploy?repo=https://github.com/Molecule-AI/molecule-monorepo)
|
||||
|
||||
</div>
|
||||
|
||||
@ -53,8 +53,8 @@ Molecule AI is the most powerful way to govern an AI agent organization in produ
|
||||
It combines the parts that are usually scattered across demos, internal glue code, and framework-specific tooling into one product:
|
||||
|
||||
- one org-native control plane for teams, roles, hierarchy, and lifecycle
|
||||
- one runtime layer that lets **eight** agent runtimes — LangGraph, DeepAgents, Claude Code, CrewAI, AutoGen, **Hermes**, **Gemini CLI**, and OpenClaw — run side by side behind one workspace contract
|
||||
- one memory model that keeps recall, sharing, and skill evolution aligned with organizational boundaries (Memory v2 backed by pgvector for semantic recall)
|
||||
- one runtime layer that lets LangGraph, DeepAgents, Claude Code, CrewAI, AutoGen, and OpenClaw run side by side
|
||||
- one memory model that keeps recall, sharing, and skill evolution aligned with organizational boundaries
|
||||
- one operational surface for observing, pausing, restarting, inspecting, and improving live workspaces
|
||||
|
||||
Most teams can build a workflow, a strong single agent, a coding agent, or a custom multi-agent graph.
|
||||
@ -75,7 +75,7 @@ You do not wire collaboration paths by hand. Hierarchy defines the default commu
|
||||
|
||||
### 3. Runtime choice stops being a dead-end decision
|
||||
|
||||
LangGraph, DeepAgents, Claude Code, CrewAI, AutoGen, Hermes, Gemini CLI, and OpenClaw can all plug into the same workspace abstraction. Teams can standardize governance without forcing every group onto one runtime.
|
||||
LangGraph, DeepAgents, Claude Code, CrewAI, AutoGen, and OpenClaw can all plug into the same workspace abstraction. Teams can standardize governance without forcing every group onto one runtime.
|
||||
|
||||
### 4. Memory is treated like infrastructure
|
||||
|
||||
@ -117,8 +117,6 @@ Molecule AI is not trying to replace the frameworks below. It is the system that
|
||||
| **Claude Code** | Shipping on `main` | Real coding workflows, CLI-native continuity | Secure workspace abstraction, A2A delegation, org boundaries, shared control plane |
|
||||
| **CrewAI** | Shipping on `main` | Role-based crews | Persistent workspace identity, policy consistency, shared canvas and registry |
|
||||
| **AutoGen** | Shipping on `main` | Assistant/tool orchestration | Standardized deployment, hierarchy-aware collaboration, shared ops plane |
|
||||
| **Hermes 4** | Shipping on `main` | Hybrid reasoning, native tools, json_schema (NousResearch/hermes-agent) | Option B upstream hook, A2A bridge to OpenAI-compat API, multi-provider provider derivation |
|
||||
| **Gemini CLI** | Shipping on `main` | Google Gemini CLI continuity | Workspace lifecycle, A2A, hierarchy-aware collaboration, shared ops plane |
|
||||
| **OpenClaw** | Shipping on `main` | CLI-native runtime with its own session model | Workspace lifecycle, templates, activity logs, topology-aware collaboration |
|
||||
| **NemoClaw** | WIP on `feat/nemoclaw-t4-docker` | NVIDIA-oriented runtime path | Planned to join the same abstraction once merged; not yet part of `main` |
|
||||
|
||||
@ -184,10 +182,9 @@ The result is not just “an agent that learns.” It is **an organization that
|
||||
|
||||
## What Ships In `main`
|
||||
|
||||
### Canvas (v4)
|
||||
### Canvas
|
||||
|
||||
- Next.js 15 + React Flow + Zustand
|
||||
- **warm-paper theme system** — light / dark / follow-system, SSR cookie + nonce'd boot script + ThemeProvider; terminal + code surfaces stay dark unconditionally
|
||||
- drag-to-nest team building
|
||||
- empty-state deployment + onboarding wizard
|
||||
- template palette
|
||||
@ -196,9 +193,8 @@ The result is not just “an agent that learns.” It is **an organization that
|
||||
|
||||
### Platform
|
||||
|
||||
- Go 1.25 / Gin control plane (80+ HTTP endpoints + Gorilla WebSocket fanout)
|
||||
- workspace CRUD and provisioning (pluggable Provisioner — Docker locally, EC2 + SSM in production)
|
||||
- **A2A response path is a typed discriminated union (RFC #2967)** — frozen dataclasses + total parser; 100% unit + adversarial fuzz coverage
|
||||
- Go/Gin control plane
|
||||
- workspace CRUD and provisioning
|
||||
- registry and heartbeats
|
||||
- browser-safe A2A proxy
|
||||
- team expansion/collapse
|
||||
@ -208,10 +204,10 @@ The result is not just “an agent that learns.” It is **an organization that
|
||||
|
||||
### Runtime
|
||||
|
||||
- unified `workspace/` image; thin AMI in production (us-east-2)
|
||||
- adapter-driven execution across **8 runtimes** (Claude Code, Hermes, Gemini CLI, LangGraph, DeepAgents, CrewAI, AutoGen, OpenClaw)
|
||||
- unified `workspace/` image
|
||||
- adapter-driven execution
|
||||
- Agent Card registration
|
||||
- awareness-backed memory integration; **Memory v2 backed by pgvector** for semantic recall
|
||||
- awareness-backed memory integration
|
||||
- plugin-mounted shared rules/skills
|
||||
- hot-reloadable local skills
|
||||
- coordinator-only delegation path
|
||||
@ -225,21 +221,6 @@ The result is not just “an agent that learns.” It is **an organization that
|
||||
- runtime tiers
|
||||
- direct workspace inspection through terminal and files
|
||||
|
||||
### SaaS (via [`molecule-controlplane`](https://git.moleculesai.app/molecule-ai/molecule-controlplane))
|
||||
|
||||
- multi-tenant on AWS EC2 + Neon (per-tenant Postgres branch) + Cloudflare Tunnels (per-tenant, no public ports)
|
||||
- WorkOS AuthKit + Stripe Checkout + Customer Portal
|
||||
- AWS KMS envelope encryption (DB / Redis connection strings); AWS Secrets Manager for tenant bootstrap
|
||||
- `tenant_resources` audit table + 30-min boot-event-aware reconciler — every CF / AWS lifecycle event recorded, claim vs live state diffed
|
||||
|
||||
### Bring your own Claude Code session (via [`molecule-mcp-claude-channel`](https://git.moleculesai.app/molecule-ai/molecule-mcp-claude-channel))
|
||||
|
||||
- Claude Code plugin that bridges Molecule A2A traffic into a local Claude Code session via MCP
|
||||
- subscribe to one or more workspaces; peer messages surface as conversation turns; replies route back through Molecule's A2A
|
||||
- no tunnel, no public endpoint — the plugin self-registers each watched workspace as `delivery_mode=poll` and long-polls `/activity?since_id=…`
|
||||
- multi-tenant friendly: one plugin install can watch workspaces across multiple Molecule tenants (`MOLECULE_PLATFORM_URLS` per-workspace)
|
||||
- install via the standard marketplace flow: `/plugin marketplace add Molecule-AI/molecule-mcp-claude-channel` → `/plugin install molecule-channel@molecule-mcp-claude-channel`
|
||||
|
||||
## Built For Teams That Need More Than A Demo
|
||||
|
||||
Molecule AI is especially strong when you need to run:
|
||||
@ -252,30 +233,24 @@ Molecule AI is especially strong when you need to run:
|
||||
## Architecture
|
||||
|
||||
```text
|
||||
Canvas (Next.js 15, warm-paper :3000) <--HTTP / WS--> Platform (Go 1.25 :8080) <---> Postgres + Redis
|
||||
| |
|
||||
| +--> Provisioner: Docker (local) / EC2 + SSM (prod)
|
||||
| +--> bundles · templates · secrets · KMS
|
||||
Canvas (Next.js :3000) <--HTTP / WS--> Platform (Go :8080) <---> Postgres + Redis
|
||||
| |
|
||||
| +--> Docker provisioner / bundles / templates / secrets
|
||||
|
|
||||
+------------------------- shows ------------------------> workspaces, teams, tasks, traces, events
|
||||
+-------------------- shows --------------------> workspaces, teams, tasks, traces, events
|
||||
|
||||
Workspace Runtime (Python ≥3.11, image with adapters)
|
||||
- 8 adapters: LangGraph / DeepAgents / Claude Code / CrewAI / AutoGen / Hermes / Gemini CLI / OpenClaw
|
||||
- Agent Card + A2A server (typed-SSOT response path, RFC #2967)
|
||||
- heartbeat + activity + awareness-backed memory (Memory v2 — pgvector semantic recall)
|
||||
Workspace Runtime (Python image with adapters)
|
||||
- LangGraph / DeepAgents / Claude Code / CrewAI / AutoGen / OpenClaw
|
||||
- Agent Card + A2A server
|
||||
- heartbeat + activity + awareness-backed memory
|
||||
- skills + plugins + hot reload
|
||||
|
||||
SaaS Control Plane (molecule-controlplane, private)
|
||||
- per-tenant EC2 + Neon (Postgres branch) + Cloudflare Tunnel
|
||||
- WorkOS · Stripe · KMS · AWS Secrets Manager
|
||||
- tenant_resources audit + 30-min reconciler
|
||||
```
|
||||
|
||||
## Quick Start
|
||||
|
||||
```bash
|
||||
git clone https://git.moleculesai.app/molecule-ai/molecule-core.git
|
||||
cd molecule-core
|
||||
git clone https://github.com/Molecule-AI/molecule-monorepo.git
|
||||
cd molecule-monorepo
|
||||
|
||||
cp .env.example .env
|
||||
# Defaults boot the stack locally out of the box. See .env.example for
|
||||
@ -328,11 +303,7 @@ Then open `http://localhost:3000`:
|
||||
|
||||
## Current Scope
|
||||
|
||||
The current `main` branch ships the core platform, Canvas v4 (warm-paper themed), Memory v2 (pgvector semantic recall), the typed-SSOT A2A response path (RFC #2967), **eight production adapters** (Claude Code, Hermes, Gemini CLI, LangGraph, DeepAgents, CrewAI, AutoGen, OpenClaw), skill lifecycle, and operational surfaces.
|
||||
|
||||
The companion private repo [`molecule-controlplane`](https://git.moleculesai.app/molecule-ai/molecule-controlplane) provides the SaaS surface — multi-tenant orchestration on EC2 + Neon + Cloudflare Tunnels, KMS envelope encryption, WorkOS auth, Stripe billing, and a `tenant_resources` audit table with a 30-min reconciler.
|
||||
|
||||
Adjacent runtime work such as **NemoClaw** remains branch-level until merged, and this README keeps that distinction explicit on purpose.
|
||||
The current `main` branch already includes the core platform, canvas, memory model, six production adapters, skill lifecycle, and operational surfaces. Adjacent runtime work such as **NemoClaw** remains branch-level until merged, and this README keeps that distinction explicit on purpose.
|
||||
|
||||
## License
|
||||
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
<div align="center">
|
||||
|
||||
<p>
|
||||
<img src="./docs/assets/branding/molecule-icon.svg" alt="Molecule AI" width="160" />
|
||||
<img src="./docs/assets/branding/molecule-icon.png" alt="Molecule AI 图案 Logo" width="160" />
|
||||
</p>
|
||||
|
||||
<p>
|
||||
@ -38,8 +38,8 @@
|
||||
<a href="./docs/agent-runtime/workspace-runtime.md"><strong>Workspace Runtime</strong></a>
|
||||
</p>
|
||||
|
||||
[](https://railway.app/new/template?template=https://git.moleculesai.app/molecule-ai/molecule-core)
|
||||
[](https://render.com/deploy?repo=https://git.moleculesai.app/molecule-ai/molecule-core)
|
||||
[](https://railway.app/new/template?template=https://github.com/Molecule-AI/molecule-core)
|
||||
[](https://render.com/deploy?repo=https://github.com/Molecule-AI/molecule-core)
|
||||
|
||||
</div>
|
||||
|
||||
@ -52,8 +52,8 @@ Molecule AI 是目前最强的 AI Agent 组织治理方案之一，用来把 age
|
||||
它把过去分散在 demo、内部胶水代码和各类 framework 私有工具里的关键能力，收敛成一个产品：
|
||||
|
||||
- 一套组织原生 control plane，管理团队、角色、层级和生命周期
|
||||
- 一套 runtime abstraction，让 **8 个** agent runtime —— LangGraph、DeepAgents、Claude Code、CrewAI、AutoGen、**Hermes**、**Gemini CLI**、OpenClaw —— 共用一套 workspace 契约
|
||||
- 一套与组织边界对齐的 memory 模型，把 recall、sharing 和 skill evolution 放进同一体系（Memory v2 由 pgvector 支撑语义召回）
|
||||
- 一套 runtime abstraction，让 LangGraph、DeepAgents、Claude Code、CrewAI、AutoGen、OpenClaw 并存运行
|
||||
- 一套与组织边界对齐的 memory 模型，把 recall、sharing 和 skill evolution 放进同一体系
|
||||
- 一套面向线上 workspace 的运维面，统一完成观测、暂停、重启、检查和持续改进
|
||||
|
||||
今天很多团队能做好 workflow、单 agent、coding agent，或者自定义 multi-agent graph 中的一种。
|
||||
@ -74,7 +74,7 @@ Molecule AI 填的就是这个空白。
|
||||
|
||||
### 3. Runtime 选择不再是死路
|
||||
|
||||
LangGraph、DeepAgents、Claude Code、CrewAI、AutoGen、Hermes、Gemini CLI、OpenClaw 都可以挂到同一个 workspace abstraction 下。团队可以统一治理方式，而不必统一到底层 runtime。
|
||||
LangGraph、DeepAgents、Claude Code、CrewAI、AutoGen、OpenClaw 都可以挂到同一个 workspace abstraction 下。团队可以统一治理方式，而不必统一到底层 runtime。
|
||||
|
||||
### 4. Memory 被当成基础设施来做
|
||||
|
||||
@ -116,8 +116,6 @@ Molecule AI 并不是要替代下面这些 framework，而是把它们纳入更
|
||||
| **Claude Code** | `main` 已支持 | 真实编码工作流、CLI-native continuity | 安全 workspace 抽象、A2A delegation、组织边界、共享 control plane |
|
||||
| **CrewAI** | `main` 已支持 | 角色型 crew 模式清晰 | 持久 workspace 身份、统一策略、共享 Canvas 和 registry |
|
||||
| **AutoGen** | `main` 已支持 | assistant/tool orchestration | 统一部署、层级协作、共享运维平面 |
|
||||
| **Hermes 4** | `main` 已支持 | 混合推理、原生工具调用、json_schema 输出（NousResearch/hermes-agent） | Option B 上游 hook、A2A 桥接 OpenAI 兼容 API、多 provider 自动派生 |
|
||||
| **Gemini CLI** | `main` 已支持 | Google Gemini CLI 持续会话 | workspace 生命周期、A2A、层级感知协作、共享运维平面 |
|
||||
| **OpenClaw** | `main` 已支持 | CLI-native runtime，自有 session 模型 | workspace 生命周期、templates、activity logs、拓扑感知协作 |
|
||||
| **NemoClaw** | `feat/nemoclaw-t4-docker` 分支 WIP | NVIDIA 方向 runtime 路线 | 计划并入同一抽象层，但当前还不是 `main` 已合并能力 |
|
||||
|
||||
@ -183,10 +181,9 @@ Molecule AI 并不是要替代下面这些 framework，而是把它们纳入更
|
||||
|
||||
## `main` 分支已经具备什么
|
||||
|
||||
### Canvas（v4）
|
||||
### Canvas
|
||||
|
||||
- Next.js 15 + React Flow + Zustand
|
||||
- **warm-paper 主题系统** —— light / dark / 跟随系统；SSR cookie + nonce'd boot 脚本 + ThemeProvider；终端与代码面板始终保持深色
|
||||
- drag-to-nest 团队构建
|
||||
- empty state + onboarding wizard
|
||||
- template palette
|
||||
@ -195,9 +192,8 @@ Molecule AI 并不是要替代下面这些 framework，而是把它们纳入更
|
||||
|
||||
### Platform
|
||||
|
||||
- Go 1.25 / Gin control plane（80+ HTTP 端点 + Gorilla WebSocket fanout）
|
||||
- workspace CRUD 和 provisioning（可插拔 Provisioner —— 本地 Docker、生产 EC2 + SSM）
|
||||
- **A2A 响应路径已收敛为类型化的判别联合（RFC #2967）** —— 冻结 dataclass + 全量 parser；100% 单元测试 + 对抗性 fuzz 覆盖
|
||||
- Go/Gin control plane
|
||||
- workspace CRUD 和 provisioning
|
||||
- registry 与 heartbeat
|
||||
- 浏览器安全的 A2A proxy
|
||||
- team expansion/collapse
|
||||
@ -207,10 +203,10 @@ Molecule AI 并不是要替代下面这些 framework，而是把它们纳入更
|
||||
|
||||
### Runtime
|
||||
|
||||
- 统一 `workspace/` 镜像；生产环境采用 thin AMI（us-east-2）
|
||||
- adapter 驱动执行，覆盖 **8 个 runtime**（Claude Code、Hermes、Gemini CLI、LangGraph、DeepAgents、CrewAI、AutoGen、OpenClaw）
|
||||
- 统一 `workspace/` 镜像
|
||||
- adapter 驱动执行
|
||||
- Agent Card 注册
|
||||
- awareness-backed memory；**Memory v2 由 pgvector 支撑**语义召回
|
||||
- awareness-backed memory
|
||||
- plugin 挂载共享 rules/skills
|
||||
- 本地 skills 热加载
|
||||
- coordinator-only delegation 路径
|
||||
@ -224,21 +220,6 @@ Molecule AI 并不是要替代下面这些 framework，而是把它们纳入更
|
||||
- runtime tiers
|
||||
- 终端与文件层面的 workspace 直接排障
|
||||
|
||||
### SaaS（由 [`molecule-controlplane`](https://git.moleculesai.app/molecule-ai/molecule-controlplane) 提供）
|
||||
|
||||
- 多租户运行在 AWS EC2 + Neon（每租户一个 Postgres branch）+ Cloudflare Tunnels（每租户一条隧道，对外不开任何端口）
|
||||
- WorkOS AuthKit + Stripe Checkout + Customer Portal
|
||||
- AWS KMS 信封加密（DB / Redis 连接串）；AWS Secrets Manager 负责租户 bootstrap
|
||||
- `tenant_resources` 审计表 + 30 分钟 boot-event-aware reconciler —— 每个 CF / AWS lifecycle 事件都有记录，每 30 分钟比对 claim 与实际状态
|
||||
|
||||
### 在 Claude Code 里直接接入（由 [`molecule-mcp-claude-channel`](https://git.moleculesai.app/molecule-ai/molecule-mcp-claude-channel) 提供）
|
||||
|
||||
- 把 Molecule A2A 流量桥接到本地 Claude Code 会话的 MCP 插件
|
||||
- 订阅一个或多个 workspace；peer 的消息会以 user-turn 出现，回复会经 Molecule A2A 路由出去
|
||||
- 无需公网隧道、无需公开端点 —— 插件启动时自动把每个 watched workspace 注册成 `delivery_mode=poll`，长轮询 `/activity?since_id=…`
|
||||
- 多租户友好：单次安装即可同时 watch 跨多个 Molecule 租户的 workspace（`MOLECULE_PLATFORM_URLS` 按 workspace 配置）
|
||||
- 通过标准 marketplace 流程安装：`/plugin marketplace add Molecule-AI/molecule-mcp-claude-channel` → `/plugin install molecule-channel@molecule-mcp-claude-channel`
|
||||
|
||||
## 适合什么团队
|
||||
|
||||
Molecule AI 特别适合下面这些场景：
|
||||
@ -251,29 +232,23 @@ Molecule AI 特别适合下面这些场景：
|
||||
## 架构总览
|
||||
|
||||
```text
|
||||
Canvas (Next.js 15, warm-paper :3000) <--HTTP / WS--> Platform (Go 1.25 :8080) <---> Postgres + Redis
|
||||
| |
|
||||
| +--> Provisioner: Docker (本地) / EC2 + SSM (生产)
|
||||
| +--> bundles · templates · secrets · KMS
|
||||
Canvas (Next.js :3000) <--HTTP / WS--> Platform (Go :8080) <---> Postgres + Redis
|
||||
| |
|
||||
| +--> Docker provisioner / bundles / templates / secrets
|
||||
|
|
||||
+------------------------- 展示 ------------------------> workspaces, teams, tasks, traces, events
|
||||
+-------------------- 展示 --------------------> workspaces, teams, tasks, traces, events
|
||||
|
||||
Workspace Runtime (Python ≥3.11，含 adapter 集合的镜像)
|
||||
- 8 个 adapter: LangGraph / DeepAgents / Claude Code / CrewAI / AutoGen / Hermes / Gemini CLI / OpenClaw
|
||||
- Agent Card + A2A server（typed-SSOT 响应路径，RFC #2967）
|
||||
- heartbeat + activity + awareness-backed memory（Memory v2 —— pgvector 语义召回）
|
||||
Workspace Runtime (Python image with adapters)
|
||||
- LangGraph / DeepAgents / Claude Code / CrewAI / AutoGen / OpenClaw
|
||||
- Agent Card + A2A server
|
||||
- heartbeat + activity + awareness-backed memory
|
||||
- skills + plugins + hot reload
|
||||
|
||||
SaaS Control Plane (molecule-controlplane，私有)
|
||||
- 每租户 EC2 + Neon (Postgres branch) + Cloudflare Tunnel
|
||||
- WorkOS · Stripe · KMS · AWS Secrets Manager
|
||||
- tenant_resources 审计 + 30 分钟 reconciler
|
||||
```
|
||||
|
||||
## 快速开始
|
||||
|
||||
```bash
|
||||
git clone https://git.moleculesai.app/molecule-ai/molecule-core.git
|
||||
git clone https://github.com/Molecule-AI/molecule-core.git
|
||||
cd molecule-core
|
||||
|
||||
cp .env.example .env
|
||||
@ -321,11 +296,7 @@ npm run dev
|
||||
|
||||
## 当前范围说明
|
||||
|
||||
当前 `main` 已经包含核心平台、Canvas v4（warm-paper 主题）、Memory v2（pgvector 语义召回）、typed-SSOT A2A 响应路径（RFC #2967）、**8 个正式 adapter**（Claude Code、Hermes、Gemini CLI、LangGraph、DeepAgents、CrewAI、AutoGen、OpenClaw）、skill lifecycle，以及主要运维面。
|
||||
|
||||
配套的私有仓库 [`molecule-controlplane`](https://git.moleculesai.app/molecule-ai/molecule-controlplane) 提供 SaaS 层 —— 多租户编排（EC2 + Neon + Cloudflare Tunnels）、KMS 信封加密、WorkOS 鉴权、Stripe 计费，以及 `tenant_resources` 审计表加 30 分钟 reconciler。
|
||||
|
||||
像 **NemoClaw** 这样的相邻 runtime 路线仍然属于分支级工作，只有合并后才会进入正式支持列表，这里会明确区分。
|
||||
当前 `main` 已经包含核心平台、Canvas、memory model、6 个正式 adapter、skill lifecycle 和主要运维面。像 **NemoClaw** 这样的相邻 runtime 路线仍然属于分支级工作，只有合并后才会进入正式支持列表，这里会明确区分。
|
||||
|
||||
## License
|
||||
|
||||
|
||||
@ -1,10 +0,0 @@
|
||||
# Excluded from `docker build` context. Without this, the COPY . . step in
|
||||
# canvas/Dockerfile clobbers the freshly-installed node_modules with the
|
||||
# host's (potentially broken / wrong-arch) copy — the @tailwindcss/oxide
|
||||
# native binary disagreed and broke `next build`.
|
||||
node_modules
|
||||
.next
|
||||
.git
|
||||
*.log
|
||||
.env*
|
||||
!.env.example
|
||||
@ -1,11 +1,7 @@
|
||||
FROM node:22-alpine AS builder
|
||||
WORKDIR /app
|
||||
COPY package.json package-lock.json* ./
|
||||
# `npm ci` (not `install`) for lockfile-exact reproducibility.
|
||||
# `--include=optional` ensures the platform-specific @tailwindcss/oxide
|
||||
# native binary lands — without it, postcss fails with "Cannot read
|
||||
# properties of undefined (reading 'All')" at build time.
|
||||
RUN npm ci --include=optional
|
||||
RUN npm install
|
||||
COPY . .
|
||||
ARG NEXT_PUBLIC_PLATFORM_URL=http://localhost:8080
|
||||
ARG NEXT_PUBLIC_WS_URL=ws://localhost:8080/ws
|
||||
|
||||
@ -17,24 +17,6 @@ import { dirname, join } from "node:path";
|
||||
// update one heuristic. Production is unaffected: `output: "standalone"`
|
||||
// bakes resolved env into the build, and the marker file isn't shipped.
|
||||
loadMonorepoEnv();
|
||||
// Boot-time matched-pair guard for ADMIN_TOKEN / NEXT_PUBLIC_ADMIN_TOKEN.
|
||||
// When ADMIN_TOKEN is set on the workspace-server (server-side bearer
|
||||
// gate, wsauth_middleware.go ~L245), the canvas MUST send the matching
|
||||
// NEXT_PUBLIC_ADMIN_TOKEN as `Authorization: Bearer ...` on every API
|
||||
// call. If only one is set, every workspace API call 401s silently —
|
||||
// the canvas hydrates with empty data and the user sees a broken page
|
||||
// with no console hint about the auth-config mismatch.
|
||||
//
|
||||
// Pre-fix the matched-pair contract was descriptive only (a comment in
|
||||
// .env): future devs/agents could re-misconfigure with one of the two
|
||||
// unset and silently 401. Closes the post-PR-#174 self-review gap.
|
||||
//
|
||||
// Warn-only (not exit) — production canvas Docker images bake these
|
||||
// vars into the build at image-build time, and a missed pair there
|
||||
// would still emit the warning at runtime via the standalone server's
|
||||
// startup. Killing the process on misconfiguration would turn a
|
||||
// recoverable auth issue into a hard crashloop.
|
||||
checkAdminTokenPair();
|
||||
|
||||
const nextConfig: NextConfig = {
|
||||
output: "standalone",
|
||||
@ -75,43 +57,6 @@ function loadMonorepoEnv() {
|
||||
);
|
||||
}
|
||||
|
||||
// Boot-time matched-pair guard. Runs after .env has been loaded so the
|
||||
// check sees the post-load state. The two env vars must be set or
|
||||
// unset together; one-without-the-other is the silent-401 footgun.
|
||||
//
|
||||
// Treats empty string ("") as unset. An explicitly-empty `KEY=` in
|
||||
// .env counts as set-to-empty in `process.env`, but for auth purposes
|
||||
// an empty bearer token is equivalent to no token — so both
|
||||
// `ADMIN_TOKEN=` and an unset ADMIN_TOKEN are equivalent relative to
|
||||
// the matched-pair invariant.
|
||||
//
|
||||
// Returns void; side effect is the console.error warning. Kept as a
|
||||
// separate function (exported) so a future test can reset env, call
|
||||
// this, and assert on captured stderr.
|
||||
export function checkAdminTokenPair(): void {
|
||||
const serverSet = !!process.env.ADMIN_TOKEN;
|
||||
const clientSet = !!process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
if (serverSet === clientSet) return;
|
||||
// Distinct messages so the operator can tell which half is missing
|
||||
// — the fix is symmetric (set the other one) but the diagnostic
|
||||
// mentions which side is currently set so they don't have to grep.
|
||||
if (serverSet && !clientSet) {
|
||||
// eslint-disable-next-line no-console
|
||||
console.error(
|
||||
"[next.config] ADMIN_TOKEN is set but NEXT_PUBLIC_ADMIN_TOKEN is not — " +
|
||||
"canvas will 401 against workspace-server because the bearer header " +
|
||||
"is never attached. Set both to the same value, or unset both.",
|
||||
);
|
||||
} else {
|
||||
// eslint-disable-next-line no-console
|
||||
console.error(
|
||||
"[next.config] NEXT_PUBLIC_ADMIN_TOKEN is set but ADMIN_TOKEN is not — " +
|
||||
"workspace-server will reject the bearer because no AdminAuth gate " +
|
||||
"is configured. Set both to the same value, or unset both.",
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
function findMonorepoRoot(start: string): string | null {
|
||||
let dir = start;
|
||||
for (let i = 0; i < 6; i++) {
|
||||
|
||||
@ -41,7 +41,7 @@ export default function PricingPage() {
|
||||
<p className="mt-2 text-ink-mid">
|
||||
We publish the{" "}
|
||||
<a
|
||||
href="https://git.moleculesai.app/molecule-ai/molecule-monorepo"
|
||||
href="https://github.com/Molecule-AI/molecule-monorepo"
|
||||
className="text-accent underline hover:text-accent"
|
||||
>
|
||||
full source on GitHub
|
||||
|
||||
@ -1,10 +1,9 @@
|
||||
'use client';
|
||||
|
||||
import { useEffect, useMemo, useCallback, useRef } from "react";
|
||||
import { useEffect, useMemo, useCallback } from "react";
|
||||
import { type Edge, MarkerType } from "@xyflow/react";
|
||||
import { api } from "@/lib/api";
|
||||
import { useCanvasStore } from "@/store/canvas";
|
||||
import { useSocketEvent } from "@/hooks/useSocketEvent";
|
||||
import type { ActivityEntry } from "@/types/activity";
|
||||
|
||||
// ── Constants ─────────────────────────────────────────────────────────────────
|
||||
@ -12,6 +11,9 @@ import type { ActivityEntry } from "@/types/activity";
|
||||
/** 60-minute look-back window for delegation activity */
|
||||
export const A2A_WINDOW_MS = 60 * 60 * 1000;
|
||||
|
||||
/** Polling interval — refresh edges every 60 seconds */
|
||||
export const A2A_POLL_MS = 60 * 1_000;
|
||||
|
||||
/** Threshold for "hot" edges: < 5 minutes → animated + violet stroke */
|
||||
export const A2A_HOT_MS = 5 * 60 * 1_000;
|
||||
|
||||
@ -129,20 +131,6 @@ export function buildA2AEdges(
|
||||
* `a2aEdges`. Canvas.tsx merges these with topology edges and passes the
|
||||
* combined list to ReactFlow.
|
||||
*
|
||||
* Update shape (issue #61 Stage 2, replaces the 60s polling loop):
|
||||
* - On mount (when showA2AEdges): one HTTP fan-out per visible workspace
|
||||
* (delegation rows, 60-min window). Bootstraps the local row buffer.
|
||||
* - Steady state: subscribes to ACTIVITY_LOGGED via useSocketEvent.
|
||||
* Each delegation event from a visible workspace is appended to the
|
||||
* buffer; edges are re-derived via the existing buildA2AEdges helper.
|
||||
* - showA2AEdges toggle off: clears edges + buffer.
|
||||
* - Visible-ID-set change: re-bootstraps so a freshly-shown workspace
|
||||
* backfills its 60-min history (existing visibleIdsKey selector
|
||||
* behaviour preserved — that's the 2026-05-04 render-loop fix).
|
||||
*
|
||||
* No interval poll. The singleton ReconnectingSocket already owns
|
||||
* reconnect / backoff / health-check; useSocketEvent inherits those.
|
||||
*
|
||||
* Mount this inside CanvasInner (no ReactFlow hook dependency).
|
||||
*/
|
||||
export function A2ATopologyOverlay() {
|
||||
@ -169,9 +157,7 @@ export function A2ATopologyOverlay() {
|
||||
// the symptom of this re-render storm.
|
||||
//
|
||||
// The fix is purely the dependency-stability change here; the fetch
|
||||
// logic is unchanged. Post-#61 the polling-driven fetch is gone, but
|
||||
// the visibleIdsKey gate is still required so a peer-discovery write
|
||||
// doesn't trigger a wasteful re-bootstrap.
|
||||
// logic is unchanged.
|
||||
const visibleIdsKey = useCanvasStore((s) =>
|
||||
s.nodes
|
||||
.filter((n) => !n.hidden)
|
||||
@ -185,42 +171,16 @@ export function A2ATopologyOverlay() {
|
||||
[visibleIdsKey]
|
||||
);
|
||||
|
||||
// Local rolling buffer of delegation rows. Pruned by A2A_WINDOW_MS on
|
||||
// each rebuild so a long-lived session doesn't accumulate unbounded
|
||||
// history. The buffer's high-water mark is approximately:
|
||||
// visibleIds.length × bootstrap-fetch-limit (500) + WS arrivals
|
||||
// Real-world ceiling: ~3000 entries at the 60-min boundary, all of
|
||||
// which buildA2AEdges aggregates into at most N² edges.
|
||||
const bufferRef = useRef<ActivityEntry[]>([]);
|
||||
// visibleIdsRef gives the WS handler the latest visible-ID set without
|
||||
// re-subscribing on every render. The bus listener is registered
|
||||
// exactly once per mount; subscriber-side filtering reads from this ref.
|
||||
const visibleIdsRef = useRef(visibleIds);
|
||||
visibleIdsRef.current = visibleIds;
|
||||
|
||||
// Re-derive overlay edges from the current buffer + push to store.
|
||||
// Prunes by A2A_WINDOW_MS first so memory stays bounded across long
|
||||
// sessions and the aggregation cost stays O(window-size).
|
||||
const recomputeAndPush = useCallback(() => {
|
||||
const cutoff = Date.now() - A2A_WINDOW_MS;
|
||||
bufferRef.current = bufferRef.current.filter(
|
||||
(r) => new Date(r.created_at).getTime() > cutoff
|
||||
);
|
||||
setA2AEdges(buildA2AEdges(bufferRef.current));
|
||||
}, [setA2AEdges]);
|
||||
|
||||
// Bootstrap fan-out — one HTTP per visible workspace. Replaces the
|
||||
// 60s polling loop entirely. Race-aware: any WS arrivals that landed
|
||||
// in the buffer DURING the fetch (between the await and resume) are
|
||||
// preserved by id-dedup-with-fetched-first ordering.
|
||||
const bootstrap = useCallback(async () => {
|
||||
// Fetch delegation activity for all visible workspaces and rebuild overlay edges.
|
||||
const fetchAndUpdate = useCallback(async () => {
|
||||
if (visibleIds.length === 0) {
|
||||
bufferRef.current = [];
|
||||
setA2AEdges([]);
|
||||
return;
|
||||
}
|
||||
try {
|
||||
const fetchedRows = (
|
||||
// Fan-out — one request per visible workspace.
|
||||
// Per-request failures are swallowed so one broken workspace doesn't blank the overlay.
|
||||
const allRows = (
|
||||
await Promise.all(
|
||||
visibleIds.map((id) =>
|
||||
api
|
||||
@ -232,76 +192,24 @@ export function A2ATopologyOverlay() {
|
||||
)
|
||||
).flat();
|
||||
|
||||
// Merge: fetched rows first, then any in-flight WS arrivals that
|
||||
// accumulated during the await. Dedup by id so rows that appear
|
||||
// in both paths are not double-counted in the aggregation.
|
||||
const merged = [...fetchedRows, ...bufferRef.current];
|
||||
const seen = new Set<string>();
|
||||
bufferRef.current = merged.filter((r) => {
|
||||
if (seen.has(r.id)) return false;
|
||||
seen.add(r.id);
|
||||
return true;
|
||||
});
|
||||
recomputeAndPush();
|
||||
setA2AEdges(buildA2AEdges(allRows));
|
||||
} catch {
|
||||
// Overlay failure is non-critical — canvas remains functional
|
||||
}
|
||||
}, [visibleIds, setA2AEdges, recomputeAndPush]);
|
||||
}, [visibleIds, setA2AEdges]);
|
||||
|
||||
useEffect(() => {
|
||||
if (!showA2AEdges) {
|
||||
// Clear edges + buffer immediately when toggled off
|
||||
bufferRef.current = [];
|
||||
// Clear edges immediately when toggled off
|
||||
setA2AEdges([]);
|
||||
return;
|
||||
}
|
||||
void bootstrap();
|
||||
}, [showA2AEdges, bootstrap, setA2AEdges]);
|
||||
|
||||
// Live-update path. Filters server-side ACTIVITY_LOGGED events down
|
||||
// to delegation initiations from visible workspaces and appends each
|
||||
// into the rolling buffer, re-deriving edges via buildA2AEdges.
|
||||
//
|
||||
// Only `method === "delegate"` rows count — the same filter
|
||||
// buildA2AEdges applies — so delegate_result rows arriving over the
|
||||
// wire don't double-count.
|
||||
useSocketEvent((msg) => {
|
||||
if (!showA2AEdges) return;
|
||||
if (msg.event !== "ACTIVITY_LOGGED") return;
|
||||
|
||||
const p = (msg.payload || {}) as Record<string, unknown>;
|
||||
if (p.activity_type !== "delegation") return;
|
||||
if (p.method !== "delegate") return;
|
||||
|
||||
const wsId = msg.workspace_id;
|
||||
if (!visibleIdsRef.current.includes(wsId)) return;
|
||||
|
||||
// Synthesise an ActivityEntry from the WS payload so buildA2AEdges
|
||||
// (which the bootstrap path also feeds) handles it identically.
|
||||
const entry: ActivityEntry = {
|
||||
id:
|
||||
(p.id as string) ||
|
||||
`ws-push-${msg.timestamp || Date.now()}-${wsId}`,
|
||||
workspace_id: wsId,
|
||||
activity_type: "delegation",
|
||||
source_id: (p.source_id as string | null) ?? null,
|
||||
target_id: (p.target_id as string | null) ?? null,
|
||||
method: "delegate",
|
||||
summary: (p.summary as string | null) ?? null,
|
||||
request_body: null,
|
||||
response_body: null,
|
||||
duration_ms: (p.duration_ms as number | null) ?? null,
|
||||
status: (p.status as string) || "ok",
|
||||
error_detail: null,
|
||||
created_at:
|
||||
(p.created_at as string) ||
|
||||
msg.timestamp ||
|
||||
new Date().toISOString(),
|
||||
};
|
||||
|
||||
bufferRef.current = [...bufferRef.current, entry];
|
||||
recomputeAndPush();
|
||||
});
|
||||
// Initial fetch, then poll every 60 s
|
||||
void fetchAndUpdate();
|
||||
const timer = setInterval(() => void fetchAndUpdate(), A2A_POLL_MS);
|
||||
return () => clearInterval(timer);
|
||||
}, [showA2AEdges, fetchAndUpdate, setA2AEdges]);
|
||||
|
||||
// Pure side-effect — renders nothing
|
||||
return null;
|
||||
|
||||
@ -3,7 +3,6 @@
|
||||
import { useState, useEffect, useCallback, useRef } from "react";
|
||||
import { useCanvasStore } from "@/store/canvas";
|
||||
import { api } from "@/lib/api";
|
||||
import { useSocketEvent } from "@/hooks/useSocketEvent";
|
||||
import { COMM_TYPE_LABELS } from "@/lib/design-tokens";
|
||||
|
||||
interface Communication {
|
||||
@ -19,71 +18,32 @@ interface Communication {
|
||||
durationMs: number | null;
|
||||
}
|
||||
|
||||
/** Workspace-server `ACTIVITY_LOGGED` payload shape. Pulled out so the
|
||||
* WS handler below has a typed view of the same fields the HTTP
|
||||
* bootstrap consumes — drift between the two paths is a class of bug
|
||||
* AgentCommsPanel hit historically. */
|
||||
interface ActivityLoggedPayload {
|
||||
id?: string;
|
||||
activity_type?: string;
|
||||
source_id?: string | null;
|
||||
target_id?: string | null;
|
||||
workspace_id?: string;
|
||||
summary?: string | null;
|
||||
status?: string;
|
||||
duration_ms?: number | null;
|
||||
created_at?: string;
|
||||
}
|
||||
|
||||
/** Fan-out cap for the bootstrap HTTP fetch on mount / on visibility
|
||||
* re-open. Kept at 3 (carried over from the 2026-05-04 fix) so a
|
||||
* freshly-mounted overlay on a 15-workspace tenant only spends 3
|
||||
* round-trips bootstrapping. Live updates after that arrive via the
|
||||
* WS subscription below — no polling, no fan-out to maintain. */
|
||||
const BOOTSTRAP_FAN_OUT_CAP = 3;
|
||||
|
||||
/** Cap on the rendered list. Bootstrap + every WS push prepends, the
|
||||
* list is sliced to this size after each update. Mirrors the prior
|
||||
* polling-loop behaviour. */
|
||||
const COMMS_RENDER_CAP = 20;
|
||||
|
||||
/**
|
||||
* Overlay showing recent A2A communications between workspaces.
|
||||
*
|
||||
* Update shape (issue #61 Stage 1, replaces the 30s polling loop):
|
||||
* - On mount (when visible): one HTTP bootstrap per online workspace,
|
||||
* capped at BOOTSTRAP_FAN_OUT_CAP. Yields the initial recent-comms
|
||||
* window without waiting for live events.
|
||||
* - Steady state: subscribes to ACTIVITY_LOGGED via useSocketEvent.
|
||||
* Each event with a matching activity_type from a visible online
|
||||
* workspace gets synthesised into a Communication and prepended.
|
||||
* - Visibility re-open: re-bootstraps so the user sees the freshest
|
||||
* window even if WS was idle while collapsed.
|
||||
*
|
||||
* No interval poll. The singleton ReconnectingSocket in `store/socket.ts`
|
||||
* already owns reconnect/backoff/health-check, and `useSocketEvent`
|
||||
* inherits those guarantees. If WS is genuinely unhealthy, the overlay
|
||||
* shows the bootstrap snapshot until the next visibility re-open or
|
||||
* the next WS reconnect (which fires its own rehydrate burst).
|
||||
* Renders as a floating log panel that auto-updates.
|
||||
*/
|
||||
export function CommunicationOverlay() {
|
||||
const [comms, setComms] = useState<Communication[]>([]);
|
||||
const [visible, setVisible] = useState(true);
|
||||
const selectedNodeId = useCanvasStore((s) => s.selectedNodeId);
|
||||
const nodes = useCanvasStore((s) => s.nodes);
|
||||
// nodesRef gives the WS handler current node-name resolution without
|
||||
// re-subscribing on every node-list change. The bus listener is
|
||||
// registered exactly once per mount; subscriber-side filtering reads
|
||||
// the latest value via this ref.
|
||||
const nodesRef = useRef(nodes);
|
||||
nodesRef.current = nodes;
|
||||
|
||||
const bootstrapComms = useCallback(async () => {
|
||||
const fetchComms = useCallback(async () => {
|
||||
try {
|
||||
// Fan-out cap: each polled workspace = 1 round-trip. The platform
|
||||
// rate limits at 600 req/min/IP; combined with heartbeats + other
|
||||
// canvas polling, every workspace polled here costs ~6 req/min
|
||||
// (1 every 30s × 1 per workspace). Capping at 3 keeps this
|
||||
// overlay's footprint at 18 req/min worst case — well under
|
||||
// budget even with 8+ workspaces visible. Caught 2026-05-04 when
|
||||
// a user with 8+ workspaces (Design Director + 6 sub-agents +
|
||||
// 3 standalones) saw sustained 429s in canvas console.
|
||||
const onlineNodes = nodesRef.current.filter((n) => n.data.status === "online");
|
||||
const allComms: Communication[] = [];
|
||||
|
||||
for (const node of onlineNodes.slice(0, BOOTSTRAP_FAN_OUT_CAP)) {
|
||||
for (const node of onlineNodes.slice(0, 3)) {
|
||||
try {
|
||||
const activities = await api.get<Array<{
|
||||
id: string;
|
||||
@ -99,8 +59,8 @@ export function CommunicationOverlay() {
|
||||
|
||||
for (const a of activities) {
|
||||
if (a.activity_type === "a2a_send" || a.activity_type === "a2a_receive") {
|
||||
const sourceNode = nodesRef.current.find((n) => n.id === (a.source_id || a.workspace_id));
|
||||
const targetNode = nodesRef.current.find((n) => n.id === (a.target_id || ""));
|
||||
const sourceNode = nodes.find((n) => n.id === (a.source_id || a.workspace_id));
|
||||
const targetNode = nodes.find((n) => n.id === (a.target_id || ""));
|
||||
allComms.push({
|
||||
id: a.id,
|
||||
sourceId: a.source_id || a.workspace_id,
|
||||
@ -116,12 +76,11 @@ export function CommunicationOverlay() {
|
||||
}
|
||||
}
|
||||
} catch {
|
||||
// Per-workspace failures must not blank the panel — the same
|
||||
// robustness the polling version had.
|
||||
// Skip workspaces that fail
|
||||
}
|
||||
}
|
||||
|
||||
// Newest-first with id-dedup, capped at COMMS_RENDER_CAP.
|
||||
// Sort by timestamp, newest first, dedupe
|
||||
const seen = new Set<string>();
|
||||
const sorted = allComms
|
||||
.sort((a, b) => b.timestamp.localeCompare(a.timestamp))
|
||||
@ -130,78 +89,29 @@ export function CommunicationOverlay() {
|
||||
seen.add(c.id);
|
||||
return true;
|
||||
})
|
||||
.slice(0, COMMS_RENDER_CAP);
|
||||
.slice(0, 20);
|
||||
|
||||
setComms(sorted);
|
||||
} catch {
|
||||
// Bootstrap failure is non-blocking — the WS subscription below
|
||||
// will populate the panel as live events arrive.
|
||||
// Silently handle API errors
|
||||
}
|
||||
}, []);
|
||||
|
||||
// Bootstrap once on mount + every time the user re-opens after a
|
||||
// collapse. Closed-panel state intentionally drops live updates so
|
||||
// the panel doesn't churn invisible state — the next open reloads.
|
||||
useEffect(() => {
|
||||
// Gate polling on visibility — when the user collapses the overlay
|
||||
// the data isn't being read, so the per-workspace fan-out becomes
|
||||
// pure rate-limit overhead. Pre-fix this overlay polled regardless
|
||||
// of whether the panel was shown, costing ~36 req/min from a
|
||||
// hidden surface.
|
||||
if (!visible) return;
|
||||
bootstrapComms();
|
||||
}, [bootstrapComms, visible]);
|
||||
|
||||
// Live-update path. Filters server-side ACTIVITY_LOGGED events down
|
||||
// to the comm-overlay-relevant subset and prepends each into the
|
||||
// rendered list with the same dedup the bootstrap path uses.
|
||||
//
|
||||
// Scope guard: ignore events for workspaces not in the visible online
|
||||
// set, so a user collapsing one workspace doesn't see its comms
|
||||
// continue to scroll in. Same shape the bootstrap path applies.
|
||||
useSocketEvent((msg) => {
|
||||
if (!visible) return;
|
||||
if (msg.event !== "ACTIVITY_LOGGED") return;
|
||||
|
||||
const p = (msg.payload || {}) as ActivityLoggedPayload;
|
||||
const type = p.activity_type;
|
||||
if (type !== "a2a_send" && type !== "a2a_receive" && type !== "task_update") return;
|
||||
|
||||
const wsId = msg.workspace_id;
|
||||
const onlineSet = new Set(
|
||||
nodesRef.current.filter((n) => n.data.status === "online").map((n) => n.id),
|
||||
);
|
||||
if (!onlineSet.has(wsId)) return;
|
||||
|
||||
const sourceId = p.source_id || wsId;
|
||||
const targetId = p.target_id || "";
|
||||
const sourceNode = nodesRef.current.find((n) => n.id === sourceId);
|
||||
const targetNode = nodesRef.current.find((n) => n.id === targetId);
|
||||
|
||||
const incoming: Communication = {
|
||||
id: p.id || `${msg.timestamp || Date.now()}:${sourceId}:${targetId}`,
|
||||
sourceId,
|
||||
targetId,
|
||||
sourceName: sourceNode?.data.name || "Unknown",
|
||||
targetName: targetNode?.data.name || "Unknown",
|
||||
type: type as Communication["type"],
|
||||
summary: p.summary || "",
|
||||
status: p.status || "ok",
|
||||
timestamp: p.created_at || msg.timestamp || new Date().toISOString(),
|
||||
durationMs: p.duration_ms ?? null,
|
||||
};
|
||||
|
||||
setComms((prev) => {
|
||||
// Prepend, dedup by id, re-cap. Functional setState is necessary
|
||||
// because two ACTIVITY_LOGGED events arriving in the same React
|
||||
// batch would otherwise read a stale `comms` from the closure.
|
||||
const seen = new Set<string>();
|
||||
const merged = [incoming, ...prev]
|
||||
.sort((a, b) => b.timestamp.localeCompare(a.timestamp))
|
||||
.filter((c) => {
|
||||
if (seen.has(c.id)) return false;
|
||||
seen.add(c.id);
|
||||
return true;
|
||||
})
|
||||
.slice(0, COMMS_RENDER_CAP);
|
||||
return merged;
|
||||
});
|
||||
});
|
||||
fetchComms();
|
||||
// 30s cadence (was 10s). At 3-workspace fan-out that's 6 req/min
|
||||
// worst case from this overlay. Combined with heartbeats (~30/min)
|
||||
// and other canvas polling, leaves ample headroom under the 600/
|
||||
// min/IP server-side rate limit even at 8+ workspace tenants.
|
||||
const interval = setInterval(fetchComms, 30000);
|
||||
return () => clearInterval(interval);
|
||||
}, [fetchComms, visible]);
|
||||
|
||||
if (!visible || comms.length === 0) {
|
||||
return (
|
||||
|
||||
@ -41,10 +41,6 @@ vi.mock("@/store/canvas", () => ({
|
||||
// ── Imports (after mocks) ─────────────────────────────────────────────────────
|
||||
|
||||
import { api } from "@/lib/api";
|
||||
import {
|
||||
emitSocketEvent,
|
||||
_resetSocketEventListenersForTests,
|
||||
} from "@/store/socket-events";
|
||||
import {
|
||||
buildA2AEdges,
|
||||
formatA2ARelativeTime,
|
||||
@ -346,151 +342,6 @@ describe("A2ATopologyOverlay component", () => {
|
||||
expect(mockGet.mock.calls.length).toBe(callsAfterMount);
|
||||
});
|
||||
|
||||
// ── #61 Stage 2: ACTIVITY_LOGGED subscription tests ────────────────────────
|
||||
//
|
||||
// Pin the post-#61 behaviour: WS push for delegation contributes to
|
||||
// the overlay's edge buffer with NO additional HTTP fetch. Same shape
|
||||
// as Stage 1 (CommunicationOverlay).
|
||||
|
||||
describe("#61 stage 2 — ACTIVITY_LOGGED subscription", () => {
|
||||
beforeEach(() => {
|
||||
_resetSocketEventListenersForTests();
|
||||
});
|
||||
afterEach(() => {
|
||||
_resetSocketEventListenersForTests();
|
||||
});
|
||||
|
||||
function emitDelegation(overrides: {
|
||||
workspaceId?: string;
|
||||
sourceId?: string;
|
||||
targetId?: string;
|
||||
method?: string;
|
||||
activityType?: string;
|
||||
} = {}) {
|
||||
// Use Date.now() (real time, fake-timer-frozen) rather than the
|
||||
// hardcoded NOW constant — buildA2AEdges prunes by Date.now() -
|
||||
// A2A_WINDOW_MS, so a row dated against the wrong epoch silently
|
||||
// falls outside the window and the test fails for a confusing
|
||||
// reason ("edges array empty" vs "filter dropped my row").
|
||||
const realNow = Date.now();
|
||||
emitSocketEvent({
|
||||
event: "ACTIVITY_LOGGED",
|
||||
workspace_id: overrides.workspaceId ?? "ws-a",
|
||||
timestamp: new Date(realNow).toISOString(),
|
||||
payload: {
|
||||
id: `act-${Math.random().toString(36).slice(2)}`,
|
||||
activity_type: overrides.activityType ?? "delegation",
|
||||
method: overrides.method ?? "delegate",
|
||||
source_id: overrides.sourceId ?? "ws-a",
|
||||
target_id: overrides.targetId ?? "ws-b",
|
||||
status: "ok",
|
||||
created_at: new Date(realNow - 30_000).toISOString(),
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
it("does NOT poll on a 60s interval after bootstrap (post-#61)", async () => {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
mockGet.mockResolvedValue([] as any);
|
||||
render(<A2ATopologyOverlay />);
|
||||
await act(async () => { await Promise.resolve(); });
|
||||
const callsAfterBootstrap = mockGet.mock.calls.length;
|
||||
expect(callsAfterBootstrap).toBe(2); // ws-a + ws-b
|
||||
|
||||
// Pre-#61: a 60s clock tick would fire a fresh fan-out (2 more
|
||||
// calls). Post-#61: no interval, no extra calls.
|
||||
await act(async () => {
|
||||
vi.advanceTimersByTime(120_000);
|
||||
});
|
||||
expect(mockGet.mock.calls.length).toBe(callsAfterBootstrap);
|
||||
});
|
||||
|
||||
it("WS push for a delegation event from a visible workspace updates edges with NO HTTP call", async () => {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
mockGet.mockResolvedValue([] as any);
|
||||
render(<A2ATopologyOverlay />);
|
||||
await act(async () => { await Promise.resolve(); await Promise.resolve(); });
|
||||
mockGet.mockClear();
|
||||
mockStoreState.setA2AEdges.mockClear();
|
||||
|
||||
await act(async () => {
|
||||
emitDelegation({ sourceId: "ws-a", targetId: "ws-b" });
|
||||
});
|
||||
|
||||
// Edges-set called with at least one a2a edge for the new push.
|
||||
const calls = mockStoreState.setA2AEdges.mock.calls;
|
||||
expect(calls.length).toBeGreaterThanOrEqual(1);
|
||||
const lastCall = calls[calls.length - 1][0] as Array<{ id: string }>;
|
||||
expect(lastCall.some((e) => e.id === "a2a-ws-a-ws-b")).toBe(true);
|
||||
|
||||
// Critical: no HTTP fetch fired during the WS path.
|
||||
expect(mockGet).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("WS push for a non-delegation activity_type is ignored", async () => {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
mockGet.mockResolvedValue([] as any);
|
||||
render(<A2ATopologyOverlay />);
|
||||
await act(async () => { await Promise.resolve(); });
|
||||
mockStoreState.setA2AEdges.mockClear();
|
||||
|
||||
await act(async () => {
|
||||
emitDelegation({ activityType: "a2a_send" });
|
||||
});
|
||||
|
||||
// setA2AEdges must not be called by the WS handler — the only
|
||||
// setA2AEdges calls in this test came from the initial bootstrap.
|
||||
expect(mockStoreState.setA2AEdges).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("WS push for a delegate_result row is ignored (mirrors buildA2AEdges filter)", async () => {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
mockGet.mockResolvedValue([] as any);
|
||||
render(<A2ATopologyOverlay />);
|
||||
await act(async () => { await Promise.resolve(); });
|
||||
mockStoreState.setA2AEdges.mockClear();
|
||||
|
||||
await act(async () => {
|
||||
emitDelegation({ method: "delegate_result" });
|
||||
});
|
||||
|
||||
// delegate_result rows do not contribute to the edge count — they
|
||||
// are completion signals, not initiations.
|
||||
expect(mockStoreState.setA2AEdges).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("WS push from a hidden workspace is ignored", async () => {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
mockGet.mockResolvedValue([] as any);
|
||||
render(<A2ATopologyOverlay />);
|
||||
await act(async () => { await Promise.resolve(); });
|
||||
mockStoreState.setA2AEdges.mockClear();
|
||||
|
||||
await act(async () => {
|
||||
emitDelegation({ workspaceId: "ws-hidden" });
|
||||
});
|
||||
|
||||
expect(mockStoreState.setA2AEdges).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("WS push while showA2AEdges is false is ignored", async () => {
|
||||
mockStoreState.showA2AEdges = false;
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
mockGet.mockResolvedValue([] as any);
|
||||
render(<A2ATopologyOverlay />);
|
||||
// The mount path with showA2AEdges=false calls setA2AEdges([])
|
||||
// once — clear that to isolate the WS path.
|
||||
mockStoreState.setA2AEdges.mockClear();
|
||||
|
||||
await act(async () => {
|
||||
emitDelegation();
|
||||
});
|
||||
|
||||
expect(mockStoreState.setA2AEdges).not.toHaveBeenCalled();
|
||||
expect(mockGet).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
|
||||
it("re-fetches when the visible ID set actually changes", async () => {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
mockGet.mockResolvedValue([] as any);
|
||||
|
||||
@ -36,10 +36,6 @@ vi.mock("@/hooks/useWorkspaceName", () => ({
|
||||
useWorkspaceName: () => () => "Test WS",
|
||||
}));
|
||||
|
||||
import {
|
||||
emitSocketEvent,
|
||||
_resetSocketEventListenersForTests,
|
||||
} from "@/store/socket-events";
|
||||
import { ActivityTab } from "../tabs/ActivityTab";
|
||||
|
||||
// ── Fixtures ──────────────────────────────────────────────────────────────────
|
||||
@ -362,191 +358,6 @@ describe("ActivityTab — refresh button", () => {
|
||||
});
|
||||
});
|
||||
|
||||
// ── Suite 6.5: ACTIVITY_LOGGED subscription (#61 stage 3) ─────────────────────
|
||||
//
|
||||
// Pin the post-#61 behaviour: WS push extends the rendered list with NO
|
||||
// additional HTTP fetch. The 5s polling loop is gone; live updates
|
||||
// arrive over the WebSocket bus.
|
||||
|
||||
describe("ActivityTab — #61 stage 3: ACTIVITY_LOGGED subscription", () => {
|
||||
beforeEach(() => {
|
||||
vi.clearAllMocks();
|
||||
mockGet.mockResolvedValue([]);
|
||||
_resetSocketEventListenersForTests();
|
||||
});
|
||||
afterEach(() => {
|
||||
cleanup();
|
||||
_resetSocketEventListenersForTests();
|
||||
});
|
||||
|
||||
function emitActivity(overrides: {
|
||||
workspaceId?: string;
|
||||
activityType?: string;
|
||||
summary?: string;
|
||||
id?: string;
|
||||
} = {}) {
|
||||
const realNow = Date.now();
|
||||
emitSocketEvent({
|
||||
event: "ACTIVITY_LOGGED",
|
||||
workspace_id: overrides.workspaceId ?? "ws-1",
|
||||
timestamp: new Date(realNow).toISOString(),
|
||||
payload: {
|
||||
id: overrides.id ?? `act-${Math.random().toString(36).slice(2)}`,
|
||||
activity_type: overrides.activityType ?? "agent_log",
|
||||
source_id: null,
|
||||
target_id: null,
|
||||
method: null,
|
||||
summary: overrides.summary ?? "live-pushed",
|
||||
status: "ok",
|
||||
created_at: new Date(realNow - 5_000).toISOString(),
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
it("WS push for matching workspace prepends to the list with NO HTTP call", async () => {
|
||||
render(<ActivityTab workspaceId="ws-1" />);
|
||||
await waitFor(() => {
|
||||
expect(screen.getByText(/0 activities|no activity/i)).toBeTruthy();
|
||||
});
|
||||
mockGet.mockClear();
|
||||
|
||||
await act(async () => {
|
||||
emitActivity({ summary: "live-row-from-bus" });
|
||||
});
|
||||
|
||||
await waitFor(() => {
|
||||
expect(screen.getByText(/live-row-from-bus/)).toBeTruthy();
|
||||
});
|
||||
expect(mockGet).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("WS push for a different workspace is ignored", async () => {
|
||||
render(<ActivityTab workspaceId="ws-1" />);
|
||||
await waitFor(() => screen.getByText(/no activity/i));
|
||||
|
||||
await act(async () => {
|
||||
emitActivity({
|
||||
workspaceId: "ws-other",
|
||||
summary: "should-not-render-other-ws",
|
||||
});
|
||||
});
|
||||
|
||||
expect(screen.queryByText(/should-not-render-other-ws/)).toBeNull();
|
||||
});
|
||||
|
||||
it("WS push respects the active filter — non-matching activity_type is ignored", async () => {
|
||||
render(<ActivityTab workspaceId="ws-1" />);
|
||||
await waitFor(() => screen.getByText(/no activity/i));
|
||||
|
||||
// Apply "Tasks" filter.
|
||||
clickButton(/tasks/i);
|
||||
await waitFor(() => {
|
||||
expect(
|
||||
screen.getByRole("button", { name: /tasks/i }).getAttribute("aria-pressed"),
|
||||
).toBe("true");
|
||||
});
|
||||
|
||||
// Push an a2a_send (does NOT match task_update filter).
|
||||
await act(async () => {
|
||||
emitActivity({
|
||||
activityType: "a2a_send",
|
||||
summary: "should-not-render-filter-mismatch",
|
||||
});
|
||||
});
|
||||
|
||||
expect(
|
||||
screen.queryByText(/should-not-render-filter-mismatch/),
|
||||
).toBeNull();
|
||||
});
|
||||
|
||||
it("WS push respects the active filter — matching activity_type is rendered", async () => {
|
||||
render(<ActivityTab workspaceId="ws-1" />);
|
||||
await waitFor(() => screen.getByText(/no activity/i));
|
||||
|
||||
clickButton(/tasks/i);
|
||||
await waitFor(() => {
|
||||
expect(
|
||||
screen.getByRole("button", { name: /tasks/i }).getAttribute("aria-pressed"),
|
||||
).toBe("true");
|
||||
});
|
||||
|
||||
await act(async () => {
|
||||
emitActivity({
|
||||
activityType: "task_update",
|
||||
summary: "task-filter-match",
|
||||
});
|
||||
});
|
||||
|
||||
await waitFor(() => {
|
||||
expect(screen.getByText(/task-filter-match/)).toBeTruthy();
|
||||
});
|
||||
});
|
||||
|
||||
it("WS push while autoRefresh is paused is ignored", async () => {
|
||||
render(<ActivityTab workspaceId="ws-1" />);
|
||||
await waitFor(() => screen.getByText(/no activity/i));
|
||||
|
||||
// Toggle Live → Paused.
|
||||
clickButton(/live/i);
|
||||
await waitFor(() => {
|
||||
expect(screen.getByText(/Paused/)).toBeTruthy();
|
||||
});
|
||||
|
||||
await act(async () => {
|
||||
emitActivity({ summary: "should-not-render-paused" });
|
||||
});
|
||||
|
||||
expect(screen.queryByText(/should-not-render-paused/)).toBeNull();
|
||||
});
|
||||
|
||||
it("WS push for a row already in the list is deduped (no double-render)", async () => {
|
||||
// Bootstrap with one row — same id as the WS push to trigger dedup.
|
||||
mockGet.mockResolvedValueOnce([
|
||||
makeEntry({ id: "shared-id", summary: "bootstrap-summary" }),
|
||||
]);
|
||||
render(<ActivityTab workspaceId="ws-1" />);
|
||||
await waitFor(() => {
|
||||
expect(screen.getByText(/bootstrap-summary/)).toBeTruthy();
|
||||
});
|
||||
mockGet.mockClear();
|
||||
|
||||
// Push a row with the SAME id but a different summary — must not
|
||||
// render the new summary; original row stays.
|
||||
await act(async () => {
|
||||
emitActivity({
|
||||
id: "shared-id",
|
||||
summary: "should-not-replace-existing",
|
||||
});
|
||||
});
|
||||
|
||||
expect(screen.queryByText(/should-not-replace-existing/)).toBeNull();
|
||||
// Also verify count didn't grow.
|
||||
expect(screen.getByText(/1 activities/)).toBeTruthy();
|
||||
});
|
||||
|
||||
it("does NOT poll on a 5s interval after mount (post-#61)", async () => {
|
||||
vi.useFakeTimers();
|
||||
try {
|
||||
render(<ActivityTab workspaceId="ws-1" />);
|
||||
// Drain the mount-time bootstrap promise.
|
||||
await act(async () => {
|
||||
await Promise.resolve();
|
||||
await Promise.resolve();
|
||||
});
|
||||
const callsAfterBootstrap = mockGet.mock.calls.length;
|
||||
expect(callsAfterBootstrap).toBeGreaterThanOrEqual(1);
|
||||
|
||||
// Pre-#61: a 30s clock advance fires 6 more polls. Post-#61: 0.
|
||||
await act(async () => {
|
||||
vi.advanceTimersByTime(30_000);
|
||||
});
|
||||
expect(mockGet.mock.calls.length).toBe(callsAfterBootstrap);
|
||||
} finally {
|
||||
vi.useRealTimers();
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
// ── Suite 7: Activity count ───────────────────────────────────────────────────
|
||||
|
||||
describe("ActivityTab — activity count", () => {
|
||||
|
||||
@ -1,28 +1,18 @@
|
||||
// @vitest-environment jsdom
|
||||
/**
|
||||
* CommunicationOverlay tests — pin both the 2026-05-04 fan-out cap fix
|
||||
* AND the 2026-05-07 polling → ACTIVITY_LOGGED-subscriber refactor
|
||||
* (issue #61 stage 1).
|
||||
* CommunicationOverlay tests — pin the rate-limit fix shipped 2026-05-04.
|
||||
*
|
||||
* The overlay used to poll /workspaces/:id/activity?limit=5 on a 30s
|
||||
* interval per online workspace (capped at 3). Post-#61: it bootstraps
|
||||
* once on mount via the same HTTP path (cap of 3 retained), then
|
||||
* subscribes to ACTIVITY_LOGGED via the global socket bus for live
|
||||
* updates. No interval poll.
|
||||
* The overlay polls /workspaces/:id/activity?limit=5 for each online
|
||||
* workspace. Pre-fix it (a) polled regardless of visibility and (b)
|
||||
* fanned out to 6 workspaces every 10s. With 8+ workspaces a user
|
||||
* triggered sustained 429s (server-side rate limit is 600 req/min/IP).
|
||||
*
|
||||
* These tests pin:
|
||||
* 1. Bootstrap fan-out cap of 3 — even with 6 online nodes, only 3
|
||||
* HTTP fetches on mount.
|
||||
* 2. Visibility gate — when collapsed, no HTTP fetches; re-open
|
||||
* re-bootstraps.
|
||||
* 3. NO interval polling — advancing the clock past 30s does not fire
|
||||
* additional HTTP calls.
|
||||
* 4. WS push extends the rendered list without firing any HTTP call.
|
||||
* 5. WS push for an offline workspace is ignored.
|
||||
* 6. WS push for a non-comm activity_type is ignored.
|
||||
* 1. Fan-out cap of 3 — even with 6 online nodes, only 3 fetches
|
||||
* 2. Visibility gate — when collapsed, no polling
|
||||
*
|
||||
* If a future refactor regresses any of these, CI fails before the
|
||||
* regression hits a paying tenant.
|
||||
* If a future refactor pushes either dial back up, CI fails before
|
||||
* the regression hits a paying tenant.
|
||||
*/
|
||||
import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
|
||||
import { render, cleanup, act, fireEvent } from "@testing-library/react";
|
||||
@ -33,7 +23,7 @@ vi.mock("@/lib/api", () => ({
|
||||
api: { get: vi.fn() },
|
||||
}));
|
||||
|
||||
// Six online nodes — enough to verify the bootstrap cap of 3.
|
||||
// Six online nodes — enough to verify the cap of 3.
|
||||
const mockStoreState = {
|
||||
selectedNodeId: null as string | null,
|
||||
nodes: [
|
||||
@ -66,10 +56,6 @@ vi.mock("@/lib/design-tokens", () => ({
|
||||
// ── Imports (after mocks) ─────────────────────────────────────────────────────
|
||||
|
||||
import { api } from "@/lib/api";
|
||||
import {
|
||||
emitSocketEvent,
|
||||
_resetSocketEventListenersForTests,
|
||||
} from "@/store/socket-events";
|
||||
import { CommunicationOverlay } from "../CommunicationOverlay";
|
||||
|
||||
const mockGet = vi.mocked(api.get);
|
||||
@ -80,34 +66,30 @@ beforeEach(() => {
|
||||
vi.useFakeTimers();
|
||||
mockGet.mockReset();
|
||||
mockGet.mockResolvedValue([]);
|
||||
// Drop any subscribers the previous test left on the singleton bus —
|
||||
// each render adds one via useSocketEvent.
|
||||
_resetSocketEventListenersForTests();
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
cleanup();
|
||||
vi.useRealTimers();
|
||||
_resetSocketEventListenersForTests();
|
||||
});
|
||||
|
||||
// ── Tests ─────────────────────────────────────────────────────────────────────
|
||||
|
||||
describe("CommunicationOverlay — bootstrap fan-out cap", () => {
|
||||
it("bootstraps at most 3 of 6 online workspaces (rate-limit floor preserved post-#61)", async () => {
|
||||
describe("CommunicationOverlay — fan-out cap", () => {
|
||||
it("polls at most 3 of 6 online workspaces (rate-limit floor)", async () => {
|
||||
await act(async () => {
|
||||
render(<CommunicationOverlay />);
|
||||
});
|
||||
// Mount fires the bootstrap synchronously — pre-#61 this was the
|
||||
// first poll cycle; post-#61 it's the only HTTP fetch (live updates
|
||||
// arrive via WS push). 6 nodes → 3 fetches.
|
||||
// Mount fires the first poll synchronously (no interval tick yet).
|
||||
// Pre-fix: 6 calls. Post-fix: 3.
|
||||
expect(mockGet).toHaveBeenCalledTimes(3);
|
||||
// Verify the calls are for the FIRST 3 online nodes (slice order).
|
||||
expect(mockGet).toHaveBeenCalledWith("/workspaces/ws-1/activity?limit=5");
|
||||
expect(mockGet).toHaveBeenCalledWith("/workspaces/ws-2/activity?limit=5");
|
||||
expect(mockGet).toHaveBeenCalledWith("/workspaces/ws-3/activity?limit=5");
|
||||
});
|
||||
|
||||
it("never bootstraps offline workspaces", async () => {
|
||||
it("never polls offline workspaces", async () => {
|
||||
await act(async () => {
|
||||
render(<CommunicationOverlay />);
|
||||
});
|
||||
@ -117,39 +99,40 @@ describe("CommunicationOverlay — bootstrap fan-out cap", () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe("CommunicationOverlay — no interval polling (post-#61)", () => {
|
||||
// The pre-#61 implementation re-fetched every 30s per workspace.
|
||||
// Post-#61 the only HTTP path is the bootstrap on mount + on
|
||||
// visibility-toggle. This test pins the absence of any interval
|
||||
// poll: a 60s clock advance must not produce a second round of
|
||||
// fetches.
|
||||
it("does NOT poll on a 30s interval after bootstrap", async () => {
|
||||
describe("CommunicationOverlay — cadence", () => {
|
||||
it("uses 30s interval cadence (was 10s pre-fix)", async () => {
|
||||
await act(async () => {
|
||||
render(<CommunicationOverlay />);
|
||||
});
|
||||
expect(mockGet).toHaveBeenCalledTimes(3); // initial bootstrap
|
||||
mockGet.mockClear();
|
||||
expect(mockGet).toHaveBeenCalledTimes(3); // initial mount poll
|
||||
|
||||
// Advance 60s — well past any plausible cadence the prior version
|
||||
// could have used.
|
||||
// Advance 10s — pre-fix this would fire another poll. Post-fix: silent.
|
||||
await act(async () => {
|
||||
vi.advanceTimersByTime(60_000);
|
||||
vi.advanceTimersByTime(10_000);
|
||||
});
|
||||
expect(mockGet).not.toHaveBeenCalled();
|
||||
expect(mockGet).toHaveBeenCalledTimes(3);
|
||||
|
||||
// Advance to 30s — interval fires.
|
||||
await act(async () => {
|
||||
vi.advanceTimersByTime(20_000);
|
||||
});
|
||||
expect(mockGet).toHaveBeenCalledTimes(6); // +3 from second tick
|
||||
});
|
||||
});
|
||||
|
||||
describe("CommunicationOverlay — visibility gate", () => {
|
||||
// The visibility gate now does two things post-#61:
|
||||
// - while closed, the WS handler short-circuits (no setComms churn)
|
||||
// - re-opening triggers a fresh bootstrap so the list reflects
|
||||
// anything that happened while the panel was collapsed
|
||||
// The visibility gate is the dial that drops collapsed-panel polling
|
||||
// to ZERO. The cadence test above can't catch its removal — if a
|
||||
// refactor dropped `if (!visible) return`, the cadence test would
|
||||
// still pass because the effect would still fire every 30s.
|
||||
//
|
||||
// Direct probe: render with comms-returning mock so the panel
|
||||
// actually renders (close button only exists in the expanded panel,
|
||||
// not the collapsed button-state). Click close, advance the clock,
|
||||
// assert no further fetches.
|
||||
it("stops fetching while collapsed and re-bootstraps on re-open", async () => {
|
||||
it("stops polling after the user collapses the panel", async () => {
|
||||
// Mock returns one a2a_send so comms.length > 0 → panel renders →
|
||||
// close button accessible.
|
||||
mockGet.mockResolvedValue([
|
||||
{
|
||||
id: "act-1",
|
||||
@ -167,202 +150,29 @@ describe("CommunicationOverlay — visibility gate", () => {
|
||||
const { getByLabelText } = await act(async () => {
|
||||
return render(<CommunicationOverlay />);
|
||||
});
|
||||
// Drain pending microtasks (resolves the await in bootstrap) so
|
||||
// setComms lands and the panel renders. Don't advance time — it's
|
||||
// not load-bearing for the gate test, but matches the pattern used
|
||||
// pre-#61 for stability.
|
||||
// Drain pending microtasks (resolves the await in fetchComms) so
|
||||
// setComms lands and the panel renders. Don't advance time — that
|
||||
// would fire the next interval tick and pollute the assertion.
|
||||
await act(async () => {
|
||||
await Promise.resolve();
|
||||
await Promise.resolve();
|
||||
await Promise.resolve();
|
||||
});
|
||||
expect(mockGet).toHaveBeenCalledTimes(3); // initial bootstrap
|
||||
// Initial mount polled 3 workspaces.
|
||||
expect(mockGet).toHaveBeenCalledTimes(3);
|
||||
mockGet.mockClear();
|
||||
|
||||
// Click close. While closed, no fetches and no WS-driven updates.
|
||||
// Click the close button. Synchronous getByLabelText avoids
|
||||
// findBy's internal setTimeout (deadlocks under useFakeTimers).
|
||||
const closeBtn = getByLabelText("Close communications panel");
|
||||
await act(async () => {
|
||||
fireEvent.click(closeBtn);
|
||||
});
|
||||
|
||||
// Advance well past the 30s cadence — gate should suppress the tick.
|
||||
await act(async () => {
|
||||
vi.advanceTimersByTime(60_000);
|
||||
});
|
||||
expect(mockGet).not.toHaveBeenCalled();
|
||||
|
||||
// Re-open via the collapsed button. Must trigger a fresh bootstrap.
|
||||
const openBtn = getByLabelText("Show communications panel");
|
||||
await act(async () => {
|
||||
fireEvent.click(openBtn);
|
||||
});
|
||||
await act(async () => {
|
||||
await Promise.resolve();
|
||||
await Promise.resolve();
|
||||
});
|
||||
expect(mockGet).toHaveBeenCalledTimes(3); // re-bootstrap on re-open
|
||||
});
|
||||
});
|
||||
|
||||
describe("CommunicationOverlay — WS subscription (#61 stage 1 core)", () => {
|
||||
// The load-bearing post-#61 behaviour. Every test in this block must
|
||||
// verify (a) the WS push DID update the rendered comms list, and
|
||||
// (b) NO additional HTTP call was fired — the whole point of the
|
||||
// refactor is to remove the polling-driven HTTP traffic.
|
||||
function emitActivityLogged(overrides: Partial<{
|
||||
workspaceId: string;
|
||||
payload: Record<string, unknown>;
|
||||
}> = {}) {
|
||||
emitSocketEvent({
|
||||
event: "ACTIVITY_LOGGED",
|
||||
workspace_id: overrides.workspaceId ?? "ws-1",
|
||||
timestamp: new Date().toISOString(),
|
||||
payload: {
|
||||
id: `act-${Math.random().toString(36).slice(2)}`,
|
||||
activity_type: "a2a_send",
|
||||
source_id: "ws-1",
|
||||
target_id: "ws-2",
|
||||
summary: "live push",
|
||||
status: "ok",
|
||||
duration_ms: 42,
|
||||
created_at: new Date().toISOString(),
|
||||
...overrides.payload,
|
||||
},
|
||||
});
|
||||
}
|
||||
|
||||
it("WS push for a comm activity_type extends the rendered list with NO additional HTTP call", async () => {
|
||||
const { container } = await act(async () => {
|
||||
return render(<CommunicationOverlay />);
|
||||
});
|
||||
expect(mockGet).toHaveBeenCalledTimes(3); // bootstrap
|
||||
mockGet.mockClear();
|
||||
|
||||
await act(async () => {
|
||||
emitActivityLogged({ payload: { summary: "hello" } });
|
||||
});
|
||||
await act(async () => {
|
||||
await Promise.resolve();
|
||||
});
|
||||
|
||||
// Two pins:
|
||||
// 1. comms list reflects the live push (look for the summary text)
|
||||
// 2. zero HTTP fetches fired during the WS path
|
||||
expect(container.textContent).toContain("hello");
|
||||
expect(mockGet).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("WS push for an offline workspace is ignored", async () => {
|
||||
const { container } = await act(async () => {
|
||||
return render(<CommunicationOverlay />);
|
||||
});
|
||||
mockGet.mockClear();
|
||||
|
||||
await act(async () => {
|
||||
emitActivityLogged({
|
||||
workspaceId: "ws-offline",
|
||||
payload: { source_id: "ws-offline", summary: "should-not-render" },
|
||||
});
|
||||
});
|
||||
await act(async () => {
|
||||
await Promise.resolve();
|
||||
});
|
||||
|
||||
expect(container.textContent).not.toContain("should-not-render");
|
||||
expect(mockGet).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("WS push for a non-comm activity_type is ignored (e.g. delegation)", async () => {
|
||||
const { container } = await act(async () => {
|
||||
return render(<CommunicationOverlay />);
|
||||
});
|
||||
mockGet.mockClear();
|
||||
|
||||
await act(async () => {
|
||||
emitActivityLogged({
|
||||
payload: {
|
||||
activity_type: "delegation",
|
||||
summary: "should-not-render-delegation",
|
||||
},
|
||||
});
|
||||
});
|
||||
await act(async () => {
|
||||
await Promise.resolve();
|
||||
});
|
||||
|
||||
expect(container.textContent).not.toContain("should-not-render-delegation");
|
||||
expect(mockGet).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("WS push while the panel is collapsed is ignored (no churn on hidden state)", async () => {
|
||||
// Bootstrap with one comm so the panel renders → close button
|
||||
// accessible. Then collapse, emit a WS push, re-open: the rendered
|
||||
// list must come from the re-bootstrap, NOT from the WS-push that
|
||||
// arrived during the closed state. Also: nothing visible while
|
||||
// closed (the collapsed button shows only the count, not summaries).
|
||||
mockGet.mockResolvedValue([
|
||||
{
|
||||
id: "act-bootstrap",
|
||||
workspace_id: "ws-1",
|
||||
activity_type: "a2a_send",
|
||||
source_id: "ws-1",
|
||||
target_id: "ws-2",
|
||||
summary: "bootstrap-summary",
|
||||
status: "ok",
|
||||
duration_ms: 1,
|
||||
created_at: new Date().toISOString(),
|
||||
},
|
||||
]);
|
||||
const { getByLabelText, container } = await act(async () => {
|
||||
return render(<CommunicationOverlay />);
|
||||
});
|
||||
await act(async () => {
|
||||
await Promise.resolve();
|
||||
await Promise.resolve();
|
||||
});
|
||||
|
||||
// Collapse.
|
||||
const closeBtn = getByLabelText("Close communications panel");
|
||||
await act(async () => {
|
||||
fireEvent.click(closeBtn);
|
||||
});
|
||||
|
||||
// Bootstrap mock returns nothing on the re-open path so we can
|
||||
// distinguish "WS push leaked through the gate" from "re-bootstrap
|
||||
// refilled the list."
|
||||
mockGet.mockReset();
|
||||
mockGet.mockResolvedValue([]);
|
||||
|
||||
await act(async () => {
|
||||
emitActivityLogged({
|
||||
payload: { summary: "leaked-while-closed" },
|
||||
});
|
||||
});
|
||||
await act(async () => {
|
||||
await Promise.resolve();
|
||||
});
|
||||
|
||||
// Closed state: rendered DOM must not show any push-derived text.
|
||||
expect(container.textContent).not.toContain("leaked-while-closed");
|
||||
});
|
||||
|
||||
it("non-ACTIVITY_LOGGED events are ignored (e.g. WORKSPACE_OFFLINE)", async () => {
|
||||
const { container } = await act(async () => {
|
||||
return render(<CommunicationOverlay />);
|
||||
});
|
||||
mockGet.mockClear();
|
||||
|
||||
await act(async () => {
|
||||
emitSocketEvent({
|
||||
event: "WORKSPACE_OFFLINE",
|
||||
workspace_id: "ws-1",
|
||||
timestamp: new Date().toISOString(),
|
||||
payload: { summary: "should-not-render-event" },
|
||||
});
|
||||
});
|
||||
await act(async () => {
|
||||
await Promise.resolve();
|
||||
});
|
||||
|
||||
expect(container.textContent).not.toContain("should-not-render-event");
|
||||
expect(mockGet).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
|
||||
@ -1,9 +1,8 @@
|
||||
"use client";
|
||||
|
||||
import { useState, useEffect, useCallback, useRef } from "react";
|
||||
import { useState, useEffect, useCallback } from "react";
|
||||
import { api } from "@/lib/api";
|
||||
import { ConversationTraceModal } from "@/components/ConversationTraceModal";
|
||||
import { useSocketEvent } from "@/hooks/useSocketEvent";
|
||||
import { type ActivityEntry } from "@/types/activity";
|
||||
import { useWorkspaceName } from "@/hooks/useWorkspaceName";
|
||||
import { inferA2AErrorHint } from "./chat/a2aErrorHint";
|
||||
@ -49,15 +48,6 @@ export function ActivityTab({ workspaceId }: Props) {
|
||||
const [traceOpen, setTraceOpen] = useState(false);
|
||||
const resolveName = useWorkspaceName();
|
||||
|
||||
// Refs let the WS handler read the latest filter / autoRefresh
|
||||
// selection without re-subscribing on every state change. The bus
|
||||
// listener is registered exactly once per mount via useSocketEvent's
|
||||
// ref-internal pattern; subscriber-side filtering reads from these.
|
||||
const filterRef = useRef(filter);
|
||||
filterRef.current = filter;
|
||||
const autoRefreshRef = useRef(autoRefresh);
|
||||
autoRefreshRef.current = autoRefresh;
|
||||
|
||||
const loadActivities = useCallback(async () => {
|
||||
try {
|
||||
const typeParam = filter !== "all" ? `?type=${filter}` : "";
|
||||
@ -76,58 +66,11 @@ export function ActivityTab({ workspaceId }: Props) {
|
||||
loadActivities();
|
||||
}, [loadActivities]);
|
||||
|
||||
// Live-update path (issue #61 stage 3, replaces the 5s setInterval).
|
||||
// ACTIVITY_LOGGED events from this workspace prepend to the rendered
|
||||
// list — dedup by id so a server-side update + a poll reply don't
|
||||
// double-render the same row.
|
||||
//
|
||||
// Honours the user's autoRefresh toggle: when paused, live updates
|
||||
// are dropped until the user re-enables Live (or hits Refresh, which
|
||||
// re-bootstraps via loadActivities).
|
||||
//
|
||||
// Filter awareness: matches the server-side `?type=<filter>`
|
||||
// semantics so the panel doesn't show rows the user excluded.
|
||||
useSocketEvent((msg) => {
|
||||
if (!autoRefreshRef.current) return;
|
||||
if (msg.event !== "ACTIVITY_LOGGED") return;
|
||||
if (msg.workspace_id !== workspaceId) return;
|
||||
|
||||
const p = (msg.payload || {}) as Record<string, unknown>;
|
||||
const activityType = (p.activity_type as string) || "";
|
||||
|
||||
const f = filterRef.current;
|
||||
if (f !== "all" && activityType !== f) return;
|
||||
|
||||
const entry: ActivityEntry = {
|
||||
id:
|
||||
(p.id as string) ||
|
||||
`ws-push-${msg.timestamp || Date.now()}-${msg.workspace_id}`,
|
||||
workspace_id: msg.workspace_id,
|
||||
activity_type: activityType,
|
||||
source_id: (p.source_id as string | null) ?? null,
|
||||
target_id: (p.target_id as string | null) ?? null,
|
||||
method: (p.method as string | null) ?? null,
|
||||
summary: (p.summary as string | null) ?? null,
|
||||
request_body: (p.request_body as Record<string, unknown> | null) ?? null,
|
||||
response_body:
|
||||
(p.response_body as Record<string, unknown> | null) ?? null,
|
||||
duration_ms: (p.duration_ms as number | null) ?? null,
|
||||
status: (p.status as string) || "ok",
|
||||
error_detail: (p.error_detail as string | null) ?? null,
|
||||
created_at:
|
||||
(p.created_at as string) ||
|
||||
msg.timestamp ||
|
||||
new Date().toISOString(),
|
||||
};
|
||||
|
||||
setActivities((prev) => {
|
||||
// Dedup by id — a row that arrived via the bootstrap fetch and
|
||||
// also fires ACTIVITY_LOGGED from a delayed server-side hook
|
||||
// must render exactly once.
|
||||
if (prev.some((e) => e.id === entry.id)) return prev;
|
||||
return [entry, ...prev];
|
||||
});
|
||||
});
|
||||
useEffect(() => {
|
||||
if (!autoRefresh) return;
|
||||
const interval = setInterval(loadActivities, 5000);
|
||||
return () => clearInterval(interval);
|
||||
}, [loadActivities, autoRefresh]);
|
||||
|
||||
return (
|
||||
<div className="flex flex-col h-full">
|
||||
|
||||
@ -13,6 +13,7 @@ import { AttachmentPreview } from "./chat/AttachmentPreview";
|
||||
import { extractFilesFromTask } from "./chat/message-parser";
|
||||
import { AgentCommsPanel } from "./chat/AgentCommsPanel";
|
||||
import { appendActivityLine } from "./chat/activityLog";
|
||||
import { activityRowToMessages, type ActivityRowForHydration } from "./chat/historyHydration";
|
||||
import { runtimeDisplayName } from "@/lib/runtime-names";
|
||||
import { ConfirmDialog } from "@/components/ConfirmDialog";
|
||||
|
||||
@ -49,12 +50,38 @@ interface A2AResponse {
|
||||
};
|
||||
}
|
||||
|
||||
// Internal-self-message filtering moved server-side in RFC #2945
|
||||
// PR-C/D — the platform's /chat-history endpoint applies the
|
||||
// IsInternalSelfMessage predicate before returning rows, so the
|
||||
// client no longer needs the local backstop on the history path.
|
||||
// The proper fix is still X-Workspace-ID header (source_id=workspace_id);
|
||||
// the platform-side prefix filter handles the residual cases.
|
||||
/** Detect activity-log rows that the workspace's own runtime fired
|
||||
* against itself but were misclassified as canvas-source. The proper
|
||||
* fix is the X-Workspace-ID header from `self_source_headers()` in
|
||||
* workspace/platform_auth.py, which makes the platform record
|
||||
* source_id = workspace_id. But three failure modes still leak a
|
||||
* self-message into "My Chat":
|
||||
*
|
||||
* 1. Historical rows already in the DB with source_id=NULL.
|
||||
* 2. Workspace containers running pre-fix heartbeat.py / main.py
|
||||
* (the fix only takes effect after an image rebuild + redeploy).
|
||||
* 3. Future internal triggers added without the helper.
|
||||
*
|
||||
* This client-side filter recognises the heartbeat trigger by its
|
||||
* exact prefix — the heartbeat assembles
|
||||
*
|
||||
* "Delegation results are ready. Review them and take appropriate
|
||||
* action:\n" + summary_lines + report_instruction
|
||||
*
|
||||
* in workspace/heartbeat.py. The prefix is template-fixed so a
|
||||
* string match is reliable. If the heartbeat copy ever changes,
|
||||
* update this constant in the same commit.
|
||||
*
|
||||
* This is a backstop, not the primary defence — the X-Workspace-ID
|
||||
* header is. Filtering content is fragile to copy edits, so keep
|
||||
* the list narrow. */
|
||||
const INTERNAL_SELF_MESSAGE_PREFIXES = [
|
||||
"Delegation results are ready. Review them and take appropriate action",
|
||||
];
|
||||
|
||||
function isInternalSelfMessage(text: string): boolean {
|
||||
return INTERNAL_SELF_MESSAGE_PREFIXES.some((p) => text.startsWith(p));
|
||||
}
|
||||
|
||||
// extractReplyText pulls the agent's text reply out of an A2A response.
|
||||
// Concatenates ALL text parts (joined with "\n") rather than returning
|
||||
@ -107,19 +134,8 @@ const INITIAL_HISTORY_LIMIT = 10;
|
||||
const OLDER_HISTORY_BATCH = 20;
|
||||
|
||||
/**
|
||||
* Load chat history from the platform's typed /chat-history endpoint.
|
||||
*
|
||||
* Server-side rendering of activity_logs rows into ChatMessage shape
|
||||
* lives in workspace-server/internal/messagestore/postgres_store.go
|
||||
* (RFC #2945 PR-C/D). The server already applies the canvas-source
|
||||
* filter, the internal-self-message predicate, the role decision
|
||||
* (status=error vs agent-error prefix → system), and the v0/v1
|
||||
* file-shape extraction. Canvas just renders what it receives.
|
||||
*
|
||||
* Wire shape (mirrors ChatMessage exactly, no per-row mapping needed):
|
||||
*
|
||||
* GET /workspaces/:id/chat-history?limit=N&before_ts=T
|
||||
* 200 → {"messages": ChatMessage[], "reached_end": boolean}
|
||||
* Load chat history from the activity_logs database via the platform API.
|
||||
* Uses source=canvas to only get user-initiated messages (not agent-to-agent).
|
||||
*
|
||||
* Pagination:
|
||||
* - Pass `limit` to bound the page size (newest-first from server).
|
||||
@ -127,10 +143,10 @@ const OLDER_HISTORY_BATCH = 20;
|
||||
* timestamp. Combined with limit, this yields the next-older page
|
||||
* when scrolling backward through history.
|
||||
*
|
||||
* `reachedEnd` is propagated from the server. The server computes it
|
||||
* by comparing rowCount vs limit so a partial last page is correctly
|
||||
* detected even when the row→bubble fan-out is non-1:1 (each row
|
||||
* produces 1-2 bubbles).
|
||||
* `reachedEnd` is true when the server returned fewer rows than asked
|
||||
* for — caller uses this to disable further older-batch fetches.
|
||||
* (Counts row-level returns, not chat-bubble count: each row may
|
||||
* produce 1-2 bubbles.)
|
||||
*/
|
||||
async function loadMessagesFromDB(
|
||||
workspaceId: string,
|
||||
@ -138,23 +154,25 @@ async function loadMessagesFromDB(
|
||||
beforeTs?: string,
|
||||
): Promise<{ messages: ChatMessage[]; error: string | null; reachedEnd: boolean }> {
|
||||
try {
|
||||
const params = new URLSearchParams({ limit: String(limit) });
|
||||
const params = new URLSearchParams({
|
||||
type: "a2a_receive",
|
||||
source: "canvas",
|
||||
limit: String(limit),
|
||||
});
|
||||
if (beforeTs) params.set("before_ts", beforeTs);
|
||||
const resp = await api.get<{ messages: ChatMessage[]; reached_end: boolean }>(
|
||||
`/workspaces/${workspaceId}/chat-history?${params.toString()}`,
|
||||
const activities = await api.get<ActivityRowForHydration[]>(
|
||||
`/workspaces/${workspaceId}/activity?${params.toString()}`,
|
||||
);
|
||||
|
||||
// Server emits oldest-first within the page (RFC #2945 PR-C-2
|
||||
// post-fix: server reverses row-aware before returning so the
|
||||
// wire is display-ready). Canvas appends/prepends without
|
||||
// reordering — this avoids the pair-flip bug a naive flat
|
||||
// reverse causes when each row produces a (user, agent) pair
|
||||
// with the same timestamp.
|
||||
return {
|
||||
messages: resp.messages ?? [],
|
||||
error: null,
|
||||
reachedEnd: resp.reached_end,
|
||||
};
|
||||
const messages: ChatMessage[] = [];
|
||||
// Activities are newest-first, reverse for chronological order.
|
||||
// Per-row mapping lives in chat/historyHydration.ts so it can be
|
||||
// unit-tested without spinning up the full ChatTab component
|
||||
// (regression cover for the timestamp-collapse bug).
|
||||
for (const a of [...activities].reverse()) {
|
||||
messages.push(...activityRowToMessages(a, isInternalSelfMessage));
|
||||
}
|
||||
return { messages, error: null, reachedEnd: activities.length < limit };
|
||||
} catch (err) {
|
||||
return {
|
||||
messages: [],
|
||||
|
||||
@ -21,39 +21,20 @@ interface Props {
|
||||
// --- Agent Card Section ---
|
||||
|
||||
function AgentCardSection({ workspaceId }: { workspaceId: string }) {
|
||||
// Initial card value comes from the canvas store — node.data.agentCard
|
||||
// is hydrated by the platform stream when the workspace appears in the
|
||||
// graph, so reading it here avoids a duplicate `GET /workspaces/${id}`
|
||||
// (the parent ConfigTab.loadConfig already fetches workspace metadata,
|
||||
// and refetching here adds a serialised RTT to the panel-open path —
|
||||
// contributed to the ~20s detail-panel load reported in core#11).
|
||||
// Local state still tracks the edited/saved value so the editor flow
|
||||
// is unchanged.
|
||||
const storeCard = useCanvasStore((s) => {
|
||||
// Defensive against test mocks that omit `nodes` (some test files
|
||||
// stub the store with a minimal shape). In production `nodes` is
|
||||
// always an array — empty or not — so the optional chaining only
|
||||
// matters for the test path.
|
||||
const node = s.nodes?.find?.((n) => n.id === workspaceId);
|
||||
return (node?.data.agentCard as
|
||||
| Record<string, unknown>
|
||||
| null
|
||||
| undefined) ?? null;
|
||||
});
|
||||
const [card, setCard] = useState<Record<string, unknown> | null>(storeCard);
|
||||
const [card, setCard] = useState<Record<string, unknown> | null>(null);
|
||||
const [loading, setLoading] = useState(true);
|
||||
const [editing, setEditing] = useState(false);
|
||||
const [draft, setDraft] = useState("");
|
||||
const [saving, setSaving] = useState(false);
|
||||
const [error, setError] = useState<string | null>(null);
|
||||
const [success, setSuccess] = useState(false);
|
||||
|
||||
// If the store updates while this section is mounted (another tab
|
||||
// pushed an update via the platform event stream), reflect that —
|
||||
// unless the user is mid-edit, in which case we don't clobber their
|
||||
// unsaved draft.
|
||||
useEffect(() => {
|
||||
if (!editing) setCard(storeCard);
|
||||
}, [storeCard, editing]);
|
||||
api.get<Record<string, unknown>>(`/workspaces/${workspaceId}`)
|
||||
.then((ws) => setCard((ws.agent_card as Record<string, unknown>) || null))
|
||||
.catch(() => {})
|
||||
.finally(() => setLoading(false));
|
||||
}, [workspaceId]);
|
||||
|
||||
const handleSave = async () => {
|
||||
setError(null);
|
||||
@ -72,7 +53,9 @@ function AgentCardSection({ workspaceId }: { workspaceId: string }) {
|
||||
|
||||
return (
|
||||
<Section title="Agent Card" defaultOpen={false}>
|
||||
{editing ? (
|
||||
{loading ? (
|
||||
<div className="text-[10px] text-ink-soft">Loading...</div>
|
||||
) : editing ? (
|
||||
<div className="space-y-2">
|
||||
<textarea
|
||||
aria-label="Agent card JSON editor"
|
||||
@ -238,51 +221,47 @@ export function ConfigTab({ workspaceId }: Props) {
|
||||
setLoading(true);
|
||||
setError(null);
|
||||
|
||||
// Load workspace metadata (runtime + model + provider) in parallel.
|
||||
// These are independent GETs against three workspace-server endpoints
|
||||
// and used to be awaited serially — for SaaS workspaces each call
|
||||
// round-trips through an EIC SSH tunnel, so the previous serial
|
||||
// pattern stacked 3-5s of tunnel-setup latency per call (core#11).
|
||||
// Promise.all overlaps them; the per-call cost stays the same but
|
||||
// wall time drops to max() instead of sum().
|
||||
//
|
||||
// Each leg has its own .catch handler that yields a sentinel value,
|
||||
// matching the previous semantics:
|
||||
// - /workspaces/${id}: required source-of-truth for runtime+tier;
|
||||
// fall back to YAML if the GET fails (rare, network-class only).
|
||||
// - /workspaces/${id}/model: non-fatal; empty model lets the form
|
||||
// fall through to YAML runtime_config.model.
|
||||
// - /workspaces/${id}/provider: non-fatal; old workspace-servers
|
||||
// return 404, in which case provider="" and Save skips the PUT.
|
||||
//
|
||||
// See GH #1894 for the workspace-row-as-source-of-truth rationale
|
||||
// that motivated splitting from a single config.yaml read.
|
||||
const [wsRes, modelRes, providerRes] = await Promise.all([
|
||||
api.get<{ runtime?: string; tier?: number }>(`/workspaces/${workspaceId}`)
|
||||
.catch(() => ({} as { runtime?: string; tier?: number })),
|
||||
api.get<{ model?: string }>(`/workspaces/${workspaceId}/model`)
|
||||
.catch(() => ({} as { model?: string })),
|
||||
api.get<{ provider?: string }>(`/workspaces/${workspaceId}/provider`)
|
||||
.catch(() => null),
|
||||
]);
|
||||
const wsMetadataRuntime = (wsRes.runtime || "").trim();
|
||||
const wsMetadataModel = (modelRes.model || "").trim();
|
||||
const wsMetadataTier: number | null =
|
||||
typeof wsRes.tier === "number" ? wsRes.tier : null;
|
||||
if (providerRes !== null) {
|
||||
const loadedProvider = (providerRes.provider || "").trim();
|
||||
setProvider(loadedProvider);
|
||||
setOriginalProvider(loadedProvider);
|
||||
} else {
|
||||
setProvider("");
|
||||
setOriginalProvider("");
|
||||
}
|
||||
// ALWAYS load workspace metadata first (runtime + model). These are the
|
||||
// source of truth regardless of whether the runtime uses our config.yaml
|
||||
// template. Without this the form falls back to empty/default values on
|
||||
// a hermes workspace (which doesn't use our template), creating the
|
||||
// appearance that the saved runtime is unset — and worse, clicking Save
|
||||
// would silently flip `runtime` from `hermes` back to the dropdown
|
||||
// default `LangGraph`. See GH #1894.
|
||||
let wsMetadataRuntime = "";
|
||||
let wsMetadataModel = "";
|
||||
let wsMetadataTier: number | null = null;
|
||||
try {
|
||||
const ws = await api.get<{ runtime?: string; tier?: number }>(`/workspaces/${workspaceId}`);
|
||||
wsMetadataRuntime = (ws.runtime || "").trim();
|
||||
if (typeof ws.tier === "number") wsMetadataTier = ws.tier;
|
||||
} catch { /* fall back to config.yaml */ }
|
||||
try {
|
||||
const m = await api.get<{ model?: string }>(`/workspaces/${workspaceId}/model`);
|
||||
wsMetadataModel = (m.model || "").trim();
|
||||
} catch { /* non-fatal */ }
|
||||
// originalModel is set further down once the YAML has been parsed —
|
||||
// we want it to reflect what the form ACTUALLY rendered, which may
|
||||
// be the YAML's runtime_config.model fallback when MODEL_PROVIDER
|
||||
// is empty. Setting it here from wsMetadataModel alone would be
|
||||
// wrong for hermes/pre-#240 workspaces.
|
||||
|
||||
// Load explicit provider override (Option B PR-5). Endpoint returns
|
||||
// {provider: "", source: "default"} when no override is set, so the
|
||||
// empty string is the legitimate "auto-derive" signal — don't treat
|
||||
// it as a load error. Non-fatal: an older workspace-server that
|
||||
// predates PR-2 returns 404 here; the form falls back to "" and
|
||||
// Save just won't PUT the provider field.
|
||||
try {
|
||||
const p = await api.get<{ provider?: string }>(`/workspaces/${workspaceId}/provider`);
|
||||
const loadedProvider = (p.provider || "").trim();
|
||||
setProvider(loadedProvider);
|
||||
setOriginalProvider(loadedProvider);
|
||||
} catch {
|
||||
setProvider("");
|
||||
setOriginalProvider("");
|
||||
}
|
||||
|
||||
// Skip the config.yaml fetch entirely for runtimes that manage
|
||||
// their own config (external, hermes, etc.) — they don't have a
|
||||
// platform-side template, so the GET would 404. The catch block
|
||||
|
||||
@ -1,11 +1,13 @@
|
||||
// @vitest-environment jsdom
|
||||
//
|
||||
// Pins the lazy-loading chat-history pagination.
|
||||
// Pins the lazy-loading chat-history pagination added 2026-05-05.
|
||||
//
|
||||
// PR-C-2 (RFC #2945): canvas was migrated from /activity?type=a2a_receive
|
||||
// to /chat-history. Server now returns typed ChatMessage[] in
|
||||
// display-ready oldest-first order. These tests guard the canvas-side
|
||||
// pagination invariants against the new endpoint surface.
|
||||
// Pre-fix: ChatTab fetched the newest 50 messages on every mount and
|
||||
// scrolled to bottom, paying full DOM cost up-front even when the user
|
||||
// only wanted to read the last few bubbles. Post-fix: initial load is
|
||||
// bounded to 10 newest, and an IntersectionObserver on a top sentinel
|
||||
// triggers loadOlder() (batch of 20 with `before_ts` cursor) when the
|
||||
// user scrolls up.
|
||||
//
|
||||
// Pinned branches:
|
||||
// 1. Initial fetch carries `limit=10` and NO before_ts (newest-first
|
||||
@ -18,10 +20,11 @@
|
||||
// asserting the rendered bubble count matches the full page).
|
||||
// 4. The retry button after a failed initial load uses the same
|
||||
// INITIAL_HISTORY_LIMIT (10), not the legacy 50.
|
||||
// 5. before_ts cursor is the OLDEST timestamp from the current page,
|
||||
// passed verbatim to walk backward.
|
||||
// 6. Inflight guard rejects duplicate IO triggers while a loadOlder
|
||||
// fetch is in flight.
|
||||
//
|
||||
// IntersectionObserver / scroll-anchor restoration is exercised by the
|
||||
// E2E synth-canary suite — pinning it in jsdom would require mocking
|
||||
// the observer and faking layout, which is brittler than trusting a
|
||||
// live-DOM canary against the staging tenant.
|
||||
|
||||
import { describe, it, expect, vi, afterEach, beforeEach } from "vitest";
|
||||
import { render, screen, cleanup, waitFor, fireEvent } from "@testing-library/react";
|
||||
@ -30,31 +33,24 @@ import React from "react";
|
||||
afterEach(cleanup);
|
||||
|
||||
// Both ChatTab sub-panels (MyChat + AgentComms) mount simultaneously so
|
||||
// keyboard tab order and aria-controls land on a real DOM. MyChat's
|
||||
// loadMessagesFromDB hits /chat-history; AgentComms's polling hits a
|
||||
// different URL. Route the mock by URL so each gets a sensible default
|
||||
// and only MyChat's calls land in the assertion array.
|
||||
const myChatHistoryCalls: string[] = [];
|
||||
let myChatNextResponse:
|
||||
| { ok: true; messages: unknown[]; reachedEnd?: boolean }
|
||||
| { ok: false; err: Error } = { ok: true, messages: [] };
|
||||
|
||||
// keyboard tab order and aria-controls land on a real DOM. Both fire
|
||||
// /activity GETs on mount: MyChat's hits `type=a2a_receive&source=canvas`,
|
||||
// AgentComms's hits a different filter. Route the mock by URL so each
|
||||
// gets a sensible default and only MyChat's call is what the assertions
|
||||
// scrutinise.
|
||||
const myChatActivityCalls: string[] = [];
|
||||
let myChatNextResponse: { ok: true; rows: unknown[] } | { ok: false; err: Error } = {
|
||||
ok: true,
|
||||
rows: [],
|
||||
};
|
||||
const apiGet = vi.fn((path: string): Promise<unknown> => {
|
||||
if (path.includes("/chat-history")) {
|
||||
myChatHistoryCalls.push(path);
|
||||
if (myChatNextResponse.ok) {
|
||||
const reached_end =
|
||||
myChatNextResponse.reachedEnd !== undefined
|
||||
? myChatNextResponse.reachedEnd
|
||||
: myChatNextResponse.messages.length < 10;
|
||||
return Promise.resolve({
|
||||
messages: myChatNextResponse.messages,
|
||||
reached_end,
|
||||
});
|
||||
}
|
||||
if (path.includes("type=a2a_receive") && path.includes("source=canvas")) {
|
||||
myChatActivityCalls.push(path);
|
||||
if (myChatNextResponse.ok) return Promise.resolve(myChatNextResponse.rows);
|
||||
return Promise.reject(myChatNextResponse.err);
|
||||
}
|
||||
// AgentComms / heartbeat / anything else — empty array safe default.
|
||||
// AgentComms / heartbeat / anything else — empty array is a safe
|
||||
// default that won't blow up the corresponding component's .then().
|
||||
return Promise.resolve([]);
|
||||
});
|
||||
const apiPost = vi.fn();
|
||||
@ -88,8 +84,8 @@ const ioInstances: IOInstance[] = [];
|
||||
beforeEach(() => {
|
||||
apiGet.mockClear();
|
||||
apiPost.mockReset();
|
||||
myChatHistoryCalls.length = 0;
|
||||
myChatNextResponse = { ok: true, messages: [] };
|
||||
myChatActivityCalls.length = 0;
|
||||
myChatNextResponse = { ok: true, rows: [] };
|
||||
ioInstances.length = 0;
|
||||
class FakeIO {
|
||||
private inst: IOInstance;
|
||||
@ -105,12 +101,20 @@ beforeEach(() => {
|
||||
this.inst.disconnected = true;
|
||||
}
|
||||
}
|
||||
// Install on every reachable global — different bundlers / module
|
||||
// graphs can resolve `IntersectionObserver` via `window`, `globalThis`,
|
||||
// or the bare global. Without all three, jsdom's own (pre-existing)
|
||||
// stub silently wins and ioInstances stays empty.
|
||||
(window as unknown as { IntersectionObserver: unknown }).IntersectionObserver = FakeIO;
|
||||
(globalThis as unknown as { IntersectionObserver: unknown }).IntersectionObserver = FakeIO;
|
||||
// jsdom doesn't implement scrollIntoView; ChatTab calls it after every
|
||||
// messages update.
|
||||
Element.prototype.scrollIntoView = vi.fn();
|
||||
});
|
||||
|
||||
function triggerIntersection(instanceIdx = -1) {
|
||||
// -1 → the latest observer (the live one). Tests targeting an old
|
||||
// (disconnected) instance pass a positive index.
|
||||
const inst = ioInstances.at(instanceIdx);
|
||||
if (!inst) throw new Error(`no IO instance at ${instanceIdx}`);
|
||||
inst.callback(
|
||||
@ -121,30 +125,25 @@ function triggerIntersection(instanceIdx = -1) {
|
||||
|
||||
import { ChatTab } from "../ChatTab";
|
||||
|
||||
// makeMessagePair returns a (user, agent) pair sharing a timestamp,
|
||||
// matching the wire shape /chat-history emits per activity_logs row.
|
||||
// Server-side reverseRowChunks ensures the wire is oldest-first across
|
||||
// rows but [user, agent] within each row.
|
||||
function makeMessagePair(seq: number): unknown[] {
|
||||
// Zero-pad seq into the minute slot so seq=10 produces a valid
|
||||
// timestamp (00:10:00Z, not 00:010:00Z).
|
||||
function makeActivityRow(seq: number): Record<string, unknown> {
|
||||
// Zero-pad seq into the minute slot so "seq=10" doesn't produce
|
||||
// the invalid timestamp "00:010:00Z" (caught by the loadOlder URL
|
||||
// assertion below — first version of the helper used `0${seq}` and
|
||||
// the test failed on `before_ts` having an extra digit).
|
||||
const mm = String(seq).padStart(2, "0");
|
||||
const ts = `2026-05-05T00:${mm}:00Z`;
|
||||
return [
|
||||
{ id: `u-${seq}`, role: "user", content: `user msg ${seq}`, timestamp: ts },
|
||||
{ id: `a-${seq}`, role: "agent", content: `agent reply ${seq}`, timestamp: ts },
|
||||
];
|
||||
return {
|
||||
activity_type: "a2a_receive",
|
||||
status: "ok",
|
||||
created_at: `2026-05-05T00:${mm}:00Z`,
|
||||
request_body: { params: { message: { parts: [{ kind: "text", text: `user msg ${seq}` }] } } },
|
||||
response_body: { result: `agent reply ${seq}` },
|
||||
};
|
||||
}
|
||||
|
||||
// pageOldestFirst builds a wire-shape page (oldest-first within page)
|
||||
// of `count` row-pairs starting at seq=`start`. Mirrors the server's
|
||||
// post-reverseRowChunks emission order.
|
||||
function pageOldestFirst(start: number, count: number): unknown[] {
|
||||
const out: unknown[] = [];
|
||||
for (let i = 0; i < count; i++) {
|
||||
out.push(...makeMessagePair(start + i));
|
||||
}
|
||||
return out;
|
||||
// Server returns newest-first; the helper builds a server-shape page
|
||||
// so the order in the rendered messages array matches production.
|
||||
function newestFirstPage(start: number, count: number): unknown[] {
|
||||
return Array.from({ length: count }, (_, i) => makeActivityRow(start + count - 1 - i));
|
||||
}
|
||||
|
||||
const minimalData = {
|
||||
@ -154,30 +153,28 @@ const minimalData = {
|
||||
} as unknown as Parameters<typeof ChatTab>[0]["data"];
|
||||
|
||||
describe("ChatTab lazy history pagination", () => {
|
||||
it("initial fetch carries limit=10 (not the legacy 50) and hits /chat-history", async () => {
|
||||
myChatNextResponse = { ok: true, messages: makeMessagePair(1) };
|
||||
it("initial fetch carries limit=10 (not the legacy 50)", async () => {
|
||||
myChatNextResponse = { ok: true, rows: [makeActivityRow(1)] };
|
||||
render(<ChatTab workspaceId="ws-1" data={minimalData} />);
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(1));
|
||||
const url = myChatHistoryCalls[0];
|
||||
expect(url).toContain("/chat-history");
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(1));
|
||||
const url = myChatActivityCalls[0];
|
||||
expect(url).toContain("limit=10");
|
||||
expect(url).not.toContain("limit=50");
|
||||
// before_ts should NOT be set on the initial fetch — that's the
|
||||
// newest-first slice the user lands on.
|
||||
expect(url).not.toContain("before_ts");
|
||||
// /chat-history filters source-canvas server-side; client should
|
||||
// NOT pass type/source params (they belonged to /activity).
|
||||
expect(url).not.toContain("type=a2a_receive");
|
||||
expect(url).not.toContain("source=canvas");
|
||||
});
|
||||
|
||||
it("hides the top sentinel when initial fetch returns fewer than the limit", async () => {
|
||||
// 3 < 10 → server says "no more older history exists"; sentinel
|
||||
// should NOT mount and the "Loading older messages…" line should
|
||||
// never appear.
|
||||
myChatNextResponse = { ok: true, messages: pageOldestFirst(1, 3) };
|
||||
// never appear (it can't, since the sentinel is what triggers it).
|
||||
myChatNextResponse = {
|
||||
ok: true,
|
||||
rows: [makeActivityRow(1), makeActivityRow(2), makeActivityRow(3)],
|
||||
};
|
||||
render(<ChatTab workspaceId="ws-2" data={minimalData} />);
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(1));
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(1));
|
||||
await waitFor(() => {
|
||||
expect(screen.queryByText(/Loading chat history/i)).toBeNull();
|
||||
});
|
||||
@ -185,15 +182,15 @@ describe("ChatTab lazy history pagination", () => {
|
||||
});
|
||||
|
||||
it("renders all messages when initial fetch returns exactly the limit", async () => {
|
||||
// limit=10 row-pairs → 20 ChatMessages. reachedEnd should be FALSE
|
||||
// so the sentinel mounts. Verified by bubble counts.
|
||||
myChatNextResponse = {
|
||||
ok: true,
|
||||
messages: pageOldestFirst(1, 10),
|
||||
reachedEnd: false,
|
||||
};
|
||||
// 10 == limit → server might have more older rows; sentinel SHOULD
|
||||
// mount so the IO observer can fire loadOlder() on scroll-up. We
|
||||
// verify by checking the rendered bubble count — if hasMore stayed
|
||||
// true the sentinel render path doesn't crash and all 10 rows
|
||||
// produced their pair of bubbles.
|
||||
const fullPage = Array.from({ length: 10 }, (_, i) => makeActivityRow(i + 1));
|
||||
myChatNextResponse = { ok: true, rows: fullPage };
|
||||
render(<ChatTab workspaceId="ws-3" data={minimalData} />);
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(1));
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(1));
|
||||
await waitFor(() => {
|
||||
expect(screen.queryByText(/Loading chat history/i)).toBeNull();
|
||||
});
|
||||
@ -205,67 +202,54 @@ describe("ChatTab lazy history pagination", () => {
|
||||
myChatNextResponse = { ok: false, err: new Error("network down") };
|
||||
render(<ChatTab workspaceId="ws-4" data={minimalData} />);
|
||||
const retry = await screen.findByText(/Retry/);
|
||||
myChatNextResponse = { ok: true, messages: makeMessagePair(1) };
|
||||
myChatNextResponse = { ok: true, rows: [makeActivityRow(1)] };
|
||||
fireEvent.click(retry);
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(2));
|
||||
const retryUrl = myChatHistoryCalls[1];
|
||||
expect(retryUrl).toContain("/chat-history");
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(2));
|
||||
const retryUrl = myChatActivityCalls[1];
|
||||
expect(retryUrl).toContain("limit=10");
|
||||
expect(retryUrl).not.toContain("limit=50");
|
||||
});
|
||||
|
||||
it("loadOlder fetches limit=20 with before_ts=oldest.timestamp", async () => {
|
||||
// Initial page = 10 row-pairs in oldest-first order (seq 1..10).
|
||||
// The oldest (and so the cursor for loadOlder) is seq=1's
|
||||
// timestamp 2026-05-05T00:01:00Z.
|
||||
myChatNextResponse = {
|
||||
ok: true,
|
||||
messages: pageOldestFirst(1, 10),
|
||||
reachedEnd: false,
|
||||
};
|
||||
// Initial page = 10 rows in newest-first order (seq 10..1). After
|
||||
// the component reverses to oldest-first for display, messages[0]
|
||||
// is built from seq=1 — the oldest — and its timestamp is what
|
||||
// before_ts should carry.
|
||||
myChatNextResponse = { ok: true, rows: newestFirstPage(1, 10) };
|
||||
render(<ChatTab workspaceId="ws-load-older" data={minimalData} />);
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(1));
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(1));
|
||||
await waitFor(() => expect(ioInstances.length).toBeGreaterThan(0));
|
||||
|
||||
// Stage older-batch response, then fire IO callback.
|
||||
myChatNextResponse = {
|
||||
ok: true,
|
||||
messages: pageOldestFirst(0, 1),
|
||||
reachedEnd: true,
|
||||
};
|
||||
// Stage the older-batch response, then fire the IO callback.
|
||||
myChatNextResponse = { ok: true, rows: newestFirstPage(0, 1) };
|
||||
triggerIntersection();
|
||||
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(2));
|
||||
const olderUrl = myChatHistoryCalls[1];
|
||||
expect(olderUrl).toContain("/chat-history");
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(2));
|
||||
const olderUrl = myChatActivityCalls[1];
|
||||
expect(olderUrl).toContain("limit=20");
|
||||
expect(olderUrl).toContain("before_ts=");
|
||||
expect(decodeURIComponent(olderUrl)).toContain("before_ts=2026-05-05T00:01:00Z");
|
||||
});
|
||||
|
||||
it("inflight guard rejects a second IO trigger while first loadOlder is in flight", async () => {
|
||||
myChatNextResponse = {
|
||||
ok: true,
|
||||
messages: pageOldestFirst(1, 10),
|
||||
reachedEnd: false,
|
||||
};
|
||||
myChatNextResponse = { ok: true, rows: newestFirstPage(1, 10) };
|
||||
render(<ChatTab workspaceId="ws-inflight" data={minimalData} />);
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(1));
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(1));
|
||||
await waitFor(() => expect(ioInstances.length).toBeGreaterThan(0));
|
||||
|
||||
// Hold the next loadOlder fetch open with a manual deferred so we
|
||||
// can fire the second trigger while the first is in-flight.
|
||||
let release!: (resp: unknown) => void;
|
||||
const deferred = new Promise<unknown>((res) => {
|
||||
let release!: (rows: unknown[]) => void;
|
||||
const deferred = new Promise<unknown[]>((res) => {
|
||||
release = res;
|
||||
});
|
||||
apiGet.mockImplementationOnce((path: string): Promise<unknown> => {
|
||||
myChatHistoryCalls.push(path);
|
||||
myChatActivityCalls.push(path);
|
||||
return deferred;
|
||||
});
|
||||
|
||||
triggerIntersection(); // start loadOlder #1
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(2));
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(2));
|
||||
|
||||
// Second IO trigger lands while #1 is still pending.
|
||||
triggerIntersection();
|
||||
@ -274,62 +258,79 @@ describe("ChatTab lazy history pagination", () => {
|
||||
// Without the inflight guard, each of these would have started a
|
||||
// new fetch. With the guard, none of them do — call count stays 2.
|
||||
await new Promise((r) => setTimeout(r, 10));
|
||||
expect(myChatHistoryCalls.length).toBe(2);
|
||||
expect(myChatActivityCalls.length).toBe(2);
|
||||
|
||||
// Release the first fetch with a valid wire response shape.
|
||||
release({ messages: [], reached_end: true });
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(2));
|
||||
// Release the first fetch. Inflight clears in the finally block;
|
||||
// a subsequent IO trigger is permitted again (verified by checking
|
||||
// we can fire a follow-up after release without hanging the test).
|
||||
release([]);
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(2));
|
||||
});
|
||||
|
||||
it("empty older response clears the scroll anchor and unmounts the sentinel", async () => {
|
||||
myChatNextResponse = {
|
||||
ok: true,
|
||||
messages: pageOldestFirst(1, 10),
|
||||
reachedEnd: false,
|
||||
};
|
||||
// The bug we're pinning: if loadOlder returns 0 rows, the
|
||||
// scrollAnchorRef must be cleared so the next paint doesn't try to
|
||||
// restore against a no-op prepend (which would fight the natural
|
||||
// bottom-pin for any subsequent live message). hasMore flipping to
|
||||
// false is the same flag-flip path; sentinel disappearing is the
|
||||
// observable proxy.
|
||||
myChatNextResponse = { ok: true, rows: newestFirstPage(1, 10) };
|
||||
render(<ChatTab workspaceId="ws-anchor" data={minimalData} />);
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(1));
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(1));
|
||||
await waitFor(() => expect(ioInstances.length).toBeGreaterThan(0));
|
||||
|
||||
myChatNextResponse = {
|
||||
ok: true,
|
||||
messages: [],
|
||||
reachedEnd: true,
|
||||
};
|
||||
myChatNextResponse = { ok: true, rows: [] }; // empty → reachedEnd
|
||||
triggerIntersection();
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(2));
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(2));
|
||||
|
||||
// After reachedEnd the sentinel unmounts (hasMore=false). We can't
|
||||
// peek scrollAnchorRef directly, but we can assert the consequence:
|
||||
// scrollIntoView (the bottom-pin for live appends) is not blocked
|
||||
// by a stale anchor. Trigger a re-render via an unrelated state
|
||||
// change… in practice the safest assertion here is that the
|
||||
// sentinel disappeared (proving the empty response propagated to
|
||||
// hasMore correctly, which is the same flag-flip path as anchor
|
||||
// clearing).
|
||||
await waitFor(() => {
|
||||
expect(screen.queryByText(/Loading older messages/i)).toBeNull();
|
||||
});
|
||||
});
|
||||
|
||||
it("IntersectionObserver does not churn when older messages prepend", async () => {
|
||||
myChatNextResponse = {
|
||||
ok: true,
|
||||
messages: pageOldestFirst(1, 10),
|
||||
reachedEnd: false,
|
||||
};
|
||||
// Whole-PR perf invariant: prepending older history (the load-bearing
|
||||
// user gesture) must NOT tear down + re-arm the IO observer.
|
||||
// Triggering loadOlder is the cleanest way to drive a messages
|
||||
// mutation from inside the test, since live agent push goes through
|
||||
// a Zustand store that's harder to drive reliably from jsdom.
|
||||
//
|
||||
// Pre-fix, loadOlder depended on `messages`, so every prepend
|
||||
// recreated loadOlder → re-ran the IO effect → new observer. Each
|
||||
// call to triggerIntersection() produced a fresh disconnected
|
||||
// observer + a new live one. Post-fix, the observer survives.
|
||||
myChatNextResponse = { ok: true, rows: newestFirstPage(1, 10) };
|
||||
render(<ChatTab workspaceId="ws-stable-io" data={minimalData} />);
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(1));
|
||||
await waitFor(() => expect(myChatActivityCalls.length).toBe(1));
|
||||
await waitFor(() => expect(ioInstances.length).toBeGreaterThan(0));
|
||||
|
||||
// Snapshot the observer instance after first paint stabilises.
|
||||
const observerBefore = ioInstances.at(-1);
|
||||
expect(observerBefore).toBeDefined();
|
||||
expect(observerBefore!.disconnected).toBe(false);
|
||||
|
||||
// Trigger three older-batch prepends. Each batch returns the full
|
||||
// OLDER_HISTORY_BATCH (20 row-pairs = 40 messages) so reachedEnd
|
||||
// stays false and the sentinel keeps mounting.
|
||||
// OLDER_HISTORY_BATCH (20 rows) so reachedEnd stays false and the
|
||||
// sentinel keeps mounting. Pre-fix, each prepend mutated `messages`
|
||||
// → recreated loadOlder → re-ran the IO effect → new observer.
|
||||
for (let batch = 0; batch < 3; batch++) {
|
||||
myChatNextResponse = {
|
||||
ok: true,
|
||||
messages: pageOldestFirst(-(batch + 1) * 20, 20),
|
||||
reachedEnd: false,
|
||||
rows: newestFirstPage(-(batch + 1) * 20, 20),
|
||||
};
|
||||
const callsBefore = myChatHistoryCalls.length;
|
||||
const callsBefore = myChatActivityCalls.length;
|
||||
triggerIntersection();
|
||||
await waitFor(() => expect(myChatHistoryCalls.length).toBe(callsBefore + 1));
|
||||
await waitFor(() =>
|
||||
expect(myChatActivityCalls.length).toBe(callsBefore + 1),
|
||||
);
|
||||
}
|
||||
|
||||
// The original observer is still the live one — no churn.
|
||||
|
||||
@ -9,7 +9,6 @@
|
||||
// AttachmentLightbox).
|
||||
|
||||
import { useState, useEffect, useRef } from "react";
|
||||
import { platformAuthHeaders } from "@/lib/api";
|
||||
import type { ChatAttachment } from "./types";
|
||||
import { isPlatformAttachment, resolveAttachmentHref } from "./uploads";
|
||||
import { AttachmentChip } from "./AttachmentViews";
|
||||
@ -44,8 +43,13 @@ export function AttachmentAudio({ workspaceId, attachment, onDownload, tone }: P
|
||||
void (async () => {
|
||||
try {
|
||||
const href = resolveAttachmentHref(workspaceId, attachment.uri);
|
||||
const headers: Record<string, string> = {};
|
||||
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
|
||||
const slug = getTenantSlug();
|
||||
if (slug) headers["X-Molecule-Org-Slug"] = slug;
|
||||
const res = await fetch(href, {
|
||||
headers: platformAuthHeaders(),
|
||||
headers,
|
||||
credentials: "include",
|
||||
signal: AbortSignal.timeout(60_000),
|
||||
});
|
||||
@ -112,5 +116,9 @@ export function AttachmentAudio({ workspaceId, attachment, onDownload, tone }: P
|
||||
);
|
||||
}
|
||||
|
||||
// Local getTenantSlug() removed — auth-header construction now goes
|
||||
// through platformAuthHeaders() from @/lib/api (#178).
|
||||
function getTenantSlug(): string | null {
|
||||
if (typeof window === "undefined") return null;
|
||||
const host = window.location.hostname;
|
||||
const m = host.match(/^([^.]+)\.moleculesai\.app$/);
|
||||
return m ? m[1] : null;
|
||||
}
|
||||
|
||||
@ -35,7 +35,6 @@
|
||||
// downscale via canvas, but defer that to v2.
|
||||
|
||||
import { useState, useEffect, useRef } from "react";
|
||||
import { platformAuthHeaders } from "@/lib/api";
|
||||
import type { ChatAttachment } from "./types";
|
||||
import { isPlatformAttachment, resolveAttachmentHref } from "./uploads";
|
||||
import { AttachmentLightbox } from "./AttachmentLightbox";
|
||||
@ -76,14 +75,22 @@ export function AttachmentImage({ workspaceId, attachment, onDownload, tone }: P
|
||||
}
|
||||
|
||||
// Platform-auth path: identical to downloadChatFile but we keep
|
||||
// the blob (don't trigger a Save-As). Auth headers come from the
|
||||
// shared `platformAuthHeaders()` helper — one source of truth for
|
||||
// every authenticated raw fetch in the canvas (#178).
|
||||
// the blob (don't trigger a Save-As). Use the same headers it does
|
||||
// by going through it indirectly — no, downloadChatFile triggers a
|
||||
// Save-As. Need a separate fetch.
|
||||
void (async () => {
|
||||
try {
|
||||
const href = resolveAttachmentHref(workspaceId, attachment.uri);
|
||||
const headers: Record<string, string> = {};
|
||||
// Read the same env var downloadChatFile reads — single source
|
||||
// of truth would be cleaner; refactor opportunity for PR-2 if
|
||||
// we add the same path to AttachmentVideo.
|
||||
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
|
||||
const slug = getTenantSlug();
|
||||
if (slug) headers["X-Molecule-Org-Slug"] = slug;
|
||||
const res = await fetch(href, {
|
||||
headers: platformAuthHeaders(),
|
||||
headers,
|
||||
credentials: "include",
|
||||
signal: AbortSignal.timeout(30_000),
|
||||
});
|
||||
@ -177,7 +184,15 @@ export function AttachmentImage({ workspaceId, attachment, onDownload, tone }: P
|
||||
);
|
||||
}
|
||||
|
||||
// Local getTenantSlug() removed — auth-header construction now goes
|
||||
// through platformAuthHeaders() from @/lib/api which uses the canonical
|
||||
// getTenantSlug() from @/lib/tenant. This eliminates the duplicate
|
||||
// hostname-regex + the duplicate bearer-token-attach pattern (#178).
|
||||
// Internal helper — duplicated from uploads.ts (it's not exported
|
||||
// there). Kept local so this component doesn't reach into private
|
||||
// surface; if AttachmentVideo / AttachmentPDF in PR-2/PR-3 also need
|
||||
// it, lift to an exported helper at that point (the third-caller
|
||||
// rule).
|
||||
function getTenantSlug(): string | null {
|
||||
if (typeof window === "undefined") return null;
|
||||
const host = window.location.hostname;
|
||||
// Tenant subdomain shape: <slug>.moleculesai.app
|
||||
const m = host.match(/^([^.]+)\.moleculesai\.app$/);
|
||||
return m ? m[1] : null;
|
||||
}
|
||||
|
||||
@ -33,7 +33,6 @@
|
||||
// timeout, swap to chip. Implemented as a 3-second watchdog.
|
||||
|
||||
import { useState, useEffect, useRef } from "react";
|
||||
import { platformAuthHeaders } from "@/lib/api";
|
||||
import type { ChatAttachment } from "./types";
|
||||
import { isPlatformAttachment, resolveAttachmentHref } from "./uploads";
|
||||
import { AttachmentLightbox } from "./AttachmentLightbox";
|
||||
@ -70,8 +69,13 @@ export function AttachmentPDF({ workspaceId, attachment, onDownload, tone }: Pro
|
||||
void (async () => {
|
||||
try {
|
||||
const href = resolveAttachmentHref(workspaceId, attachment.uri);
|
||||
const headers: Record<string, string> = {};
|
||||
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
|
||||
const slug = getTenantSlug();
|
||||
if (slug) headers["X-Molecule-Org-Slug"] = slug;
|
||||
const res = await fetch(href, {
|
||||
headers: platformAuthHeaders(),
|
||||
headers,
|
||||
credentials: "include",
|
||||
signal: AbortSignal.timeout(60_000),
|
||||
});
|
||||
@ -185,5 +189,9 @@ function PdfGlyph() {
|
||||
);
|
||||
}
|
||||
|
||||
// Local getTenantSlug() removed — auth-header construction now goes
|
||||
// through platformAuthHeaders() from @/lib/api (#178).
|
||||
function getTenantSlug(): string | null {
|
||||
if (typeof window === "undefined") return null;
|
||||
const host = window.location.hostname;
|
||||
const m = host.match(/^([^.]+)\.moleculesai\.app$/);
|
||||
return m ? m[1] : null;
|
||||
}
|
||||
|
||||
@ -26,7 +26,6 @@
|
||||
// to download the full file.
|
||||
|
||||
import { useState, useEffect } from "react";
|
||||
import { platformAuthHeaders } from "@/lib/api";
|
||||
import type { ChatAttachment } from "./types";
|
||||
import { isPlatformAttachment, resolveAttachmentHref } from "./uploads";
|
||||
import { AttachmentChip } from "./AttachmentViews";
|
||||
@ -58,13 +57,13 @@ export function AttachmentTextPreview({ workspaceId, attachment, onDownload, ton
|
||||
void (async () => {
|
||||
try {
|
||||
const href = resolveAttachmentHref(workspaceId, attachment.uri);
|
||||
// Only attach platform auth headers for in-platform URIs —
|
||||
// off-platform URLs (HTTP/HTTPS attachments) MUST NOT receive
|
||||
// our bearer token (it would leak the admin token to a third
|
||||
// party). The branch is preserved with the new shared helper.
|
||||
const headers: Record<string, string> = isPlatformAttachment(attachment.uri)
|
||||
? platformAuthHeaders()
|
||||
: {};
|
||||
const headers: Record<string, string> = {};
|
||||
if (isPlatformAttachment(attachment.uri)) {
|
||||
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
|
||||
const slug = getTenantSlug();
|
||||
if (slug) headers["X-Molecule-Org-Slug"] = slug;
|
||||
}
|
||||
const res = await fetch(href, {
|
||||
headers,
|
||||
credentials: "include",
|
||||
@ -183,5 +182,9 @@ export function AttachmentTextPreview({ workspaceId, attachment, onDownload, ton
|
||||
);
|
||||
}
|
||||
|
||||
// Local getTenantSlug() removed — auth-header construction now goes
|
||||
// through platformAuthHeaders() from @/lib/api (#178).
|
||||
function getTenantSlug(): string | null {
|
||||
if (typeof window === "undefined") return null;
|
||||
const host = window.location.hostname;
|
||||
const m = host.match(/^([^.]+)\.moleculesai\.app$/);
|
||||
return m ? m[1] : null;
|
||||
}
|
||||
|
||||
@ -25,7 +25,6 @@
|
||||
// fetch via service worker. v2 if measured-needed.
|
||||
|
||||
import { useState, useEffect, useRef } from "react";
|
||||
import { platformAuthHeaders } from "@/lib/api";
|
||||
import type { ChatAttachment } from "./types";
|
||||
import { isPlatformAttachment, resolveAttachmentHref } from "./uploads";
|
||||
import { AttachmentChip } from "./AttachmentViews";
|
||||
@ -62,8 +61,13 @@ export function AttachmentVideo({ workspaceId, attachment, onDownload, tone }: P
|
||||
void (async () => {
|
||||
try {
|
||||
const href = resolveAttachmentHref(workspaceId, attachment.uri);
|
||||
const headers: Record<string, string> = {};
|
||||
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
|
||||
const slug = getTenantSlug();
|
||||
if (slug) headers["X-Molecule-Org-Slug"] = slug;
|
||||
const res = await fetch(href, {
|
||||
headers: platformAuthHeaders(),
|
||||
headers,
|
||||
credentials: "include",
|
||||
// Videos are larger than images on average; give the request
|
||||
// more headroom. The server's per-request body cap (50MB) is
|
||||
@ -143,5 +147,11 @@ export function AttachmentVideo({ workspaceId, attachment, onDownload, tone }: P
|
||||
);
|
||||
}
|
||||
|
||||
// Local getTenantSlug() removed — auth-header construction now goes
|
||||
// through platformAuthHeaders() from @/lib/api (#178).
|
||||
// Internal helper — same shape as AttachmentImage's. Lifted to a
|
||||
// shared util in PR-2.5 if a third caller needs it (PDF, audio).
|
||||
function getTenantSlug(): string | null {
|
||||
if (typeof window === "undefined") return null;
|
||||
const host = window.location.hostname;
|
||||
const m = host.match(/^([^.]+)\.moleculesai\.app$/);
|
||||
return m ? m[1] : null;
|
||||
}
|
||||
|
||||
@ -1,16 +1,12 @@
|
||||
import { PLATFORM_URL, platformAuthHeaders } from "@/lib/api";
|
||||
import { PLATFORM_URL } from "@/lib/api";
|
||||
import { getTenantSlug } from "@/lib/tenant";
|
||||
import type { ChatAttachment } from "./types";
|
||||
|
||||
/** Chat attachments are intentionally uploaded via a direct fetch()
|
||||
* instead of the `api.post` helper — `api.post` JSON-stringifies the
|
||||
* body, which would 500 on a Blob. Auth headers (tenant slug, admin
|
||||
* token, credentials) come from `platformAuthHeaders()` — the same
|
||||
* helper `request()` uses, so a missing bearer surfaces as a single
|
||||
* fix site instead of N copies. We deliberately do NOT set
|
||||
* Content-Type so the browser writes the multipart boundary into the
|
||||
* header; setting it manually would yield a multipart body the server
|
||||
* can't parse. See lib/api.ts platformAuthHeaders() for the full
|
||||
* rationale on why this pair must stay matched. */
|
||||
* body, which would 500 on a Blob. Mirrors the header plumbing
|
||||
* (tenant slug, admin token, credentials) so SaaS + self-hosted
|
||||
* callers work the same way. */
|
||||
export async function uploadChatFiles(
|
||||
workspaceId: string,
|
||||
files: File[],
|
||||
@ -20,12 +16,18 @@ export async function uploadChatFiles(
|
||||
const form = new FormData();
|
||||
for (const f of files) form.append("files", f, f.name);
|
||||
|
||||
const headers: Record<string, string> = {};
|
||||
const slug = getTenantSlug();
|
||||
if (slug) headers["X-Molecule-Org-Slug"] = slug;
|
||||
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
|
||||
|
||||
// Uploads legitimately take a while on cold cache (tar write +
|
||||
// docker cp into the container). 60s is comfortable for the 25MB/
|
||||
// 50MB caps the server enforces.
|
||||
const res = await fetch(`${PLATFORM_URL}/workspaces/${workspaceId}/chat/uploads`, {
|
||||
method: "POST",
|
||||
headers: platformAuthHeaders(),
|
||||
headers,
|
||||
body: form,
|
||||
credentials: "include",
|
||||
signal: AbortSignal.timeout(60_000),
|
||||
@ -141,8 +143,14 @@ export async function downloadChatFile(
|
||||
return;
|
||||
}
|
||||
|
||||
const headers: Record<string, string> = {};
|
||||
const slug = getTenantSlug();
|
||||
if (slug) headers["X-Molecule-Org-Slug"] = slug;
|
||||
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
|
||||
|
||||
const res = await fetch(href, {
|
||||
headers: platformAuthHeaders(),
|
||||
headers,
|
||||
credentials: "include",
|
||||
signal: AbortSignal.timeout(60_000),
|
||||
});
|
||||
|
||||
@ -1,130 +0,0 @@
|
||||
// @vitest-environment node
|
||||
import { describe, it, expect, beforeEach, afterEach, vi } from "vitest";
|
||||
|
||||
// Tests for the boot-time matched-pair guard added to next.config.ts.
|
||||
//
|
||||
// Why this lives in src/lib/__tests__ even though the function is in
|
||||
// canvas/next.config.ts:
|
||||
// - next.config.ts runs as ESM-but-also-CJS depending on which
|
||||
// consumer loads it (Next.js dev server vs Next.js build); we
|
||||
// want the test to be a plain ESM module Vitest already handles.
|
||||
// - Importing from "../../../next.config" pulls in the rest of the
|
||||
// file (loadMonorepoEnv, the default export, etc.) which has
|
||||
// side effects on module load (it runs loadMonorepoEnv()
|
||||
// immediately). To keep the test hermetic we don't import — we
|
||||
// duplicate the function under test.
|
||||
//
|
||||
// Sourcing the function from a shared module would be cleaner, but
|
||||
// next.config.ts is required to be a single self-contained file by
|
||||
// Next.js's loader on some host configurations. Pin invariant: the
|
||||
// duplicated function below MUST stay byte-identical to the one in
|
||||
// next.config.ts. If you change one, change the other and bump this
|
||||
// comment.
|
||||
|
||||
function checkAdminTokenPair(): void {
|
||||
const serverSet = !!process.env.ADMIN_TOKEN;
|
||||
const clientSet = !!process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
if (serverSet === clientSet) return;
|
||||
if (serverSet && !clientSet) {
|
||||
// eslint-disable-next-line no-console
|
||||
console.error(
|
||||
"[next.config] ADMIN_TOKEN is set but NEXT_PUBLIC_ADMIN_TOKEN is not — " +
|
||||
"canvas will 401 against workspace-server because the bearer header " +
|
||||
"is never attached. Set both to the same value, or unset both.",
|
||||
);
|
||||
} else {
|
||||
// eslint-disable-next-line no-console
|
||||
console.error(
|
||||
"[next.config] NEXT_PUBLIC_ADMIN_TOKEN is set but ADMIN_TOKEN is not — " +
|
||||
"workspace-server will reject the bearer because no AdminAuth gate " +
|
||||
"is configured. Set both to the same value, or unset both.",
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
describe("checkAdminTokenPair", () => {
|
||||
// Snapshot env so individual tests can stomp on it without leaking.
|
||||
// Rebuild from snapshot in afterEach so the next test sees a known
|
||||
// baseline regardless of mutation pattern.
|
||||
let originalEnv: Record<string, string | undefined>;
|
||||
let errorSpy: ReturnType<typeof vi.spyOn>;
|
||||
|
||||
beforeEach(() => {
|
||||
originalEnv = {
|
||||
ADMIN_TOKEN: process.env.ADMIN_TOKEN,
|
||||
NEXT_PUBLIC_ADMIN_TOKEN: process.env.NEXT_PUBLIC_ADMIN_TOKEN,
|
||||
};
|
||||
delete process.env.ADMIN_TOKEN;
|
||||
delete process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
errorSpy = vi.spyOn(console, "error").mockImplementation(() => {});
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
if (originalEnv.ADMIN_TOKEN === undefined) delete process.env.ADMIN_TOKEN;
|
||||
else process.env.ADMIN_TOKEN = originalEnv.ADMIN_TOKEN;
|
||||
if (originalEnv.NEXT_PUBLIC_ADMIN_TOKEN === undefined) delete process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
else process.env.NEXT_PUBLIC_ADMIN_TOKEN = originalEnv.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
errorSpy.mockRestore();
|
||||
});
|
||||
|
||||
it("emits no warning when both are unset", () => {
|
||||
checkAdminTokenPair();
|
||||
expect(errorSpy).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("emits no warning when both are set (matched pair, the happy path)", () => {
|
||||
process.env.ADMIN_TOKEN = "local-dev-admin";
|
||||
process.env.NEXT_PUBLIC_ADMIN_TOKEN = "local-dev-admin";
|
||||
checkAdminTokenPair();
|
||||
expect(errorSpy).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("warns when ADMIN_TOKEN is set but NEXT_PUBLIC_ADMIN_TOKEN is not", () => {
|
||||
process.env.ADMIN_TOKEN = "local-dev-admin";
|
||||
checkAdminTokenPair();
|
||||
expect(errorSpy).toHaveBeenCalledTimes(1);
|
||||
// Exact-string assertion — substring would also pass when the
|
||||
// function's branch logic is broken (e.g. emits both messages, or
|
||||
// emits the wrong one). Pin the exact message that operators will
|
||||
// see in their dev console so regressions are visible.
|
||||
expect(errorSpy).toHaveBeenCalledWith(
|
||||
"[next.config] ADMIN_TOKEN is set but NEXT_PUBLIC_ADMIN_TOKEN is not — " +
|
||||
"canvas will 401 against workspace-server because the bearer header " +
|
||||
"is never attached. Set both to the same value, or unset both.",
|
||||
);
|
||||
});
|
||||
|
||||
it("warns when NEXT_PUBLIC_ADMIN_TOKEN is set but ADMIN_TOKEN is not", () => {
|
||||
process.env.NEXT_PUBLIC_ADMIN_TOKEN = "local-dev-admin";
|
||||
checkAdminTokenPair();
|
||||
expect(errorSpy).toHaveBeenCalledTimes(1);
|
||||
expect(errorSpy).toHaveBeenCalledWith(
|
||||
"[next.config] NEXT_PUBLIC_ADMIN_TOKEN is set but ADMIN_TOKEN is not — " +
|
||||
"workspace-server will reject the bearer because no AdminAuth gate " +
|
||||
"is configured. Set both to the same value, or unset both.",
|
||||
);
|
||||
});
|
||||
|
||||
// Empty string in process.env is the JS-side representation of `KEY=`
|
||||
// (no value) in a .env file. Treating "" as unset makes the pair
|
||||
// invariant symmetric: `KEY=` and `unset KEY` produce the same
|
||||
// verdict. Without this branch, an operator who comments out the
|
||||
// value but leaves the line would get a false-positive warning.
|
||||
it("treats empty string as unset (so KEY= and unset KEY are equivalent)", () => {
|
||||
process.env.ADMIN_TOKEN = "";
|
||||
process.env.NEXT_PUBLIC_ADMIN_TOKEN = "";
|
||||
checkAdminTokenPair();
|
||||
expect(errorSpy).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("warns when ADMIN_TOKEN is set and NEXT_PUBLIC_ADMIN_TOKEN is empty string", () => {
|
||||
process.env.ADMIN_TOKEN = "local-dev-admin";
|
||||
process.env.NEXT_PUBLIC_ADMIN_TOKEN = "";
|
||||
checkAdminTokenPair();
|
||||
expect(errorSpy).toHaveBeenCalledTimes(1);
|
||||
// First branch — server set, client unset.
|
||||
expect(errorSpy).toHaveBeenCalledWith(
|
||||
expect.stringContaining("ADMIN_TOKEN is set but NEXT_PUBLIC_ADMIN_TOKEN is not"),
|
||||
);
|
||||
});
|
||||
});
|
||||
@ -1,97 +0,0 @@
|
||||
// @vitest-environment jsdom
|
||||
import { describe, it, expect, beforeEach, afterEach, vi } from "vitest";
|
||||
|
||||
// Tests for platformAuthHeaders — the shared helper extracted in #178
|
||||
// to consolidate the bearer-token-attach + tenant-slug-attach pattern
|
||||
// that was previously duplicated across 7 raw-fetch callsites in the
|
||||
// canvas (uploads + 5 Attachment* components + the api.ts request()
|
||||
// function).
|
||||
//
|
||||
// What we pin here:
|
||||
// - Returns a fresh object each call (so callers can mutate without
|
||||
// leaking into each other).
|
||||
// - Empty result on a non-tenant host with no admin token (the
|
||||
// localhost / self-hosted shape).
|
||||
// - Bearer attached when NEXT_PUBLIC_ADMIN_TOKEN is set.
|
||||
// - X-Molecule-Org-Slug attached when window.location.hostname is a
|
||||
// tenant subdomain (<slug>.moleculesai.app).
|
||||
// - Both attached when both apply (the production SaaS shape).
|
||||
//
|
||||
// Why jsdom: getTenantSlug() reads window.location.hostname. Node-only
|
||||
// environment yields no window and getTenantSlug returns null
|
||||
// unconditionally — wouldn't exercise the slug branch.
|
||||
|
||||
import { platformAuthHeaders } from "../api";
|
||||
|
||||
describe("platformAuthHeaders", () => {
|
||||
let originalAdminToken: string | undefined;
|
||||
|
||||
beforeEach(() => {
|
||||
originalAdminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
delete process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
if (originalAdminToken === undefined) delete process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
else process.env.NEXT_PUBLIC_ADMIN_TOKEN = originalAdminToken;
|
||||
// jsdom resets hostname between tests via the @vitest-environment
|
||||
// pragma's per-test isolation. No explicit reset needed.
|
||||
});
|
||||
|
||||
it("returns an empty object on a non-tenant host with no admin token", () => {
|
||||
// jsdom default hostname is "localhost" — not a tenant slug, so
|
||||
// getTenantSlug() returns null and no X-Molecule-Org-Slug is added.
|
||||
const headers = platformAuthHeaders();
|
||||
expect(headers).toEqual({});
|
||||
});
|
||||
|
||||
it("attaches Authorization when NEXT_PUBLIC_ADMIN_TOKEN is set", () => {
|
||||
process.env.NEXT_PUBLIC_ADMIN_TOKEN = "local-dev-admin";
|
||||
const headers = platformAuthHeaders();
|
||||
expect(headers).toEqual({ Authorization: "Bearer local-dev-admin" });
|
||||
});
|
||||
|
||||
it("does NOT attach Authorization when NEXT_PUBLIC_ADMIN_TOKEN is empty string", () => {
|
||||
// Empty-string env is the JS-side shape of `KEY=` in .env.
|
||||
// Treating it as unset matches the matched-pair guard in
|
||||
// next.config.ts (admin-token-pair.test.ts) — symmetric semantics.
|
||||
process.env.NEXT_PUBLIC_ADMIN_TOKEN = "";
|
||||
const headers = platformAuthHeaders();
|
||||
expect(headers).toEqual({});
|
||||
});
|
||||
|
||||
it("attaches X-Molecule-Org-Slug on a tenant subdomain", () => {
|
||||
Object.defineProperty(window, "location", {
|
||||
value: { hostname: "reno-stars.moleculesai.app" },
|
||||
writable: true,
|
||||
});
|
||||
const headers = platformAuthHeaders();
|
||||
expect(headers).toEqual({ "X-Molecule-Org-Slug": "reno-stars" });
|
||||
});
|
||||
|
||||
it("attaches both when both apply (production SaaS shape)", () => {
|
||||
Object.defineProperty(window, "location", {
|
||||
value: { hostname: "reno-stars.moleculesai.app" },
|
||||
writable: true,
|
||||
});
|
||||
process.env.NEXT_PUBLIC_ADMIN_TOKEN = "tenant-bearer";
|
||||
const headers = platformAuthHeaders();
|
||||
// Pin exact-equality on the full shape — substring/contains
|
||||
// assertions would also pass for an extra-header bug.
|
||||
expect(headers).toEqual({
|
||||
"X-Molecule-Org-Slug": "reno-stars",
|
||||
Authorization: "Bearer tenant-bearer",
|
||||
});
|
||||
});
|
||||
|
||||
it("returns a fresh object each call (callers can mutate safely)", () => {
|
||||
process.env.NEXT_PUBLIC_ADMIN_TOKEN = "tok";
|
||||
const a = platformAuthHeaders();
|
||||
const b = platformAuthHeaders();
|
||||
expect(a).not.toBe(b); // distinct refs
|
||||
expect(a).toEqual(b); // same content
|
||||
a["Content-Type"] = "application/json";
|
||||
// Mutation on `a` does not leak into `b`.
|
||||
expect(b["Content-Type"]).toBeUndefined();
|
||||
});
|
||||
});
|
||||
@ -21,45 +21,6 @@ export interface RequestOptions {
|
||||
timeoutMs?: number;
|
||||
}
|
||||
|
||||
/**
|
||||
* Build the platform auth header set used by every authenticated fetch
|
||||
* from the canvas. Returns a fresh object so callers can mutate (e.g.
|
||||
* append `Content-Type` for JSON requests, omit it for FormData).
|
||||
*
|
||||
* SaaS cross-origin shape:
|
||||
* - `X-Molecule-Org-Slug` — derived from `window.location.hostname`
|
||||
* by `getTenantSlug()`. Control plane uses it for fly-replay
|
||||
* routing. Empty on localhost / non-tenant hosts — safe to omit.
|
||||
* - `Authorization: Bearer <token>` — `NEXT_PUBLIC_ADMIN_TOKEN` baked
|
||||
* into the canvas build (see canvas/Dockerfile L8/L11). Required by
|
||||
* the workspace-server when `ADMIN_TOKEN` is set on the server side
|
||||
* (Tier-2b AdminAuth gate, wsauth_middleware.go ~L245). Empty when
|
||||
* no admin token was provisioned — the Tier-1 session-cookie path
|
||||
* handles that case via `credentials:"include"`.
|
||||
*
|
||||
* Why a shared helper: the two-line "read env, attach bearer; read
|
||||
* slug, attach header" pattern was duplicated across `request()` and
|
||||
* 7 raw-fetch callsites (chat uploads/download + 5 Attachment*
|
||||
* components) before this consolidation. A new poller or raw fetch
|
||||
* that forgets one of the two headers silently 401s against
|
||||
* workspace-server when ADMIN_TOKEN is set — the exact bug shape
|
||||
* called out in #178 / closes the post-#176 self-review gap.
|
||||
*
|
||||
* Callers that want JSON Content-Type should spread this and add it
|
||||
* themselves; FormData callers should NOT add Content-Type (the
|
||||
* browser sets the multipart boundary). Centralizing the auth pair
|
||||
* but leaving Content-Type up to the caller is the minimum viable
|
||||
* shared shape.
|
||||
*/
|
||||
export function platformAuthHeaders(): Record<string, string> {
|
||||
const headers: Record<string, string> = {};
|
||||
const slug = getTenantSlug();
|
||||
if (slug) headers["X-Molecule-Org-Slug"] = slug;
|
||||
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
|
||||
return headers;
|
||||
}
|
||||
|
||||
async function request<T>(
|
||||
method: string,
|
||||
path: string,
|
||||
@ -67,16 +28,17 @@ async function request<T>(
|
||||
retryCount = 0,
|
||||
options?: RequestOptions,
|
||||
): Promise<T> {
|
||||
// JSON-bodied request — Content-Type is JSON. Auth pair comes from
|
||||
// the shared helper; see its doc comment for the SaaS-shape rationale.
|
||||
const headers: Record<string, string> = {
|
||||
"Content-Type": "application/json",
|
||||
...platformAuthHeaders(),
|
||||
};
|
||||
// Re-read slug locally for the 401 handler below — `headers` already
|
||||
// has it, but the 401 branch needs the bare value to gate the
|
||||
// session-probe + redirect logic on tenant context.
|
||||
// SaaS cross-origin shape:
|
||||
// - X-Molecule-Org-Slug: derived from window.location.hostname by
|
||||
// getTenantSlug(). Control plane uses it for fly-replay routing.
|
||||
// Empty on localhost / non-tenant hosts — safe to omit.
|
||||
// - credentials:"include": sends the session cookie cross-origin.
|
||||
// Cookie's Domain=.moleculesai.app attribute + cp's CORS allow this.
|
||||
const headers: Record<string, string> = { "Content-Type": "application/json" };
|
||||
const slug = getTenantSlug();
|
||||
if (slug) headers["X-Molecule-Org-Slug"] = slug;
|
||||
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
|
||||
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
|
||||
|
||||
const res = await fetch(`${PLATFORM_URL}${path}`, {
|
||||
method,
|
||||
|
||||
@ -7,32 +7,6 @@ export default defineConfig({
|
||||
test: {
|
||||
environment: 'node',
|
||||
exclude: ['e2e/**', 'node_modules/**', '**/dist/**'],
|
||||
// CI-conditional test timeout (issue #96).
|
||||
//
|
||||
// Vitest's 5000ms default is too tight for the first test in any
|
||||
// file under our CI shape: `npx vitest run --coverage` on the
|
||||
// self-hosted Gitea Actions Docker runner. The cold-start cost
|
||||
// (v8 coverage instrumentation init + JSDOM bootstrap + module-
|
||||
// graph import for @/components/* and @/lib/* + first React
|
||||
// render) consistently consumes 5-7 seconds for the first
|
||||
// synchronous test in heavyweight component files
|
||||
// (ActivityTab.test.tsx, CreateWorkspaceDialog.test.tsx,
|
||||
// ConfigTab.provider.test.tsx) — even though every subsequent
|
||||
// test in the same file completes in 100-1500ms.
|
||||
//
|
||||
// Empirically the worst observed first-test was 6453ms in a
|
||||
// single file (CreateWorkspaceDialog). 30000ms gives ~5x
|
||||
// headroom over that on CI; we still keep 5000ms locally so
|
||||
// genuine waitFor races / hung promises stay sensitive in dev.
|
||||
//
|
||||
// Same vitest pattern documented at:
|
||||
// https://vitest.dev/config/testtimeout
|
||||
// https://vitest.dev/guide/coverage#profiling-test-performance
|
||||
//
|
||||
// Per-test duration is still emitted to the CI log; if a test
|
||||
// ever silently approaches 25-30s under this raised ceiling that
|
||||
// will surface as a duration regression and we revisit.
|
||||
testTimeout: process.env.CI ? 30000 : 5000,
|
||||
// Coverage is instrumented but NOT yet a CI gate — first land
|
||||
// observability so we can see the baseline, then dial in
|
||||
// thresholds + a hard gate in a follow-up PR (#1815). Today's
|
||||
|
||||
@ -1,43 +0,0 @@
|
||||
# docker-compose.dev.yml — overlay over docker-compose.yml for local dev
|
||||
# with air-driven live reload of the platform (workspace-server) service.
|
||||
#
|
||||
# Usage:
|
||||
# docker compose -f docker-compose.yml -f docker-compose.dev.yml up
|
||||
# (or `make dev` shorthand from repo root)
|
||||
#
|
||||
# What this overlay changes vs docker-compose.yml alone:
|
||||
# - Platform service uses workspace-server/Dockerfile.dev (air on top of
|
||||
# golang:1.25-alpine) instead of the multi-stage prod Dockerfile.
|
||||
# - Platform service bind-mounts the host's workspace-server/ source
|
||||
# into /app/workspace-server so air sees source edits live.
|
||||
# - Other services (postgres, redis, langfuse, etc.) inherit unchanged
|
||||
# from docker-compose.yml.
|
||||
#
|
||||
# What stays the same:
|
||||
# - All env vars, volumes, depends_on, healthchecks from docker-compose.yml.
|
||||
# - Network topology + ports.
|
||||
# - Postgres/Redis as service containers (no in-process replacements).
|
||||
|
||||
services:
|
||||
platform:
|
||||
build:
|
||||
context: .
|
||||
dockerfile: workspace-server/Dockerfile.dev
|
||||
# Rebind source: edits under host's workspace-server/ propagate live.
|
||||
# The named volume on go-build-cache speeds up first build per container.
|
||||
volumes:
|
||||
- ./workspace-server:/app/workspace-server
|
||||
- go-build-cache:/root/.cache/go-build
|
||||
- go-mod-cache:/go/pkg/mod
|
||||
# Air signals the running binary on rebuild; ensure shell stops cleanly.
|
||||
init: true
|
||||
# Mark the service as dev-mode so the platform can short-circuit any
|
||||
# behavior that's incompatible with hot-reload (e.g. background
|
||||
# cron-style watchers that don't survive process restart). No-op
|
||||
# today; reserved for future flag use.
|
||||
environment:
|
||||
MOLECULE_DEV_HOT_RELOAD: "1"
|
||||
|
||||
volumes:
|
||||
go-build-cache:
|
||||
go-mod-cache:
|
||||
@ -13,7 +13,6 @@ services:
|
||||
- pgdata:/var/lib/postgresql/data
|
||||
networks:
|
||||
- molecule-monorepo-net
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-dev}"]
|
||||
interval: 2s
|
||||
@ -51,7 +50,6 @@ services:
|
||||
- redisdata:/data
|
||||
networks:
|
||||
- molecule-monorepo-net
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
test: ["CMD", "redis-cli", "ping"]
|
||||
interval: 2s
|
||||
@ -128,10 +126,6 @@ services:
|
||||
REDIS_URL: redis://redis:6379
|
||||
PORT: "${PLATFORM_PORT:-8080}"
|
||||
PLATFORM_URL: "http://platform:${PLATFORM_PORT:-8080}"
|
||||
# Container network namespace is already isolated; "all interfaces"
|
||||
# inside the container = the bridge interface only. The fail-open
|
||||
# default (127.0.0.1) would block host-to-container access.
|
||||
BIND_ADDR: "${BIND_ADDR:-0.0.0.0}"
|
||||
# Default MOLECULE_ENV=development so the WorkspaceAuth / AdminAuth
|
||||
# middleware fail-open path activates when ADMIN_TOKEN is unset —
|
||||
# otherwise the canvas (which runs without a bearer in pure local
|
||||
@ -201,28 +195,12 @@ services:
|
||||
# App private key — read-only bind-mount. The host-side path is
|
||||
# gitignored per .gitignore rules (/.secrets/ + *.pem).
|
||||
- ./.secrets/github-app.pem:/secrets/github-app.pem:ro
|
||||
# Per-role persona credentials (molecule-core#242 local surface).
|
||||
# Sourced at workspace creation time by org_import.go::loadPersonaEnvFile
|
||||
# when a workspace.yaml carries `role: <name>`. The host-side dir is
|
||||
# populated by the operator-host bootstrap kit (28 dev-tree personas);
|
||||
# /etc/molecule-bootstrap/personas is the in-container path the
|
||||
# platform expects (matches the prod tenant-EC2 path so the same code
|
||||
# works in both modes).
|
||||
#
|
||||
# Read-only mount — workspace-server only reads, never writes here.
|
||||
# If the host dir is empty/missing the platform's loadPersonaEnvFile
|
||||
# silently no-ops per its existing semantics, so this mount is safe
|
||||
# even on a fresh machine that hasn't run the bootstrap kit yet.
|
||||
- ${MOLECULE_PERSONA_ROOT_HOST:-${HOME}/.molecule-ai/personas}:/etc/molecule-bootstrap/personas:ro
|
||||
ports:
|
||||
- "${PLATFORM_PUBLISH_PORT:-8080}:${PLATFORM_PORT:-8080}"
|
||||
networks:
|
||||
- molecule-monorepo-net
|
||||
restart: unless-stopped
|
||||
healthcheck:
|
||||
# Plain GET — `--spider` would issue HEAD, which returns 404 because
|
||||
# /health is registered as GET only.
|
||||
test: ["CMD-SHELL", "wget -qO /dev/null --tries=1 http://localhost:${PLATFORM_PORT:-8080}/health || exit 1"]
|
||||
test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:${PLATFORM_PORT:-8080}/health || exit 1"]
|
||||
interval: 5s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
@ -234,8 +212,8 @@ services:
|
||||
# docker compose pull canvas && docker compose up -d canvas
|
||||
# First-time local setup or testing unreleased changes — build from source:
|
||||
# docker compose build canvas && docker compose up -d canvas
|
||||
# Note: ECR images require AWS auth — `aws ecr get-login-password --region us-east-2 | docker login --username AWS --password-stdin 153263036946.dkr.ecr.us-east-2.amazonaws.com` before pull.
|
||||
image: 153263036946.dkr.ecr.us-east-2.amazonaws.com/molecule-ai/canvas:latest
|
||||
# Note: GHCR images are private — `docker login ghcr.io` required before pull.
|
||||
image: ghcr.io/molecule-ai/canvas:latest
|
||||
build:
|
||||
context: ./canvas
|
||||
dockerfile: Dockerfile
|
||||
@ -260,7 +238,7 @@ services:
|
||||
networks:
|
||||
- molecule-monorepo-net
|
||||
healthcheck:
|
||||
test: ["CMD-SHELL", "wget -qO /dev/null --tries=1 http://127.0.0.1:${CANVAS_PORT:-3000} || exit 1"]
|
||||
test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://127.0.0.1:${CANVAS_PORT:-3000} || exit 1"]
|
||||
interval: 10s
|
||||
timeout: 5s
|
||||
retries: 10
|
||||
|
||||
@ -1,74 +0,0 @@
|
||||
# ADR-002: Local-build mode signalled by `MOLECULE_IMAGE_REGISTRY` presence
|
||||
|
||||
* Status: Accepted (2026-05-07)
|
||||
* Issue: #63 (closes Task #194)
|
||||
* Decision: Hongming (CTO) + Claude Opus 4.7 (implementation)
|
||||
|
||||
## Context
|
||||
|
||||
Pre-2026-05-06, every Molecule deployment — both production tenants and OSS contributor laptops — pulled workspace-template-* container images from `ghcr.io/molecule-ai/`. Production tenants additionally set `MOLECULE_IMAGE_REGISTRY` to an AWS ECR mirror via Railway env / EC2 user-data, but the OSS default was the upstream GHCR org.
|
||||
|
||||
On 2026-05-06 the `Molecule-AI` GitHub org was suspended (saved memory: `feedback_github_botring_fingerprint`). GHCR now returns **403 Forbidden** for every `molecule-ai/workspace-template-*` manifest. OSS contributors who clone `molecule-core` and run `go run ./workspace-server/cmd/server` cannot provision a workspace — every first provision fails with:
|
||||
|
||||
```
|
||||
docker image "ghcr.io/molecule-ai/workspace-template-claude-code:latest" not found after pull attempt
|
||||
```
|
||||
|
||||
Production tenants are unaffected (their `MOLECULE_IMAGE_REGISTRY` points at ECR, which we still control), but OSS onboarding is broken. Workspace template repos are intentionally separate from `molecule-core` (each runtime is OSS-shape and forkable), and they are mirrored to Gitea (`https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-<runtime>`) — but the provisioner has no path that consumes Gitea source directly.
|
||||
|
||||
## Decision
|
||||
|
||||
When `MOLECULE_IMAGE_REGISTRY` is **unset** (or empty), the provisioner switches to a **local-build mode** that:
|
||||
|
||||
1. Looks up the workspace-template repo's HEAD sha on Gitea via a single API call.
|
||||
2. Checks whether a SHA-pinned local image (`molecule-local/workspace-template-<runtime>:<sha12>`) already exists; if so, reuses it.
|
||||
3. Otherwise shallow-clones the repo into `~/.cache/molecule/workspace-template-build/<runtime>/<sha12>/` and runs `docker build --platform=linux/amd64 -t <tag> .`.
|
||||
4. Hands the SHA-pinned tag to Docker for ContainerCreate, bypassing the registry-pull path entirely.
|
||||
|
||||
When `MOLECULE_IMAGE_REGISTRY` is **set**, behavior is unchanged: pull the image from that registry. Existing prod tenants and self-hosters who mirror to a private registry are not affected.
|
||||
|
||||
## Consequences
|
||||
|
||||
### Positive
|
||||
|
||||
* **Zero-config OSS onboarding** — `git clone molecule-core && go run ./workspace-server/cmd/server` boots end-to-end without any registry credentials.
|
||||
* **Production tenants protected** — same env var, same semantics in SaaS-mode. Migration is a no-op.
|
||||
* **No new env var** — extending an existing var's semantics ("where to pull, OR build locally if absent") rather than introducing `MOLECULE_LOCAL_BUILD=1` keeps the surface small.
|
||||
* **SHA-pinned cache** — repeat builds are O(API-call); only template-repo HEAD changes invalidate.
|
||||
* **Production-parity image** — amd64 emulation on Apple Silicon honours `feedback_local_must_mimic_production`. The provisioner's existing `defaultImagePlatform()` already forces amd64 for parity; building amd64 locally lets that decision stay consistent.
|
||||
|
||||
### Negative
|
||||
|
||||
* **Conflates two concerns** — `MOLECULE_IMAGE_REGISTRY` now signals BOTH "where to pull" AND "build locally if absent." A future operator who unsets it expecting a hard error will instead get a slow first-provision. Documented in the runbook.
|
||||
* **First-provision is slow on Apple Silicon** — 5–10 min via QEMU emulation on the cold path. Mitigated by SHA-cache (subsequent runs are <1s lookup + 0s build).
|
||||
* **Coverage gap** — only 4 of 9 runtimes are mirrored to Gitea today (`claude-code`, `hermes`, `langgraph`, `autogen`). The other 5 fail with an actionable "not mirrored" error. Mirroring those repos is a separate task.
|
||||
* **Implicit trust boundary** — operator running `go run` implicitly trusts `molecule-ai/molecule-ai-workspace-template-*` repos on Gitea. This is the same trust they would extend to the GHCR images today; not a new attack surface.
|
||||
|
||||
## Alternatives considered
|
||||
|
||||
1. **New env var `MOLECULE_LOCAL_BUILD=1`** — explicit, but requires OSS contributors to know it exists. Violates the zero-config goal.
|
||||
2. **Push pre-built images to a Gitea container registry, mirror tag from upstream** — operationally cleaner but: (a) Gitea's container-registry add-on isn't deployed on the operator host, (b) defeats the OSS-contributor goal of "hack on the source, see your changes," since they'd still pull a stale image.
|
||||
3. **Embed Dockerfiles in molecule-core itself, drop the standalone template repos** — would work but breaks the OSS-shape principle; templates are intentionally separable, anyone-can-fork artifacts.
|
||||
4. **Build native arch on Apple Silicon (arm64) and drop the platform pin in local-mode** — fast, but creates `linux/arm64` images that diverge from the amd64-only prod runtime. Local-vs-prod debug behavior would diverge. Rejected per `feedback_local_must_mimic_production`.
|
||||
|
||||
## Security review
|
||||
|
||||
* **Gitea repo URL allowlist** — runtime name must be in the `knownRuntimes` allowlist (defence-in-depth against a future code path that lets cfg.Runtime carry untrusted input). Repo prefix is hardcoded to `https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-`; forks can override via `MOLECULE_LOCAL_TEMPLATE_REPO_PREFIX` (opt-in, default off).
|
||||
* **Token handling** — clones are anonymous over HTTPS by default (templates are public). `MOLECULE_GITEA_TOKEN`, if set, is passed via URL userinfo for the clone and as `Authorization: token` for the API call. The token is **masked in every log line** via `maskTokenInURL` / `maskTokenInString` and never appears in the cache dir path.
|
||||
* **No silent fallback** — if Gitea is unreachable or the runtime isn't mirrored, we return a clear error mentioning the repo URL and the missing runtime. We **never** fall back to GHCR/ECR (that would be a confusing bug for an OSS contributor who happened to have stale ECR creds in their docker config).
|
||||
* **Build-arg injection** — `docker build` is invoked with NO `--build-arg` from external input. Dockerfile is consumed as-is.
|
||||
* **Cache poisoning** — cache key is the Gitea HEAD sha + Dockerfile content; a force-push to the template repo's main branch regenerates the key on next run. Cache dir is per-user (`$HOME/.cache`), so cross-user attacks aren't relevant in single-user dev mode.
|
||||
|
||||
## Versioning + back-compat
|
||||
|
||||
* Existing prod tenants set `MOLECULE_IMAGE_REGISTRY=<ECR url>` → unchanged behavior.
|
||||
* Existing local installs that set the var → unchanged behavior.
|
||||
* Existing local installs that don't set it → switch to local-build path. Migration: none required (additive); first provision will take 5–10 min instead of failing.
|
||||
* No deprecations.
|
||||
|
||||
## References
|
||||
|
||||
* Issue #63 — feat(workspace-server): local-dev provisioner builds from Gitea source
|
||||
* Saved memory `feedback_local_must_mimic_production` — local docker must mimic prod, no bypasses
|
||||
* Saved memory `reference_post_suspension_pipeline` — full post-2026-05-06 stack shape
|
||||
* Saved memory `feedback_github_botring_fingerprint` — what got the org suspended
|
||||
@ -2,7 +2,7 @@
|
||||
|
||||
**Status:** living document — update when you ship a feature that touches one backend.
|
||||
**Owner:** workspace-server + controlplane teams.
|
||||
**Last audit:** 2026-05-07 (plugin install/uninstall closed for EC2 backend via EIC SSH push to the bind-mounted `/configs/plugins/<name>/`, mirroring the Files API PR #1702 pattern).
|
||||
**Last audit:** 2026-05-05 (Claude agent — `provisionWorkspaceAuto` / `StopWorkspaceAuto` / `HasProvisioner` SoT pattern landed in PRs #2811 + #2824).
|
||||
|
||||
## Why this exists
|
||||
|
||||
@ -54,7 +54,7 @@ For "do we have any backend?", use `HasProvisioner()`, never bare `h.provisioner
|
||||
| **Files API** | | | | |
|
||||
| List / Read / Write / Replace / Delete | `container_files.go`, `template_import.go` | `docker exec` + tar `CopyToContainer` | SSH via EIC tunnel (PR #1702) | ✅ parity as of 2026-04-22 (previously docker-only) |
|
||||
| **Plugins** | | | | |
|
||||
| Install / uninstall / list | `plugins_install.go` + `plugins_install_eic.go` | `deliverToContainer()` → exec+`CopyToContainer` on local container | `instance_id` set → EIC SSH push of the staged tarball into the EC2's bind-mounted `/configs/plugins/<name>/` (per `workspaceFilePathPrefix`), `chown 1000:1000`, restart | ✅ parity |
|
||||
| Install / uninstall / list | `plugins_install.go` | `deliverToContainer()` + volume rm | **gap — no live plugin delivery** | 🔴 **docker-only** |
|
||||
| **Terminal (WebSocket)** | | | | |
|
||||
| Dispatch | `terminal.go:90-105` | `instance_id=""` → `handleLocalConnect` → `docker attach` | `instance_id` set → `handleRemoteConnect` → EIC SSH + `docker exec` | ✅ parity (different implementations, same UX) |
|
||||
| **A2A proxy** | | | | |
|
||||
|
||||
@ -4,7 +4,7 @@ How a workspace-server code change reaches the prod tenant fleet — and how to
|
||||
|
||||
> **⚠️ State note (2026-04-22):** this doc describes the **intended design**. As of this write, the canary fleet described below is **not actually running** — no canary tenants are provisioned, `CANARY_TENANT_URLS` / `CANARY_ADMIN_TOKENS` / `CANARY_CP_SHARED_SECRET` are empty in repo secrets, and `canary-verify.yml` fails every run.
|
||||
>
|
||||
> Current merges gate on manual `promote-latest.yml` dispatches, not canary. See [molecule-controlplane/docs/canary-tenants.md](https://git.moleculesai.app/molecule-ai/molecule-controlplane/src/branch/main/docs/canary-tenants.md) for the Phase 1 code work that's already shipped + the Phase 2 plan for actually standing up the fleet + a "should we even do this now?" decision framework.
|
||||
> Current merges gate on manual `promote-latest.yml` dispatches, not canary. See [molecule-controlplane/docs/canary-tenants.md](https://github.com/Molecule-AI/molecule-controlplane/blob/main/docs/canary-tenants.md) for the Phase 1 code work that's already shipped + the Phase 2 plan for actually standing up the fleet + a "should we even do this now?" decision framework.
|
||||
>
|
||||
> **Account-specific identifiers (AWS account ID, IAM role name) referenced below in the original design have been redacted from this public doc.** The actual values — if they exist — are in `Molecule-AI/internal/runbooks/canary-fleet.md`. If you're implementing Phase 2, start there.
|
||||
>
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
# Molecule AI — Comprehensive Technical Documentation
|
||||
|
||||
> Definitive technical reference for the Molecule AI Agent Team platform.
|
||||
> Based on a full non-invasive scan of the [molecule-monorepo](https://git.moleculesai.app/molecule-ai/molecule-monorepo) repository.
|
||||
> Based on a full non-invasive scan of the [molecule-monorepo](https://github.com/Molecule-AI/molecule-monorepo) repository.
|
||||
|
||||
---
|
||||
|
||||
@ -1149,11 +1149,11 @@ Molecule AI's workspace abstraction is **runtime-agnostic by design**. A workspa
|
||||
|
||||
## Links
|
||||
|
||||
- **GitHub**: https://git.moleculesai.app/molecule-ai/molecule-monorepo
|
||||
- **Architecture Docs**: https://git.moleculesai.app/molecule-ai/molecule-monorepo/src/branch/main/docs/architecture
|
||||
- **API Protocol**: https://git.moleculesai.app/molecule-ai/molecule-monorepo/src/branch/main/docs/api-protocol
|
||||
- **Agent Runtime**: https://git.moleculesai.app/molecule-ai/molecule-monorepo/src/branch/main/docs/agent-runtime
|
||||
- **Product Docs**: https://git.moleculesai.app/molecule-ai/molecule-monorepo/src/branch/main/docs/product
|
||||
- **GitHub**: https://github.com/Molecule-AI/molecule-monorepo
|
||||
- **Architecture Docs**: https://github.com/Molecule-AI/molecule-monorepo/tree/main/docs/architecture
|
||||
- **API Protocol**: https://github.com/Molecule-AI/molecule-monorepo/tree/main/docs/api-protocol
|
||||
- **Agent Runtime**: https://github.com/Molecule-AI/molecule-monorepo/tree/main/docs/agent-runtime
|
||||
- **Product Docs**: https://github.com/Molecule-AI/molecule-monorepo/tree/main/docs/product
|
||||
|
||||
---
|
||||
|
||||
|
||||
@ -79,7 +79,7 @@ For SOC2 / ISO 27001 / customer security questionnaires:
|
||||
|
||||
## Pointers
|
||||
|
||||
- KMS envelope code: [`molecule-controlplane/internal/crypto/kms.go`](https://git.moleculesai.app/molecule-ai/molecule-controlplane/src/branch/main/internal/crypto/kms.go)
|
||||
- Static-key fallback: [`molecule-controlplane/internal/crypto/aes.go`](https://git.moleculesai.app/molecule-ai/molecule-controlplane/src/branch/main/internal/crypto/aes.go)
|
||||
- KMS envelope code: [`molecule-controlplane/internal/crypto/kms.go`](https://github.com/Molecule-AI/molecule-controlplane/blob/main/internal/crypto/kms.go)
|
||||
- Static-key fallback: [`molecule-controlplane/internal/crypto/aes.go`](https://github.com/Molecule-AI/molecule-controlplane/blob/main/internal/crypto/aes.go)
|
||||
- Tenant secrets handler: [`workspace-server/internal/crypto/aes.go`](../../workspace-server/internal/crypto/aes.go)
|
||||
- Tenant secrets schema: [database-schema.md](./database-schema.md#workspace_secrets)
|
||||
|
||||
@ -1,28 +0,0 @@
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64">
|
||||
<style>
|
||||
.bg { fill: #0a1120; }
|
||||
.accent { fill: #7fe8d6; }
|
||||
.accent-stroke { stroke: #7fe8d6; }
|
||||
@media (prefers-color-scheme: light) {
|
||||
.bg { fill: #f5f7fa; }
|
||||
.accent { fill: #1a8a72; }
|
||||
.accent-stroke { stroke: #1a8a72; }
|
||||
}
|
||||
</style>
|
||||
<rect class="bg" width="64" height="64" rx="14"/>
|
||||
<g class="accent-stroke" stroke-width="2.4" stroke-linecap="round" fill="none">
|
||||
<line x1="32" y1="32" x2="12" y2="14"/>
|
||||
<line x1="32" y1="32" x2="52" y2="18"/>
|
||||
<line x1="32" y1="32" x2="10" y2="40"/>
|
||||
<line x1="32" y1="32" x2="54" y2="44"/>
|
||||
<line x1="32" y1="32" x2="32" y2="56"/>
|
||||
</g>
|
||||
<g class="accent">
|
||||
<circle cx="32" cy="32" r="6.5"/>
|
||||
<circle cx="12" cy="14" r="3.5"/>
|
||||
<circle cx="52" cy="18" r="3.5"/>
|
||||
<circle cx="10" cy="40" r="3.5"/>
|
||||
<circle cx="54" cy="44" r="3.5"/>
|
||||
<circle cx="32" cy="56" r="3.5"/>
|
||||
</g>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 957 B |
@ -1,17 +0,0 @@
|
||||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64" role="img" aria-label="Molecule AI">
|
||||
<g stroke="#7fe8d6" stroke-width="2.6" stroke-linecap="round" fill="none">
|
||||
<line x1="32" y1="32" x2="12" y2="14"/>
|
||||
<line x1="32" y1="32" x2="52" y2="18"/>
|
||||
<line x1="32" y1="32" x2="10" y2="40"/>
|
||||
<line x1="32" y1="32" x2="54" y2="44"/>
|
||||
<line x1="32" y1="32" x2="32" y2="56"/>
|
||||
</g>
|
||||
<g fill="#7fe8d6">
|
||||
<circle cx="32" cy="32" r="7"/>
|
||||
<circle cx="12" cy="14" r="3.6"/>
|
||||
<circle cx="52" cy="18" r="3.6"/>
|
||||
<circle cx="10" cy="40" r="3.6"/>
|
||||
<circle cx="54" cy="44" r="3.6"/>
|
||||
<circle cx="32" cy="56" r="3.6"/>
|
||||
</g>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 662 B |
@ -10,7 +10,7 @@ tags: [platform, fly.io, deployment, infrastructure]
|
||||
|
||||
Your infrastructure choice just got decoupled from your agent platform choice. Molecule AI now ships three production-ready workspace backends — `docker`, `flyio`, and `controlplane` — and switching between them takes a single environment variable. Your agent code, model choices, and workspace topology stay exactly the same.
|
||||
|
||||
This post covers what shipped in [PR #501](https://git.moleculesai.app/molecule-ai/molecule-core/pull/501) (Fly Machines provisioner) and [PR #503](https://git.moleculesai.app/molecule-ai/molecule-core/pull/503) (control plane provisioner), and which backend fits your situation.
|
||||
This post covers what shipped in [PR #501](https://github.com/Molecule-AI/molecule-core/pull/501) (Fly Machines provisioner) and [PR #503](https://github.com/Molecule-AI/molecule-core/pull/503) (control plane provisioner), and which backend fits your situation.
|
||||
|
||||
## Before: One Deployment Model for Every Use Case
|
||||
|
||||
@ -107,4 +107,4 @@ No changes to agent code, tool definitions, or orchestration logic. Swap `CONTAI
|
||||
|
||||
---
|
||||
|
||||
*[PR #501](https://git.moleculesai.app/molecule-ai/molecule-core/pull/501) (Fly Machines provisioner) and [PR #503](https://git.moleculesai.app/molecule-ai/molecule-core/pull/503) (control plane provisioner) are both merged to `main`. Molecule AI is open source — contributions welcome.*
|
||||
*[PR #501](https://github.com/Molecule-AI/molecule-core/pull/501) (Fly Machines provisioner) and [PR #503](https://github.com/Molecule-AI/molecule-core/pull/503) (control plane provisioner) are both merged to `main`. Molecule AI is open source — contributions welcome.*
|
||||
|
||||
@ -299,8 +299,8 @@ Or use the Canvas UI: Workspace → Config → MCP Servers → Add browser MCP s
|
||||
|
||||
**Try it free** — Molecule AI is open source and self-hostable. Get a workspace running in under 5 minutes.
|
||||
|
||||
→ [Get started on GitHub →](https://git.moleculesai.app/molecule-ai/molecule-core)
|
||||
→ [Get started on GitHub →](https://github.com/Molecule-AI/molecule-core)
|
||||
|
||||
---
|
||||
|
||||
*Have a browser automation use case you want to see covered? File an issue with the `enhancement` label on the [molecule-core issue tracker](https://git.moleculesai.app/molecule-ai/molecule-core/issues).*
|
||||
*Have a browser automation use case you want to see covered? Open a discussion on [GitHub Discussions](https://github.com/Molecule-AI/molecule-core/discussions) — or file an issue with the `enhancement` label.*
|
||||
|
||||
@ -148,7 +148,7 @@ Then follow the [quick-start guide](/docs/guides/remote-workspaces.md).
|
||||
Or run the annotated example directly:
|
||||
|
||||
```bash
|
||||
git clone https://git.moleculesai.app/molecule-ai/molecule-sdk-python
|
||||
git clone https://github.com/Molecule-AI/molecule-sdk-python
|
||||
cd molecule-sdk-python/examples/remote-agent
|
||||
# Create workspace with runtime:external, grab the ID, then:
|
||||
WORKSPACE_ID=<your-id> PLATFORM_URL=https://acme.moleculesai.app python3 run.py
|
||||
@ -160,6 +160,6 @@ The agent appears on the canvas within seconds.
|
||||
|
||||
→ [Remote Workspaces Guide →](/docs/guides/remote-workspaces.md)
|
||||
→ [External Agent Registration Reference →](/docs/guides/external-agent-registration.md)
|
||||
→ [molecule-sdk-python →](https://git.moleculesai.app/molecule-ai/molecule-sdk-python)
|
||||
→ [molecule-sdk-python →](https://github.com/Molecule-AI/molecule-sdk-python)
|
||||
|
||||
*Phase 30 shipped in PRs #1075–#1083 and #1085–#1100 on `molecule-core`.*
|
||||
|
||||
@ -27,7 +27,7 @@ The biggest user-facing change: every Molecule AI org can now mint named, revoca
|
||||
|
||||
→ [User guide: Organization API Keys](/docs/guides/org-api-keys.md)
|
||||
→ [Architecture: Org API Keys](/docs/architecture/org-api-keys.md)
|
||||
→ PRs: [#1105](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1105), [#1107](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1107), [#1109](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1109), [#1110](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1110)
|
||||
→ PRs: [#1105](https://github.com/Molecule-AI/molecule-core/pull/1105), [#1107](https://github.com/Molecule-AI/molecule-core/pull/1107), [#1109](https://github.com/Molecule-AI/molecule-core/pull/1109), [#1110](https://github.com/Molecule-AI/molecule-core/pull/1110)
|
||||
|
||||
---
|
||||
|
||||
@ -48,7 +48,7 @@ AdminAuth now accepts a session-verification tier that runs **before** the beare
|
||||
**Self-hosted / local dev:** `CP_UPSTREAM_URL` is unset → this feature is disabled, behaviour is unchanged.
|
||||
|
||||
→ [Guide: Same-Origin Canvas Fetches & Session Auth](/docs/guides/same-origin-canvas-fetches.md)
|
||||
→ PRs: [#1099](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1099), [#1100](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1100)
|
||||
→ PRs: [#1099](https://github.com/Molecule-AI/molecule-core/pull/1099), [#1100](https://github.com/Molecule-AI/molecule-core/pull/1100)
|
||||
|
||||
---
|
||||
|
||||
@ -87,7 +87,7 @@ The proxy is **fail-closed**: only an explicit allowlist of paths (`/cp/auth/`,
|
||||
This is also the structural fix for the lateral-movement risk that session auth introduced: without the allowlist, a tenant-authed browser user could have proxied `/cp/admin/*` requests upstream and exploited the fact that those endpoints accept WorkOS session cookies. The allowlist makes that impossible by construction.
|
||||
|
||||
→ [Guide: Same-Origin Canvas Fetches & Session Auth](/docs/guides/same-origin-canvas-fetches.md)
|
||||
→ PR: [#1095](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1095)
|
||||
→ PR: [#1095](https://github.com/Molecule-AI/molecule-core/pull/1095)
|
||||
|
||||
---
|
||||
|
||||
@ -99,7 +99,7 @@ The waitlist itself is a Canvas-administered list with email hashing in audit lo
|
||||
|
||||
This is the operational surface that makes the above security work matter: the beta is invitation-only, credentials are scoped, and every admin action is auditable.
|
||||
|
||||
→ Control plane PRs [#145](https://git.moleculesai.app/molecule-ai/molecule-controlplane/pull/145), [#148](https://git.moleculesai.app/molecule-ai/molecule-controlplane/pull/148), [#150](https://git.moleculesai.app/molecule-ai/molecule-controlplane/pull/150)
|
||||
→ Control plane PRs [#145](https://github.com/Molecule-AI/molecule-controlplane/pull/145), [#148](https://github.com/Molecule-AI/molecule-controlplane/pull/148), [#150](https://github.com/Molecule-AI/molecule-controlplane/pull/150)
|
||||
|
||||
---
|
||||
|
||||
|
||||
@ -12,7 +12,7 @@ Your team is in Discord. Your AI agents are in Molecule AI. Until today, those t
|
||||
|
||||
That's now one webhook URL.
|
||||
|
||||
Molecule AI workspaces can now connect to Discord. Here's what shipped in [PR #656](https://git.moleculesai.app/molecule-ai/molecule-core/pull/656).
|
||||
Molecule AI workspaces can now connect to Discord. Here's what shipped in [PR #656](https://github.com/Molecule-AI/molecule-core/pull/656).
|
||||
|
||||
---
|
||||
|
||||
@ -70,7 +70,7 @@ For inbound slash commands, point your Discord app's **Interactions Endpoint URL
|
||||
|
||||
## Security: Webhook Tokens Don't Appear in Logs
|
||||
|
||||
Webhook URLs contain a token (`/webhooks/{id}/{token}`). If that token leaks into server logs, it's a rotation event. The Discord adapter is explicit about this: HTTP request errors are logged without the URL, and the adapter returns a generic error message. This was hardened in [PR #659](https://git.moleculesai.app/molecule-ai/molecule-core/pull/659).
|
||||
Webhook URLs contain a token (`/webhooks/{id}/{token}`). If that token leaks into server logs, it's a rotation event. The Discord adapter is explicit about this: HTTP request errors are logged without the URL, and the adapter returns a generic error message. This was hardened in [PR #659](https://github.com/Molecule-AI/molecule-core/pull/659).
|
||||
|
||||
---
|
||||
|
||||
@ -97,4 +97,4 @@ Documentation: [Social Channels guide](/docs/agent-runtime/social-channels#disco
|
||||
|
||||
---
|
||||
|
||||
*Discord adapter shipped in [PR #656](https://git.moleculesai.app/molecule-ai/molecule-core/pull/656). Security hardening in [PR #659](https://git.moleculesai.app/molecule-ai/molecule-core/pull/659). Molecule AI is open source — contributions welcome.*
|
||||
*Discord adapter shipped in [PR #656](https://github.com/Molecule-AI/molecule-core/pull/656). Security hardening in [PR #659](https://github.com/Molecule-AI/molecule-core/pull/659). Molecule AI is open source — contributions welcome.*
|
||||
|
||||
@ -133,4 +133,4 @@ With protocol-native A2A, you get:
|
||||
|
||||
Molecule AI's external agent registration is production-ready. Documentation is live at [External Agent Registration Guide](https://docs.molecule.ai/docs/guides/external-agent-registration). The npm package for the MCP server is available at [`@molecule-ai/mcp-server`](https://www.npmjs.com/package/@molecule-ai/mcp-server).
|
||||
|
||||
Read the full [A2A v1.0 protocol spec](https://git.moleculesai.app/molecule-ai/molecule-core/src/branch/main/docs/api-protocol/a2a-protocol.md) on GitHub.
|
||||
Read the full [A2A v1.0 protocol spec](https://github.com/Molecule-AI/molecule-core/blob/main/docs/api-protocol/a2a-protocol.md) on GitHub.
|
||||
@ -45,7 +45,7 @@ canonicalUrl: "https://docs.molecule.ai/blog/remote-workspaces"
|
||||
" proficiencyLevel": "Expert",
|
||||
"genre": ["technical documentation", "product announcement"],
|
||||
"sameAs": [
|
||||
"https://git.moleculesai.app/molecule-ai/molecule-core",
|
||||
"https://github.com/Molecule-AI/molecule-core",
|
||||
"https://molecule.ai"
|
||||
]
|
||||
}
|
||||
@ -270,7 +270,7 @@ Configure it in your project's `.mcp.json` and any AI agent (Claude Code, Cursor
|
||||
|
||||
→ [External Agent Registration Guide](/docs/guides/external-agent-registration) — full step-by-step with Python and Node.js reference implementations
|
||||
|
||||
→ [GitHub: molecule-core](https://git.moleculesai.app/molecule-ai/molecule-core) — source and issues
|
||||
→ [GitHub: molecule-core](https://github.com/Molecule-AI/molecule-core) — source and issues
|
||||
|
||||
→ [Phase 30 Launch Thread on X](https://x.com) — follow for updates
|
||||
|
||||
|
||||
@ -170,4 +170,4 @@ The `staging` branch is now on `a2a-sdk` 1.0.0. The `main` branch still carries
|
||||
|
||||
If you're running `a2a-sdk` 0.3.x and planning the 1.0.0 migration, this post is the reference. The four breaking changes are well-contained, the migration is a single PR, and the eight smoke scenarios above will tell you whether the upgrade is clean before you merge.
|
||||
|
||||
Questions? The [A2A protocol spec](https://github.com/google-a2a/a2a-specification) is the authoritative source. For Molecule AI's production A2A implementation, see [External Agent Registration](https://docs.molecule.ai/docs/guides/external-agent-registration) or open an issue in the [molecule-core](https://git.moleculesai.app/molecule-ai/molecule-core) repo.
|
||||
Questions? The [A2A protocol spec](https://github.com/google-a2a/a2a-specification) is the authoritative source. For Molecule AI's production A2A implementation, see [External Agent Registration](https://docs.molecule.ai/docs/guides/external-agent-registration) or open an issue in the [molecule-core](https://github.com/Molecule-AI/molecule-core) repo.
|
||||
|
||||
@ -1,41 +1,5 @@
|
||||
# Local Development
|
||||
|
||||
## Workspace Template Images: Local-Build Mode (Issue #63)
|
||||
|
||||
OSS contributors who run `molecule-core` locally do **not** need to authenticate to GHCR or AWS ECR. When the `MOLECULE_IMAGE_REGISTRY` env var is **unset**, the platform automatically:
|
||||
|
||||
1. Looks up the HEAD sha of `https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-<runtime>` (single API call, no clone).
|
||||
2. If a local image tagged `molecule-local/workspace-template-<runtime>:<sha12>` already exists, reuses it (cache hit).
|
||||
3. Otherwise, shallow-clones the repo into `~/.cache/molecule/workspace-template-build/<runtime>/<sha12>/` and runs `docker build --platform=linux/amd64 -t <tag> .`.
|
||||
4. Hands the SHA-pinned tag to Docker for `ContainerCreate`.
|
||||
|
||||
**First-provision build time:** 5–10 min on Apple Silicon (amd64 emulation). Subsequent provisions hit the cache and start in seconds. Cache is invalidated automatically when the template repo's HEAD moves.
|
||||
|
||||
**Currently mirrored on Gitea:** `claude-code`, `hermes`, `langgraph`, `autogen`. Other runtimes (`crewai`, `deepagents`, `codex`, `gemini-cli`, `openclaw`) fail with an actionable "not mirrored to Gitea" error pointing at the missing repo.
|
||||
|
||||
**Production tenants are unaffected** — every prod tenant sets `MOLECULE_IMAGE_REGISTRY` to its private ECR mirror via Railway env / EC2 user-data, so the SaaS pull path stays identical.
|
||||
|
||||
### Environment overrides
|
||||
|
||||
| Var | Default | Use case |
|
||||
|-----|---------|----------|
|
||||
| `MOLECULE_IMAGE_REGISTRY` | (unset) | Set to a real registry URL to switch from local-build to SaaS-pull mode. |
|
||||
| `MOLECULE_LOCAL_BUILD_CACHE` | `~/.cache/molecule/workspace-template-build` | Override cache directory. |
|
||||
| `MOLECULE_LOCAL_TEMPLATE_REPO_PREFIX` | `https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-` | Point at a fork. |
|
||||
| `MOLECULE_GITEA_TOKEN` | (unset) | Required only if your fork has private template repos. |
|
||||
|
||||
### Verifying a switch from the GHCR-retag stopgap
|
||||
|
||||
Pre-fix, OSS contributors worked around the suspended GHCR org by manually retagging an `:latest` image. After this change, that workaround is **redundant**: simply unset `MOLECULE_IMAGE_REGISTRY` (or leave it unset), boot the platform, and provision a workspace. Logs will show:
|
||||
|
||||
```
|
||||
Provisioner: local-build mode → using locally-built image molecule-local/workspace-template-claude-code:<sha12> for runtime claude-code
|
||||
local-build: cloning https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-claude-code → ...
|
||||
local-build: docker build done in <duration>
|
||||
```
|
||||
|
||||
If you still see `ghcr.io/molecule-ai/...` in the boot log, double-check `env | grep MOLECULE_IMAGE_REGISTRY` — a stale shell export from the pre-fix workaround could keep SaaS-mode active.
|
||||
|
||||
## Starting the Stack
|
||||
|
||||
```bash
|
||||
|
||||
@ -3,8 +3,8 @@
|
||||
**Date:** 2026-04-23
|
||||
**Severity:** High — every new SaaS tenant blocked
|
||||
**Detection path:** E2E Staging SaaS run 24848425822 failed at "tenant provisioning"; investigation of CP Railway logs surfaced the auth mismatch.
|
||||
**Status:** Fix pushed on [molecule-controlplane#238](https://git.moleculesai.app/molecule-ai/molecule-controlplane/pull/238).
|
||||
**Related:** [issue #239](https://git.moleculesai.app/molecule-ai/molecule-controlplane/issues/239) (Cloudflare DNS record quota), [testing-strategy.md](../engineering/testing-strategy.md)
|
||||
**Status:** Fix pushed on [molecule-controlplane#238](https://github.com/Molecule-AI/molecule-controlplane/pull/238).
|
||||
**Related:** [issue #239](https://github.com/Molecule-AI/molecule-controlplane/issues/239) (Cloudflare DNS record quota), [testing-strategy.md](../engineering/testing-strategy.md)
|
||||
|
||||
## Summary
|
||||
|
||||
@ -35,7 +35,7 @@ The flow was:
|
||||
|
||||
### The commit that introduced the bug
|
||||
|
||||
[molecule-controlplane#235](https://git.moleculesai.app/molecule-ai/molecule-controlplane/pull/235) — "fix(provision): wait for tenant boot-event before falling back to canary". Merged 2026-04-22.
|
||||
[molecule-controlplane#235](https://github.com/Molecule-AI/molecule-controlplane/pull/235) — "fix(provision): wait for tenant boot-event before falling back to canary". Merged 2026-04-22.
|
||||
|
||||
Before #235, readiness was determined via a canary probe through Cloudflare's edge — which didn't need CP-side auth, so the INSERT ordering didn't matter. #235 made boot-events the primary readiness signal but didn't move the INSERT earlier. The race was latent before but became load-bearing after.
|
||||
|
||||
@ -90,7 +90,7 @@ bootReady, _ := provisioner.WaitForTenantReady(ctx, h.db, org.ID, 4*time.Minute)
|
||||
h.db.ExecContext(ctx, `UPDATE org_instances SET status = 'running' WHERE org_id = $1`, org.ID)
|
||||
```
|
||||
|
||||
See [molecule-controlplane#238](https://git.moleculesai.app/molecule-ai/molecule-controlplane/pull/238) for the full diff.
|
||||
See [molecule-controlplane#238](https://github.com/Molecule-AI/molecule-controlplane/pull/238) for the full diff.
|
||||
|
||||
## Lessons
|
||||
|
||||
@ -122,9 +122,9 @@ Early investigation blamed the hermes provider 401 bug (a separate, known issue
|
||||
|
||||
## Follow-ups
|
||||
|
||||
- [ ] Land [molecule-controlplane#238](https://git.moleculesai.app/molecule-ai/molecule-controlplane/pull/238)
|
||||
- [ ] Land [molecule-controlplane#238](https://github.com/Molecule-AI/molecule-controlplane/pull/238)
|
||||
- [ ] Redeploy staging-api, verify E2E goes green
|
||||
- [ ] Add CP integration test suite (see lesson #2)
|
||||
- [ ] Wire E2E failure → notification (see lesson #3)
|
||||
- [ ] Add invariant comment in `provisionTenant` (see lesson #4)
|
||||
- [ ] Cloudflare DNS quota cleanup — [molecule-controlplane#239](https://git.moleculesai.app/molecule-ai/molecule-controlplane/issues/239)
|
||||
- [ ] Cloudflare DNS quota cleanup — [molecule-controlplane#239](https://github.com/Molecule-AI/molecule-controlplane/issues/239)
|
||||
|
||||
@ -138,5 +138,5 @@ If you see any of these, don't try to "clean it up in place" — **cherry-pick o
|
||||
|
||||
## Related
|
||||
|
||||
- [Issue #1822](https://git.moleculesai.app/molecule-ai/molecule-core/issues/1822) — backend parity drift tracker (example of docs that have to stay current)
|
||||
- [Issue #1822](https://github.com/Molecule-AI/molecule-core/issues/1822) — backend parity drift tracker (example of docs that have to stay current)
|
||||
- [Postmortem: CP boot-event 401](./postmortem-2026-04-23-boot-event-401.md) — caught before shipping because a reviewer could read the diff
|
||||
|
||||
@ -1,147 +0,0 @@
|
||||
# Rate-limit observability runbook
|
||||
|
||||
> Companion to issue #64 ("RATE_LIMIT default re-tune analysis"). After
|
||||
> #60 deployed the per-tenant `keyFor` keying, the right RATE_LIMIT
|
||||
> default became data-dependent. This runbook documents the metrics +
|
||||
> queries an operator should run to confirm whether the current 600
|
||||
> req/min/key default is correct, too tight, or too loose.
|
||||
|
||||
## What's already exposed
|
||||
|
||||
The workspace-server's existing Prometheus middleware
|
||||
(`workspace-server/internal/metrics/metrics.go`) tracks every request
|
||||
on every path:
|
||||
|
||||
```
|
||||
molecule_http_requests_total{method, path, status} counter
|
||||
molecule_http_request_duration_seconds_total{method,path,status} counter
|
||||
```
|
||||
|
||||
Path is the matched route pattern (`/workspaces/:id/activity` etc), so
|
||||
high-cardinality workspace UUIDs do not explode the label space.
|
||||
|
||||
The rate limiter middleware (#60, `workspace-server/internal/middleware/ratelimit.go`)
|
||||
also stamps every response with `X-RateLimit-Limit`, `X-RateLimit-Remaining`,
|
||||
and `X-RateLimit-Reset`. Operators with browser-side or proxy-side
|
||||
header capture can read per-request bucket state directly.
|
||||
|
||||
No new instrumentation is needed for #64's acceptance criteria. The
|
||||
metric surface is sufficient — this runbook just collects the queries.
|
||||
|
||||
## Queries to run after #60 deploys
|
||||
|
||||
### 1. Is the bucket actually firing 429s?
|
||||
|
||||
```promql
|
||||
sum(rate(molecule_http_requests_total{status="429"}[5m]))
|
||||
```
|
||||
|
||||
If this is zero on a given tenant, the bucket isn't being hit. If it's
|
||||
sustained > 1/min, dig in.
|
||||
|
||||
### 2. Which routes attract 429s?
|
||||
|
||||
```promql
|
||||
topk(
|
||||
10,
|
||||
sum by (path) (
|
||||
rate(molecule_http_requests_total{status="429"}[5m])
|
||||
)
|
||||
)
|
||||
```
|
||||
|
||||
Expected shape post-#60:
|
||||
- `/workspaces/:id/activity` should be near zero — the canvas no longer
|
||||
polls it on a 30s/60s/5s cadence (PRs #69 / #71 / #76).
|
||||
- Probe / health / heartbeat paths should be ~0 (those routes have a
|
||||
separate IP-fallback bucket).
|
||||
|
||||
If `/workspaces/:id/activity` 429s persist post-PRs-69/71/76 deploy, the
|
||||
canvas isn't running the WS-subscriber path — investigate WS health
|
||||
on that tenant.
|
||||
|
||||
### 3. Per-bucket-key inference (no direct exposure today)
|
||||
|
||||
The bucket map itself is in-memory only; we deliberately do **not**
|
||||
expose `org:<uuid>` ↔ remaining-tokens because that map can include
|
||||
SHA-256 hashes of bearer tokens. A tenant that wants per-key visibility
|
||||
should rely on response headers (`X-RateLimit-Remaining` on every
|
||||
response from a given session is the bucket's view of that session).
|
||||
|
||||
If you genuinely need server-side per-bucket counts for triage,
|
||||
file a follow-up — the proper shape is a `/internal/ratelimit-stats`
|
||||
endpoint that emits **counts per key prefix only** (e.g. `org:`, `tok:`,
|
||||
`ip:`), never the key payloads. Don't roll that ad-hoc; it's a security
|
||||
review surface.
|
||||
|
||||
## Decision tree for the re-tune
|
||||
|
||||
After 14 days of production traffic on a tenant, look at the queries
|
||||
above and walk this tree:
|
||||
|
||||
```
|
||||
Q1: Is the 429 rate sustained > 0.1/sec on any tenant?
|
||||
├─ NO → The 600 default has comfortable headroom. Either keep it,
|
||||
│ or lower it carefully (300) ONLY if you have a documented
|
||||
│ reason (e.g. a misbehaving client we want to throttle harder).
|
||||
│ Default to "no change" — see #64 for the math.
|
||||
└─ YES → Q2.
|
||||
|
||||
Q2: Is the 429 rate concentrated on ONE tenant or spread across many?
|
||||
├─ ONE tenant → Operator override: set RATE_LIMIT=1200 or 1800 on that
|
||||
│ tenant's box. Document in the tenant's ops note. The
|
||||
│ default does not need to change.
|
||||
└─ MANY tenants → Q3.
|
||||
|
||||
Q3: Are the 429s on a route that polls (e.g. /activity / /peers)?
|
||||
├─ YES → Confirm PRs #69, #71, #76 have actually deployed to those
|
||||
│ tenants. If they have and 429s persist, the canvas may have
|
||||
│ a regression — do not raise RATE_LIMIT. File a canvas issue.
|
||||
└─ NO → 429s on mutating routes mean genuine load. Raise the default
|
||||
to 1200 in `workspace-server/internal/router/router.go:54`.
|
||||
Same PR should attach: the metric chart, the time window,
|
||||
and a paragraph explaining what changed in our traffic shape.
|
||||
```
|
||||
|
||||
## Alert rule template (drop-in for Prometheus)
|
||||
|
||||
```yaml
|
||||
# Sustained 429s — file is the SLO trip-wire. If this fires, walk the
|
||||
# decision tree above. NB: the issue#64 acceptance criterion is "two
|
||||
# weeks of metrics"; this alert is the inverse — it tells you something
|
||||
# changed before the two weeks are up.
|
||||
groups:
|
||||
- name: workspace-server-ratelimit
|
||||
rules:
|
||||
- alert: WorkspaceServerRateLimit429Sustained
|
||||
expr: |
|
||||
sum by (instance) (
|
||||
rate(molecule_http_requests_total{status="429"}[10m])
|
||||
) > 0.1
|
||||
for: 30m
|
||||
labels:
|
||||
severity: warning
|
||||
owner: workspace-server
|
||||
annotations:
|
||||
summary: "{{ $labels.instance }} sustained 429s — see ratelimit-observability runbook"
|
||||
runbook: "https://git.moleculesai.app/molecule-ai/molecule-core/blob/main/docs/engineering/ratelimit-observability.md"
|
||||
```
|
||||
|
||||
Threshold rationale: 0.1 req/s = 6/min sustained over 10min. Below
|
||||
that, a 429 is almost certainly a transient burst that the canvas's
|
||||
retry-once handler at `canvas/src/lib/api.ts:55` already absorbs. The
|
||||
30m `for:` keeps the alert from chattering on a brief blip.
|
||||
|
||||
## Companion probe script
|
||||
|
||||
For one-off triage when an operator can reproduce the problem in their
|
||||
own browser, `scripts/edge-429-probe.sh` (#62) reproduces a canvas-
|
||||
sized burst against a tenant subdomain and dumps each 429's response
|
||||
shape so the operator can distinguish workspace-server bucket overflow
|
||||
from CF/Vercel edge rate-limiting without dashboard access.
|
||||
|
||||
```sh
|
||||
./scripts/edge-429-probe.sh hongming.moleculesai.app --burst 80 --out /tmp/edge.txt
|
||||
```
|
||||
|
||||
The script's report header explains how to read the output.
|
||||
@ -103,9 +103,9 @@ A bad test:
|
||||
|
||||
## Related
|
||||
|
||||
- [Issue #1821](https://git.moleculesai.app/molecule-ai/molecule-core/issues/1821) — policy tracking issue
|
||||
- [Issue #1815](https://git.moleculesai.app/molecule-ai/molecule-core/issues/1815) — Canvas coverage instrumentation
|
||||
- [Issue #1818](https://git.moleculesai.app/molecule-ai/molecule-core/issues/1818) — Python pytest-cov
|
||||
- [Issue #1814](https://git.moleculesai.app/molecule-ai/molecule-core/issues/1814) — workspace_provision_test.go unblock
|
||||
- [Issue #1816](https://git.moleculesai.app/molecule-ai/molecule-core/issues/1816) — tokens.go coverage
|
||||
- [Issue #1819](https://git.moleculesai.app/molecule-ai/molecule-core/issues/1819) — wsauth_middleware coverage
|
||||
- [Issue #1821](https://github.com/Molecule-AI/molecule-core/issues/1821) — policy tracking issue
|
||||
- [Issue #1815](https://github.com/Molecule-AI/molecule-core/issues/1815) — Canvas coverage instrumentation
|
||||
- [Issue #1818](https://github.com/Molecule-AI/molecule-core/issues/1818) — Python pytest-cov
|
||||
- [Issue #1814](https://github.com/Molecule-AI/molecule-core/issues/1814) — workspace_provision_test.go unblock
|
||||
- [Issue #1816](https://github.com/Molecule-AI/molecule-core/issues/1816) — tokens.go coverage
|
||||
- [Issue #1819](https://github.com/Molecule-AI/molecule-core/issues/1819) — wsauth_middleware coverage
|
||||
|
||||
@ -153,7 +153,7 @@ The `id` field is your workspace ID — remember it.
|
||||
|---|---|
|
||||
| "Failed to send message — agent may be unreachable" | The tenant couldn't POST to your URL. Verify `curl https://<your-tunnel>/health` returns 200 from another machine. |
|
||||
| Response takes > 30s | Canvas times out around 30s. Keep initial implementations simple. For long-running work, return a placeholder and use [polling mode](#next-step-polling-mode-preview) (once available). |
|
||||
| Agent duplicated in chat | Known canvas bug where WebSocket + HTTP responses both render. Fixed in [PR #1517](https://git.moleculesai.app/molecule-ai/molecule-core/pull/1517). |
|
||||
| Agent duplicated in chat | Known canvas bug where WebSocket + HTTP responses both render. Fixed in [PR #1517](https://github.com/Molecule-AI/molecule-core/pull/1517). |
|
||||
| Agent replies but canvas shows "Agent unreachable" | Check the tenant can reach your URL. Cloudflare quick tunnels rotate — the URL in your canvas may point at a dead tunnel after restart. |
|
||||
| Getting 404 when POSTing to tenant | Add `X-Molecule-Org-Id` header. The tenant's security layer 404s unmatched origin requests by design. |
|
||||
|
||||
@ -215,7 +215,7 @@ Push mode (this guide) works today but requires an inbound-reachable URL — whi
|
||||
|
||||
Your agent makes only outbound HTTPS calls to the platform, pulling messages from an inbox queue and posting replies back. Works behind any NAT/firewall, tolerates offline laptops, no tunnel needed.
|
||||
|
||||
See the [design doc](https://git.moleculesai.app/molecule-ai/internal/src/branch/main/product/external-workspaces-polling.md) (internal) and the implementation tracking issue (search `polling+mode` on the [molecule-core issue tracker](https://git.moleculesai.app/molecule-ai/molecule-core/issues)).
|
||||
See the [design doc](https://github.com/Molecule-AI/internal/blob/main/product/external-workspaces-polling.md) (internal) and [implementation tracking issue](https://github.com/Molecule-AI/molecule-core/issues?q=polling+mode) once opened.
|
||||
|
||||
---
|
||||
|
||||
@ -255,7 +255,7 @@ If all four pass and canvas still shows your agent as unreachable, see the [remo
|
||||
## Feedback
|
||||
|
||||
This is a new path. Tell us what broke:
|
||||
- Open an issue: https://git.moleculesai.app/molecule-ai/molecule-core/issues/new?labels=external-workspace
|
||||
- Open an issue: https://github.com/Molecule-AI/molecule-core/issues/new?labels=external-workspace
|
||||
- Join #external-workspaces on our Slack
|
||||
- Submit a PR improving this doc if something tripped you up — the faster we can make the quickstart, the more developers we bring in
|
||||
|
||||
|
||||
@ -143,5 +143,5 @@ The agent appears on the canvas with a **purple REMOTE badge** within seconds. F
|
||||
## Next Steps
|
||||
|
||||
- **[External Agent Registration Guide →](/docs/guides/external-agent-registration)** — full endpoint reference, Python + Node.js examples, troubleshooting
|
||||
- **[molecule-sdk-python →](https://git.moleculesai.app/molecule-ai/molecule-sdk-python)** — SDK source, `RemoteAgentClient` API docs
|
||||
- **[SDK Examples →](https://git.moleculesai.app/molecule-ai/molecule-sdk-python/src/branch/main/examples/remote-agent)** — `run.py` demo script, annotated walkthrough
|
||||
- **[molecule-sdk-python →](https://github.com/Molecule-AI/molecule-sdk-python)** — SDK source, `RemoteAgentClient` API docs
|
||||
- **[SDK Examples →](https://github.com/Molecule-AI/molecule-sdk-python/tree/main/examples/remote-agent)** — `run.py` demo script, annotated walkthrough
|
||||
|
||||
@ -61,7 +61,7 @@ molecule skills install arxiv-research --from community
|
||||
|
||||
Community skills are reviewed by the Molecule AI team before being
|
||||
listed. Submit a skill for review by opening a PR against
|
||||
[`molecule-ai/skills`](https://git.moleculesai.app/molecule-ai/skills).
|
||||
[`molecule-ai/skills`](https://github.com/Molecule-AI/skills).
|
||||
|
||||
## Installing via config.yaml
|
||||
|
||||
@ -151,7 +151,7 @@ molecule skills bundle my-custom-skill --output ./org-templates/my-role/
|
||||
```
|
||||
|
||||
**Publishing to the community:** Open a PR against
|
||||
[`molecule-ai/skills`](https://git.moleculesai.app/molecule-ai/skills) with a
|
||||
[`molecule-ai/skills`](https://github.com/Molecule-AI/skills) with a
|
||||
complete skill package. Community skills are reviewed for security and
|
||||
correctness before listing.
|
||||
|
||||
|
||||
@ -58,11 +58,8 @@ green — proves wire shape end-to-end against a real `hermes gateway run`
|
||||
subprocess + stub OpenAI-compat LLM. Caught + fixed a real `KeyError`
|
||||
in upstream `hermes_cli/tools_config.py` (PLATFORMS dict lookup
|
||||
crashed on plugin platforms) — fix on the patched fork branch
|
||||
(`molecule-ai/hermes-agent` `feat/platform-adapter-plugins`, commit
|
||||
`18e4849e`, hosted on Gitea at
|
||||
`https://git.moleculesai.app/molecule-ai/hermes-agent` — moved from the
|
||||
suspended `github.com/HongmingWang-Rabbit/hermes-agent`, see
|
||||
`molecule-ai/internal#72`). Upstream PR #18775 OPEN; CONFLICTING with main.
|
||||
(`HongmingWang-Rabbit/hermes-agent` `feat/platform-adapter-plugins`,
|
||||
commit `18e4849e`). Upstream PR #18775 OPEN; CONFLICTING with main.
|
||||
Not on critical path for our platform — patched fork is what the
|
||||
workspace image installs.
|
||||
|
||||
@ -99,10 +96,10 @@ fork needed in production.
|
||||
`resolve_platform_id` for plugin-platform-safe deserialization, and
|
||||
`self.adapters[adapter.platform]` keying fix (caught by real-subprocess
|
||||
test before merge — see below).
|
||||
- **Plugin package**: [Molecule-AI/hermes-platform-molecule-a2a](https://git.moleculesai.app/molecule-ai/hermes-platform-molecule-a2a)
|
||||
- **Plugin package**: [Molecule-AI/hermes-platform-molecule-a2a](https://github.com/Molecule-AI/hermes-platform-molecule-a2a)
|
||||
v0.1.0 — public, MIT-licensed. 11 unit tests + 8 in-process E2E
|
||||
+ 4 real-subprocess E2E checkpoints all green.
|
||||
- **Workspace template patch**: [Molecule-AI/molecule-ai-workspace-template-hermes#32](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-hermes/pull/32)
|
||||
- **Workspace template patch**: [Molecule-AI/molecule-ai-workspace-template-hermes#32](https://github.com/Molecule-AI/molecule-ai-workspace-template-hermes/pull/32)
|
||||
— Dockerfile installs the patched fork + plugin into the hermes
|
||||
installer's venv; start.sh seeds `platforms.molecule-a2a` config
|
||||
stanza. Pre-demo deliberately install-only; adapter.py rewrite to
|
||||
@ -157,9 +154,9 @@ intermediate shim earns its complexity.
|
||||
## Codex (OpenAI Codex CLI)
|
||||
|
||||
**Status:** Template SHIPPED. Repo live at
|
||||
[`Molecule-AI/molecule-ai-workspace-template-codex`](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-codex)
|
||||
[`Molecule-AI/molecule-ai-workspace-template-codex`](https://github.com/Molecule-AI/molecule-ai-workspace-template-codex)
|
||||
(14 files, 1411 LOC, 12/12 tests). molecule-core registration in
|
||||
[PR #2512](https://git.moleculesai.app/molecule-ai/molecule-core/pull/2512).
|
||||
[PR #2512](https://github.com/Molecule-AI/molecule-core/pull/2512).
|
||||
E2E with real A2A traffic remains.
|
||||
|
||||
**Path:** Persistent `codex app-server` stdio JSON-RPC client
|
||||
|
||||
@ -101,7 +101,7 @@ incident-shaped.
|
||||
## [v1.0.0] — initial release (RFC #2728, PRs #2729-#2742)
|
||||
|
||||
Initial plugin contract + 11-PR rollout. See
|
||||
[issue #2728](https://git.moleculesai.app/molecule-ai/molecule-core/issues/2728)
|
||||
[issue #2728](https://github.com/Molecule-AI/molecule-core/issues/2728)
|
||||
for the full RFC.
|
||||
|
||||
Endpoints: `/v1/health`, `/v1/namespaces/{name}` (PUT/PATCH/DELETE),
|
||||
|
||||
@ -160,11 +160,11 @@ not expose.
|
||||
| `molecule-skill-update-docs` | `[claude_code]` | `[claude_code, hermes]` |
|
||||
|
||||
Companion PRs:
|
||||
- [molecule-ai-plugin-ecc#2](https://git.moleculesai.app/molecule-ai/molecule-ai-plugin-ecc/pull/2)
|
||||
- [molecule-ai-plugin-superpowers#2](https://git.moleculesai.app/molecule-ai/molecule-ai-plugin-superpowers/pull/2)
|
||||
- [molecule-ai-plugin-molecule-dev#2](https://git.moleculesai.app/molecule-ai/molecule-ai-plugin-molecule-dev/pull/2)
|
||||
- [molecule-ai-plugin-molecule-skill-cron-learnings#2](https://git.moleculesai.app/molecule-ai/molecule-ai-plugin-molecule-skill-cron-learnings/pull/2)
|
||||
- [molecule-ai-plugin-molecule-skill-update-docs#2](https://git.moleculesai.app/molecule-ai/molecule-ai-plugin-molecule-skill-update-docs/pull/2)
|
||||
- [molecule-ai-plugin-ecc#2](https://github.com/Molecule-AI/molecule-ai-plugin-ecc/pull/2)
|
||||
- [molecule-ai-plugin-superpowers#2](https://github.com/Molecule-AI/molecule-ai-plugin-superpowers/pull/2)
|
||||
- [molecule-ai-plugin-molecule-dev#2](https://github.com/Molecule-AI/molecule-ai-plugin-molecule-dev/pull/2)
|
||||
- [molecule-ai-plugin-molecule-skill-cron-learnings#2](https://github.com/Molecule-AI/molecule-ai-plugin-molecule-skill-cron-learnings/pull/2)
|
||||
- [molecule-ai-plugin-molecule-skill-update-docs#2](https://github.com/Molecule-AI/molecule-ai-plugin-molecule-skill-update-docs/pull/2)
|
||||
|
||||
Security note: Security Auditor was offline at time of change. Self-assessed
|
||||
as non-security-impacting — adding `hermes` to a string list in `plugin.yaml`
|
||||
|
||||
@ -17,7 +17,7 @@ This path is aligned to the current repository and current UI. It gets you from
|
||||
## The one-command path
|
||||
|
||||
```bash
|
||||
git clone https://git.moleculesai.app/molecule-ai/molecule-monorepo.git
|
||||
git clone https://github.com/Molecule-AI/molecule-monorepo.git
|
||||
cd molecule-monorepo
|
||||
./scripts/dev-start.sh
|
||||
```
|
||||
@ -42,7 +42,7 @@ If you'd rather run each component yourself — useful when you're iterating on
|
||||
### Step 1: Clone the repository
|
||||
|
||||
```bash
|
||||
git clone https://git.moleculesai.app/molecule-ai/molecule-monorepo.git
|
||||
git clone https://github.com/Molecule-AI/molecule-monorepo.git
|
||||
cd molecule-monorepo
|
||||
```
|
||||
|
||||
|
||||
@ -1,137 +0,0 @@
|
||||
# Runbook — Handlers Postgres Integration port-collision substrate
|
||||
|
||||
**Status:** Resolved 2026-05-08 (PR for class B Hongming-owned CICD red sweep).
|
||||
|
||||
## Symptom
|
||||
|
||||
`Handlers Postgres Integration` workflow fails on staging push and PRs.
|
||||
Step `Apply migrations to Postgres service` shows:
|
||||
|
||||
```
|
||||
psql: error: connection to server at "127.0.0.1", port 5432 failed: Connection refused
|
||||
```
|
||||
|
||||
Job-cleanup step further down logs:
|
||||
|
||||
```
|
||||
Cleaning up services for job Handlers Postgres Integration
|
||||
failed to remove container: Error response from daemon: No such container: <id>
|
||||
```
|
||||
|
||||
…confirming the postgres service container was already gone before
|
||||
cleanup ran.
|
||||
|
||||
## Root cause
|
||||
|
||||
Our Gitea act_runner (operator host `5.78.80.188`,
|
||||
`/opt/molecule/runners/config.yaml`) sets:
|
||||
|
||||
```yaml
|
||||
container:
|
||||
network: host
|
||||
```
|
||||
|
||||
…which act_runner applies to BOTH the job container AND every
|
||||
`services:` container in a workflow. Multiple workflow instances
|
||||
running concurrently across the 16 parallel runners each try to bind
|
||||
postgres on `0.0.0.0:5432`. The first wins; subsequent instances exit
|
||||
immediately with:
|
||||
|
||||
```
|
||||
LOG: could not bind IPv4 address "0.0.0.0": Address in use
|
||||
HINT: Is another postmaster already running on port 5432?
|
||||
FATAL: could not create any TCP/IP sockets
|
||||
```
|
||||
|
||||
act_runner sets `AutoRemove:true` on service containers, so Docker
|
||||
garbage-collects them as soon as they exit. By the time the migrations
|
||||
step runs `pg_isready` / `psql`, the container is gone and connection
|
||||
refused.
|
||||
|
||||
Reproduction (operator host):
|
||||
|
||||
```bash
|
||||
docker run --rm -d --name pg-A --network host \
|
||||
-e POSTGRES_PASSWORD=test postgres:15-alpine
|
||||
docker run -d --name pg-B --network host \
|
||||
-e POSTGRES_PASSWORD=test postgres:15-alpine
|
||||
docker logs pg-B # FATAL: could not create any TCP/IP sockets
|
||||
```
|
||||
|
||||
## Why per-job override doesn't work
|
||||
|
||||
The natural fix — per-job `container.network` override — is silently
|
||||
ignored by act_runner. The runner log emits:
|
||||
|
||||
```
|
||||
--network and --net in the options will be ignored.
|
||||
```
|
||||
|
||||
This is a documented act_runner constraint: container network is a
|
||||
runner-wide setting, not per-job. Source: gitea/act_runner config docs
|
||||
+ vegardit/docker-gitea-act-runner issue #7.
|
||||
|
||||
Flipping the global `container.network` to `bridge` would break every
|
||||
other workflow in the repo (cache server discovery,
|
||||
`molecule-monorepo-net` peer access during integration tests, etc.) —
|
||||
unacceptable blast radius for a per-test bug.
|
||||
|
||||
## Fix shape
|
||||
|
||||
`handlers-postgres-integration.yml` no longer uses `services: postgres:`.
|
||||
It launches a sibling postgres container manually on the existing
|
||||
`molecule-monorepo-net` bridge network with a per-run unique name:
|
||||
|
||||
```yaml
|
||||
env:
|
||||
PG_NAME: pg-handlers-${{ github.run_id }}-${{ github.run_attempt }}
|
||||
PG_NETWORK: molecule-monorepo-net
|
||||
|
||||
steps:
|
||||
- name: Start sibling Postgres on bridge network
|
||||
run: |
|
||||
docker run -d --name "${PG_NAME}" --network "${PG_NETWORK}" \
|
||||
...
|
||||
postgres:15-alpine
|
||||
PG_HOST=$(docker inspect "${PG_NAME}" \
|
||||
--format "{{(index .NetworkSettings.Networks \"${PG_NETWORK}\").IPAddress}}")
|
||||
echo "PG_HOST=${PG_HOST}" >> "$GITHUB_ENV"
|
||||
|
||||
# … migrations + tests use ${PG_HOST}, not 127.0.0.1 …
|
||||
|
||||
- if: always() && …
|
||||
name: Stop sibling Postgres
|
||||
run: docker rm -f "${PG_NAME}" || true
|
||||
```
|
||||
|
||||
The host-net job container can reach a bridge-net container via the
|
||||
bridge IP directly (verified manually, 2026-05-08). Two parallel runs
|
||||
use different names + different bridge IPs — no collision.
|
||||
|
||||
## Future-proofing
|
||||
|
||||
Other workflows that hit the same shape (any `services:` with a
|
||||
fixed-port image) will exhibit the same failure mode under
|
||||
host-network runner config. Translate using this same pattern:
|
||||
|
||||
1. Drop the `services:` block.
|
||||
2. Use `${{ github.run_id }}-${{ github.run_attempt }}` for unique
|
||||
container name.
|
||||
3. Launch on `molecule-monorepo-net` (already trusted bridge in
|
||||
`docker-compose.infra.yml`).
|
||||
4. Read back the bridge IP via `docker inspect` and export as a step env.
|
||||
5. `if: always()` cleanup step at the end.
|
||||
|
||||
If the count of such workflows grows, factor into a composite action
|
||||
(`./.github/actions/sibling-postgres`) so the substrate logic lives
|
||||
in one place.
|
||||
|
||||
## Related
|
||||
|
||||
- Issue #88 (closed by #92): localhost → 127.0.0.1 fix that unmasked
|
||||
this collision; the IPv6 fix is correct, port collision is the new
|
||||
layer.
|
||||
- Issue #94 created `molecule-monorepo-net` + `alpine:latest` as
|
||||
prereqs.
|
||||
- Saved memory `feedback_act_runner_github_server_url` documents
|
||||
another act_runner-vs-GHA divergence (server URL).
|
||||
@ -198,7 +198,7 @@ Lighthouse audit against staging.yourapp.com:
|
||||
FCP: 2.4s | LCP: 5.2s | CLS: 0.18 | TBT: 620ms
|
||||
|
||||
Performance regression detected — opening GitHub issue.
|
||||
Issue: https://git.moleculesai.app/molecule-ai/molecule-core/issues/1527
|
||||
Issue: https://github.com/Molecule-AI/molecule-core/issues/1527
|
||||
Label: performance-regression | Assignees: @your-team
|
||||
```
|
||||
|
||||
|
||||
@ -85,8 +85,8 @@ Fly Machines start in milliseconds and run in 35+ regions. Provisioning agent wo
|
||||
|
||||
## Related
|
||||
|
||||
- PR #501: [feat(platform): Fly Machines provisioner](https://git.moleculesai.app/molecule-ai/molecule-core/pull/501)
|
||||
- PR #481: [feat(ci): deploy to Fly after image push](https://git.moleculesai.app/molecule-ai/molecule-core/pull/481)
|
||||
- PR #501: [feat(platform): Fly Machines provisioner](https://github.com/Molecule-AI/molecule-core/pull/501)
|
||||
- PR #481: [feat(ci): deploy to Fly after image push](https://github.com/Molecule-AI/molecule-core/pull/481)
|
||||
- [Fly Machines API docs](https://fly.io/docs/machines/api/)
|
||||
- [Platform API reference](../api-reference.md)
|
||||
- Issue [#525](https://git.moleculesai.app/molecule-ai/molecule-core/issues/525)
|
||||
- Issue [#525](https://github.com/Molecule-AI/molecule-core/issues/525)
|
||||
|
||||
@ -61,6 +61,6 @@ The real power surfaces when you mix runtimes on the same Molecule AI tenant. Yo
|
||||
|
||||
## Related
|
||||
|
||||
- PR #379: [feat(adapters): add gemini-cli runtime adapter](https://git.moleculesai.app/molecule-ai/molecule-core/pull/379)
|
||||
- PR #379: [feat(adapters): add gemini-cli runtime adapter](https://github.com/Molecule-AI/molecule-core/pull/379)
|
||||
- [Multi-provider Hermes docs](../architecture/hermes.md)
|
||||
- [Workspace runtimes reference](../reference/runtimes.md)
|
||||
|
||||
@ -68,7 +68,7 @@ ADK workspaces participate in the same A2A network as Claude Code, Gemini CLI, H
|
||||
|
||||
## Related
|
||||
|
||||
- PR #550: [feat(adapters): add google-adk runtime adapter](https://git.moleculesai.app/molecule-ai/molecule-core/pull/550)
|
||||
- PR #550: [feat(adapters): add google-adk runtime adapter](https://github.com/Molecule-AI/molecule-core/pull/550)
|
||||
- [Google ADK (adk-python)](https://github.com/google/adk-python)
|
||||
- [Gemini CLI runtime tutorial](./gemini-cli-runtime.md)
|
||||
- [Platform API reference](../api-reference.md)
|
||||
|
||||
@ -176,9 +176,9 @@ What is on the roadmap for Phase 2d (not yet shipped):
|
||||
|
||||
## Related
|
||||
|
||||
- PR #240: [Phase 2a — native Anthropic dispatch](https://git.moleculesai.app/molecule-ai/molecule-core/pull/240)
|
||||
- PR #255: [Phase 2b — native Gemini dispatch](https://git.moleculesai.app/molecule-ai/molecule-core/pull/255)
|
||||
- PR #267: [Phase 2c — multi-turn history on all paths](https://git.moleculesai.app/molecule-ai/molecule-core/pull/267)
|
||||
- PR #240: [Phase 2a — native Anthropic dispatch](https://github.com/Molecule-AI/molecule-core/pull/240)
|
||||
- PR #255: [Phase 2b — native Gemini dispatch](https://github.com/Molecule-AI/molecule-core/pull/255)
|
||||
- PR #267: [Phase 2c — multi-turn history on all paths](https://github.com/Molecule-AI/molecule-core/pull/267)
|
||||
- [Hermes adapter design](../adapters/hermes-adapter-design.md)
|
||||
- [Platform API reference](../api-reference.md)
|
||||
- Issue [#513](https://git.moleculesai.app/molecule-ai/molecule-core/issues/513)
|
||||
- Issue [#513](https://github.com/Molecule-AI/molecule-core/issues/513)
|
||||
|
||||
@ -90,6 +90,6 @@ Molecule AI canvas without code changes.
|
||||
|
||||
## Related
|
||||
|
||||
- PR #480: [feat(channels): Lark / Feishu channel adapter](https://git.moleculesai.app/molecule-ai/molecule-core/pull/480)
|
||||
- PR #480: [feat(channels): Lark / Feishu channel adapter](https://github.com/Molecule-AI/molecule-core/pull/480)
|
||||
- [Social channels architecture](../agent-runtime/social-channels.md)
|
||||
- [Channel adapter reference](../api-reference.md#channels)
|
||||
@ -98,14 +98,14 @@ Each of the 8 adapter template repos contains:
|
||||
|
||||
| Adapter | Repo |
|
||||
|---------|------|
|
||||
| claude-code | https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-claude-code |
|
||||
| langgraph | https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-langgraph |
|
||||
| crewai | https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-crewai |
|
||||
| autogen | https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-autogen |
|
||||
| deepagents | https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-deepagents |
|
||||
| hermes | https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-hermes |
|
||||
| gemini-cli | https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-gemini-cli |
|
||||
| openclaw | https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-openclaw |
|
||||
| claude-code | https://github.com/Molecule-AI/molecule-ai-workspace-template-claude-code |
|
||||
| langgraph | https://github.com/Molecule-AI/molecule-ai-workspace-template-langgraph |
|
||||
| crewai | https://github.com/Molecule-AI/molecule-ai-workspace-template-crewai |
|
||||
| autogen | https://github.com/Molecule-AI/molecule-ai-workspace-template-autogen |
|
||||
| deepagents | https://github.com/Molecule-AI/molecule-ai-workspace-template-deepagents |
|
||||
| hermes | https://github.com/Molecule-AI/molecule-ai-workspace-template-hermes |
|
||||
| gemini-cli | https://github.com/Molecule-AI/molecule-ai-workspace-template-gemini-cli |
|
||||
| openclaw | https://github.com/Molecule-AI/molecule-ai-workspace-template-openclaw |
|
||||
|
||||
## Adapter discovery (ADAPTER_MODULE)
|
||||
|
||||
@ -244,7 +244,7 @@ correctness before pushing a `runtime-v*` tag.
|
||||
## Writing a new adapter
|
||||
|
||||
Use the GitHub template repo
|
||||
[`molecule-ai/molecule-ai-workspace-template-starter`](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-starter) (note: the starter repo did not survive the 2026-05-06 GitHub-org-suspension migration; recreation tracked at internal#41)
|
||||
[`Molecule-AI/molecule-ai-workspace-template-starter`](https://github.com/Molecule-AI/molecule-ai-workspace-template-starter)
|
||||
— it ships with the canonical Dockerfile + adapter.py skeleton + config.yaml
|
||||
schema + the `repository_dispatch: [runtime-published]` cascade receiver
|
||||
already wired up. No follow-up setup PR required.
|
||||
@ -256,7 +256,7 @@ gh repo create Molecule-AI/molecule-ai-workspace-template-<runtime> \
|
||||
--public \
|
||||
--description "Molecule AI workspace template: <runtime>"
|
||||
|
||||
git clone https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-<runtime>.git
|
||||
git clone https://github.com/Molecule-AI/molecule-ai-workspace-template-<runtime>
|
||||
cd molecule-ai-workspace-template-<runtime>
|
||||
```
|
||||
|
||||
@ -286,7 +286,7 @@ After `git push`:
|
||||
If the canonical shape changes (e.g. `config.yaml` schema gets a new field,
|
||||
the `BaseAdapter` interface adds a method, the reusable CI workflow
|
||||
signature changes), update the
|
||||
[starter](https://git.moleculesai.app/molecule-ai/molecule-ai-workspace-template-starter) (recreation pending — see note above)
|
||||
[starter](https://github.com/Molecule-AI/molecule-ai-workspace-template-starter)
|
||||
**first**. Existing templates can either migrate at their own pace or be
|
||||
touched in a coordinated cleanup PR. Either way, future templates pick up
|
||||
the new shape from day one.
|
||||
|
||||
@ -1,46 +1,47 @@
|
||||
{
|
||||
"_comment": "OSS surface registry — every repo listed here MUST be public on git.moleculesai.app. Layer-3 customer/private templates are NOT registered here; they are handled at provision-time via the per-tenant credential resolver (see internal#102 RFC). 'main' refs are pinned to tags before broad rollout.",
|
||||
"_comment": "Pin refs to release tags for reproducible builds. 'main' is OK while all repos are internal.",
|
||||
"version": 1,
|
||||
"plugins": [
|
||||
{"name": "browser-automation", "repo": "molecule-ai/molecule-ai-plugin-browser-automation", "ref": "main"},
|
||||
{"name": "ecc", "repo": "molecule-ai/molecule-ai-plugin-ecc", "ref": "main"},
|
||||
{"name": "gh-identity", "repo": "molecule-ai/molecule-ai-plugin-gh-identity", "ref": "main"},
|
||||
{"name": "molecule-audit", "repo": "molecule-ai/molecule-ai-plugin-molecule-audit", "ref": "main"},
|
||||
{"name": "molecule-audit-trail", "repo": "molecule-ai/molecule-ai-plugin-molecule-audit-trail", "ref": "main"},
|
||||
{"name": "molecule-careful-bash", "repo": "molecule-ai/molecule-ai-plugin-molecule-careful-bash", "ref": "main"},
|
||||
{"name": "molecule-compliance", "repo": "molecule-ai/molecule-ai-plugin-molecule-compliance", "ref": "main"},
|
||||
{"name": "molecule-dev", "repo": "molecule-ai/molecule-ai-plugin-molecule-dev", "ref": "main"},
|
||||
{"name": "molecule-freeze-scope", "repo": "molecule-ai/molecule-ai-plugin-molecule-freeze-scope", "ref": "main"},
|
||||
{"name": "molecule-hitl", "repo": "molecule-ai/molecule-ai-plugin-molecule-hitl", "ref": "main"},
|
||||
{"name": "molecule-prompt-watchdog", "repo": "molecule-ai/molecule-ai-plugin-molecule-prompt-watchdog", "ref": "main"},
|
||||
{"name": "molecule-security-scan", "repo": "molecule-ai/molecule-ai-plugin-molecule-security-scan", "ref": "main"},
|
||||
{"name": "molecule-session-context", "repo": "molecule-ai/molecule-ai-plugin-molecule-session-context", "ref": "main"},
|
||||
{"name": "molecule-skill-code-review", "repo": "molecule-ai/molecule-ai-plugin-molecule-skill-code-review", "ref": "main"},
|
||||
{"name": "molecule-skill-cron-learnings", "repo": "molecule-ai/molecule-ai-plugin-molecule-skill-cron-learnings", "ref": "main"},
|
||||
{"name": "molecule-skill-cross-vendor-review", "repo": "molecule-ai/molecule-ai-plugin-molecule-skill-cross-vendor-review", "ref": "main"},
|
||||
{"name": "molecule-skill-llm-judge", "repo": "molecule-ai/molecule-ai-plugin-molecule-skill-llm-judge", "ref": "main"},
|
||||
{"name": "molecule-skill-update-docs", "repo": "molecule-ai/molecule-ai-plugin-molecule-skill-update-docs", "ref": "main"},
|
||||
{"name": "molecule-workflow-retro", "repo": "molecule-ai/molecule-ai-plugin-molecule-workflow-retro", "ref": "main"},
|
||||
{"name": "molecule-workflow-triage", "repo": "molecule-ai/molecule-ai-plugin-molecule-workflow-triage", "ref": "main"},
|
||||
{"name": "superpowers", "repo": "molecule-ai/molecule-ai-plugin-superpowers", "ref": "main"}
|
||||
{"name": "browser-automation", "repo": "Molecule-AI/molecule-ai-plugin-browser-automation", "ref": "main"},
|
||||
{"name": "ecc", "repo": "Molecule-AI/molecule-ai-plugin-ecc", "ref": "main"},
|
||||
{"name": "gh-identity", "repo": "Molecule-AI/molecule-ai-plugin-gh-identity", "ref": "main"},
|
||||
{"name": "molecule-audit", "repo": "Molecule-AI/molecule-ai-plugin-molecule-audit", "ref": "main"},
|
||||
{"name": "molecule-audit-trail", "repo": "Molecule-AI/molecule-ai-plugin-molecule-audit-trail", "ref": "main"},
|
||||
{"name": "molecule-careful-bash", "repo": "Molecule-AI/molecule-ai-plugin-molecule-careful-bash", "ref": "main"},
|
||||
{"name": "molecule-compliance", "repo": "Molecule-AI/molecule-ai-plugin-molecule-compliance", "ref": "main"},
|
||||
{"name": "molecule-dev", "repo": "Molecule-AI/molecule-ai-plugin-molecule-dev", "ref": "main"},
|
||||
{"name": "molecule-freeze-scope", "repo": "Molecule-AI/molecule-ai-plugin-molecule-freeze-scope", "ref": "main"},
|
||||
{"name": "molecule-hitl", "repo": "Molecule-AI/molecule-ai-plugin-molecule-hitl", "ref": "main"},
|
||||
{"name": "molecule-prompt-watchdog", "repo": "Molecule-AI/molecule-ai-plugin-molecule-prompt-watchdog", "ref": "main"},
|
||||
{"name": "molecule-security-scan", "repo": "Molecule-AI/molecule-ai-plugin-molecule-security-scan", "ref": "main"},
|
||||
{"name": "molecule-session-context", "repo": "Molecule-AI/molecule-ai-plugin-molecule-session-context", "ref": "main"},
|
||||
{"name": "molecule-skill-code-review", "repo": "Molecule-AI/molecule-ai-plugin-molecule-skill-code-review", "ref": "main"},
|
||||
{"name": "molecule-skill-cron-learnings", "repo": "Molecule-AI/molecule-ai-plugin-molecule-skill-cron-learnings", "ref": "main"},
|
||||
{"name": "molecule-skill-cross-vendor-review", "repo": "Molecule-AI/molecule-ai-plugin-molecule-skill-cross-vendor-review", "ref": "main"},
|
||||
{"name": "molecule-skill-llm-judge", "repo": "Molecule-AI/molecule-ai-plugin-molecule-skill-llm-judge", "ref": "main"},
|
||||
{"name": "molecule-skill-update-docs", "repo": "Molecule-AI/molecule-ai-plugin-molecule-skill-update-docs", "ref": "main"},
|
||||
{"name": "molecule-workflow-retro", "repo": "Molecule-AI/molecule-ai-plugin-molecule-workflow-retro", "ref": "main"},
|
||||
{"name": "molecule-workflow-triage", "repo": "Molecule-AI/molecule-ai-plugin-molecule-workflow-triage", "ref": "main"},
|
||||
{"name": "superpowers", "repo": "Molecule-AI/molecule-ai-plugin-superpowers", "ref": "main"}
|
||||
],
|
||||
"workspace_templates": [
|
||||
{"name": "claude-code-default", "repo": "molecule-ai/molecule-ai-workspace-template-claude-code", "ref": "main"},
|
||||
{"name": "hermes", "repo": "molecule-ai/molecule-ai-workspace-template-hermes", "ref": "main"},
|
||||
{"name": "openclaw", "repo": "molecule-ai/molecule-ai-workspace-template-openclaw", "ref": "main"},
|
||||
{"name": "codex", "repo": "molecule-ai/molecule-ai-workspace-template-codex", "ref": "main"},
|
||||
{"name": "langgraph", "repo": "molecule-ai/molecule-ai-workspace-template-langgraph", "ref": "main"},
|
||||
{"name": "crewai", "repo": "molecule-ai/molecule-ai-workspace-template-crewai", "ref": "main"},
|
||||
{"name": "autogen", "repo": "molecule-ai/molecule-ai-workspace-template-autogen", "ref": "main"},
|
||||
{"name": "deepagents", "repo": "molecule-ai/molecule-ai-workspace-template-deepagents", "ref": "main"},
|
||||
{"name": "gemini-cli", "repo": "molecule-ai/molecule-ai-workspace-template-gemini-cli", "ref": "main"}
|
||||
{"name": "claude-code-default", "repo": "Molecule-AI/molecule-ai-workspace-template-claude-code", "ref": "main"},
|
||||
{"name": "hermes", "repo": "Molecule-AI/molecule-ai-workspace-template-hermes", "ref": "main"},
|
||||
{"name": "openclaw", "repo": "Molecule-AI/molecule-ai-workspace-template-openclaw", "ref": "main"},
|
||||
{"name": "codex", "repo": "Molecule-AI/molecule-ai-workspace-template-codex", "ref": "main"},
|
||||
{"name": "langgraph", "repo": "Molecule-AI/molecule-ai-workspace-template-langgraph", "ref": "main"},
|
||||
{"name": "crewai", "repo": "Molecule-AI/molecule-ai-workspace-template-crewai", "ref": "main"},
|
||||
{"name": "autogen", "repo": "Molecule-AI/molecule-ai-workspace-template-autogen", "ref": "main"},
|
||||
{"name": "deepagents", "repo": "Molecule-AI/molecule-ai-workspace-template-deepagents", "ref": "main"},
|
||||
{"name": "gemini-cli", "repo": "Molecule-AI/molecule-ai-workspace-template-gemini-cli", "ref": "main"}
|
||||
],
|
||||
"org_templates": [
|
||||
{"name": "molecule-dev", "repo": "molecule-ai/molecule-ai-org-template-molecule-dev", "ref": "main"},
|
||||
{"name": "free-beats-all", "repo": "molecule-ai/molecule-ai-org-template-free-beats-all", "ref": "main"},
|
||||
{"name": "medo-smoke", "repo": "molecule-ai/molecule-ai-org-template-medo-smoke", "ref": "main"},
|
||||
{"name": "molecule-worker-gemini", "repo": "molecule-ai/molecule-ai-org-template-molecule-worker-gemini", "ref": "main"},
|
||||
{"name": "ux-ab-lab", "repo": "molecule-ai/molecule-ai-org-template-ux-ab-lab", "ref": "main"},
|
||||
{"name": "mock-bigorg", "repo": "molecule-ai/molecule-ai-org-template-mock-bigorg", "ref": "main"}
|
||||
{"name": "molecule-dev", "repo": "Molecule-AI/molecule-ai-org-template-molecule-dev", "ref": "main"},
|
||||
{"name": "free-beats-all", "repo": "Molecule-AI/molecule-ai-org-template-free-beats-all", "ref": "main"},
|
||||
{"name": "medo-smoke", "repo": "Molecule-AI/molecule-ai-org-template-medo-smoke", "ref": "main"},
|
||||
{"name": "molecule-worker-gemini", "repo": "Molecule-AI/molecule-ai-org-template-molecule-worker-gemini", "ref": "main"},
|
||||
{"name": "reno-stars", "repo": "Molecule-AI/molecule-ai-org-template-reno-stars", "ref": "main"},
|
||||
{"name": "ux-ab-lab", "repo": "Molecule-AI/molecule-ai-org-template-ux-ab-lab", "ref": "main"},
|
||||
{"name": "mock-bigorg", "repo": "Molecule-AI/molecule-ai-org-template-mock-bigorg", "ref": "main"}
|
||||
]
|
||||
}
|
||||
|
||||
@ -11,7 +11,7 @@ There are three related scripts; pick the right one:
|
||||
|---|---|---|
|
||||
| `measure-coordinator-task-bounds.sh` | **Canonical** v1 harness for the RFC #2251 / Issue 4 reproduction. Provisions a PM coordinator + Researcher child via `claude-code-default` + `langgraph` templates, sends a synthesis-heavy A2A kickoff, observes elapsed time + activity trace. | OSS-shape platform — localhost or any `/workspaces`-shaped endpoint. Has tenant/admin-token guards for non-localhost runs. |
|
||||
| `measure-coordinator-task-bounds-runner.sh` | Generalised runner for the same measurement contract but with **arbitrary template + secret + model combinations** (Hermes/MiniMax, etc.). Useful for cross-runtime variants without modifying the canonical harness. | Same as above (local or SaaS via `MODE=saas`). |
|
||||
| `measure-coordinator-task-bounds.sh` (in [molecule-controlplane](https://git.moleculesai.app/molecule-ai/molecule-controlplane)) | **Production-shape** variant that bootstraps a real staging tenant via `POST /cp/admin/orgs`, then runs the same measurement against `<slug>.staging.moleculesai.app`. | Staging controlplane only — refuses to run against production. |
|
||||
| `measure-coordinator-task-bounds.sh` (in [molecule-controlplane](https://github.com/Molecule-AI/molecule-controlplane)) | **Production-shape** variant that bootstraps a real staging tenant via `POST /cp/admin/orgs`, then runs the same measurement against `<slug>.staging.moleculesai.app`. | Staging controlplane only — refuses to run against production. |
|
||||
|
||||
See `reference_harness_pair_pattern` (auto-memory) for when to use which
|
||||
and the cross-repo design rationale.
|
||||
|
||||
@ -278,7 +278,7 @@ include = ["molecule_runtime*"]
|
||||
README_TEMPLATE = """\
|
||||
# molecule-ai-workspace-runtime
|
||||
|
||||
Shared workspace runtime for [Molecule AI](https://git.moleculesai.app/molecule-ai/molecule-core)
|
||||
Shared workspace runtime for [Molecule AI](https://github.com/Molecule-AI/molecule-core)
|
||||
agent adapters. Installed by every workspace template image
|
||||
(`workspace-template-claude-code`, `-langgraph`, `-hermes`, etc.) to provide
|
||||
A2A delegation, heartbeat, memory, plugin loading, and skill management.
|
||||
@ -376,7 +376,7 @@ hold:
|
||||
non-plugin-sourced server, which Claude Code rejects with
|
||||
`channel_enable requires a marketplace plugin`. Until the
|
||||
official `moleculesai/claude-code-plugin` marketplace lands
|
||||
(tracking [#2936](https://git.moleculesai.app/molecule-ai/molecule-core/issues/2936)),
|
||||
(tracking [#2936](https://github.com/Molecule-AI/molecule-core/issues/2936)),
|
||||
operators who want push must scaffold their own local marketplace
|
||||
under
|
||||
`~/.claude/marketplaces/molecule-local/` containing a
|
||||
@ -389,14 +389,14 @@ hold:
|
||||
Symptom of any condition failing: messages arrive but only via the
|
||||
poll path (every ~1–60s), not real-time. There's currently no
|
||||
diagnostic surfaced — `molecule-mcp doctor` (tracking
|
||||
[#2937](https://git.moleculesai.app/molecule-ai/molecule-core/issues/2937)) is
|
||||
[#2937](https://github.com/Molecule-AI/molecule-core/issues/2937)) is
|
||||
planned.
|
||||
|
||||
If you don't need real-time push, the default poll path works
|
||||
universally with no extra setup; both modes converge on the same
|
||||
`inbox_pop` ack so messages never duplicate.
|
||||
|
||||
See [`docs/workspace-runtime-package.md`](https://git.moleculesai.app/molecule-ai/molecule-core/src/branch/main/docs/workspace-runtime-package.md)
|
||||
See [`docs/workspace-runtime-package.md`](https://github.com/Molecule-AI/molecule-core/blob/main/docs/workspace-runtime-package.md)
|
||||
for the publish flow and architecture.
|
||||
"""
|
||||
|
||||
|
||||
@ -17,23 +17,12 @@
|
||||
#
|
||||
# Used by .github/workflows/auto-promote-stale-alarm.yml. Logic lives
|
||||
# here (not inline in the workflow YAML) so we can:
|
||||
# - Unit-test it with a fixture (see test-check-stale-promote-pr.sh)
|
||||
# - Unit-test it with a stubbed `gh` (see test-check-stale-promote-pr.sh)
|
||||
# - Run it ad-hoc by an operator: `scripts/check-stale-promote-pr.sh`
|
||||
# - Reuse the same surface in any sibling workflow that needs the same
|
||||
# check (SSOT — one detector, many callers).
|
||||
#
|
||||
# Requires: `curl`, `jq`. `GITEA_TOKEN` (or `GITHUB_TOKEN` / `GH_TOKEN`
|
||||
# for back-compat) in the workflow context. Reads `GITHUB_SERVER_URL`
|
||||
# / `GITEA_API_URL` for the Gitea base, defaulting to
|
||||
# https://git.moleculesai.app/api/v1.
|
||||
#
|
||||
# Post-2026-05-06 (Gitea migration, issue #75): the previous version
|
||||
# called `gh pr list/view/comment`, all of which hit GitHub.com's
|
||||
# GraphQL or /api/v3 REST shapes. Gitea exposes /api/v1/ only (no
|
||||
# GraphQL → 405, no /api/v3 → 404). So this script now talks to the
|
||||
# Gitea v1 API directly via curl. The fixture-driven unit tests are
|
||||
# unchanged — they bypass the live fetch via PR_FIXTURE and still pass
|
||||
# the historical (GitHub-shape) JSON which `detect_stale` consumes.
|
||||
# Requires: `gh` CLI, `jq`. `GH_TOKEN` env in the workflow context.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
@ -47,15 +36,14 @@ set -euo pipefail
|
||||
# alarming. Override via env for tests + edge ops.
|
||||
STALE_HOURS="${STALE_HOURS:-4}"
|
||||
|
||||
# Repo defaults to GITHUB_REPOSITORY (act_runner sets this in workflow
|
||||
# context). Tests pass --repo explicitly.
|
||||
# Repo defaults to the current `gh` context. Tests pass --repo explicitly.
|
||||
REPO="${GITHUB_REPOSITORY:-}"
|
||||
|
||||
# Whether to post a comment to the PR. Off by default to avoid noise on
|
||||
# manual ad-hoc runs; the cron workflow turns it on.
|
||||
POST_COMMENT="${POST_COMMENT:-false}"
|
||||
|
||||
# Where to read the open-PR JSON from. Empty = call Gitea live. Tests
|
||||
# Where to read the open-PR JSON from. Empty = call `gh` live. Tests
|
||||
# point this at a fixture file.
|
||||
PR_FIXTURE="${PR_FIXTURE:-}"
|
||||
|
||||
@ -63,17 +51,6 @@ PR_FIXTURE="${PR_FIXTURE:-}"
|
||||
# the staleness math is deterministic.
|
||||
NOW_OVERRIDE="${NOW_OVERRIDE:-}"
|
||||
|
||||
# Gitea API base. act_runner forwards github.server_url as
|
||||
# GITHUB_SERVER_URL; for the molecule-ai fleet that's
|
||||
# https://git.moleculesai.app. Append /api/v1 to get the REST root.
|
||||
# Override directly via GITEA_API_URL for tests / non-default hosts.
|
||||
GITEA_API_URL="${GITEA_API_URL:-${GITHUB_SERVER_URL:-https://git.moleculesai.app}/api/v1}"
|
||||
|
||||
# Token. Workflow context sets GITHUB_TOKEN; we accept GITEA_TOKEN as
|
||||
# the explicit name and GH_TOKEN for back-compat with operator habits
|
||||
# from the GitHub era. First non-empty wins.
|
||||
GITEA_TOKEN="${GITEA_TOKEN:-${GITHUB_TOKEN:-${GH_TOKEN:-}}}"
|
||||
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in
|
||||
--repo) REPO="$2"; shift 2 ;;
|
||||
@ -106,7 +83,7 @@ now_epoch() {
|
||||
fi
|
||||
}
|
||||
|
||||
# Parse RFC3339 timestamps the way Gitea / GitHub emit them (e.g.
|
||||
# Parse RFC3339 timestamps the way GitHub emits them (e.g.
|
||||
# "2026-05-05T23:15:00Z"). gnu-date uses -d, bsd-date uses -j -f. Cover
|
||||
# both because the workflow runs on ubuntu-latest (gnu) but operators
|
||||
# may run this script on macOS (bsd).
|
||||
@ -129,100 +106,14 @@ to_epoch() {
|
||||
# Fetch open auto-promote PRs
|
||||
# -----------------------------------------------------------------------------
|
||||
|
||||
# Gitea v1 returns PRs with the canonical Gitea shape (number, title,
|
||||
# created_at, html_url, mergeable, state). The previous GitHub-CLI
|
||||
# version returned a derived `mergeStateStatus` / `reviewDecision`
|
||||
# pair which only GitHub computes — Gitea doesn't expose them
|
||||
# natively. Rebuild equivalents:
|
||||
#
|
||||
# mergeStateStatus = BLOCKED ↔ Gitea: state==open AND mergeable==true
|
||||
# AND no APPROVED review yet
|
||||
# (i.e. branch protection is gating
|
||||
# the auto-merge pending an approval)
|
||||
# reviewDecision = REVIEW_REQUIRED ↔ Gitea: 0 APPROVED reviews
|
||||
#
|
||||
# This mirrors the SAME silent-block failure mode the GitHub version
|
||||
# detected: auto-merge armed, branch protection requires 1 review,
|
||||
# nobody's approved yet.
|
||||
#
|
||||
# Implementation: pull the open PR list base=main, then for each PR
|
||||
# pull /pulls/{n}/reviews and synthesize the GitHub-shape JSON the
|
||||
# rest of the script + the test fixtures consume.
|
||||
fetch_prs() {
|
||||
if [ -n "$PR_FIXTURE" ]; then
|
||||
cat "$PR_FIXTURE"
|
||||
return 0
|
||||
fi
|
||||
if [ -z "$GITEA_TOKEN" ]; then
|
||||
echo "::error::GITEA_TOKEN / GITHUB_TOKEN unset — cannot fetch PRs from $GITEA_API_URL" >&2
|
||||
return 1
|
||||
fi
|
||||
local prs_json
|
||||
prs_json="$(curl --fail-with-body -sS \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Accept: application/json" \
|
||||
"${GITEA_API_URL}/repos/${REPO}/pulls?state=open&base=main&limit=50" \
|
||||
2>/dev/null)" || {
|
||||
echo "::error::Failed to fetch PRs from ${GITEA_API_URL}/repos/${REPO}/pulls" >&2
|
||||
return 1
|
||||
}
|
||||
|
||||
# Filter to head=staging (the auto-promote shape) and synthesize
|
||||
# mergeStateStatus + reviewDecision per PR. Approval count via
|
||||
# /pulls/{n}/reviews. Errors fall through to 0-approvals (treated
|
||||
# as REVIEW_REQUIRED) preserving the existing "fail-safe — alarm if
|
||||
# uncertain" semantic.
|
||||
local synthesized="[]"
|
||||
while IFS= read -r pr; do
|
||||
[ -z "$pr" ] && continue
|
||||
[ "$pr" = "null" ] && continue
|
||||
local num
|
||||
num="$(printf '%s' "$pr" | jq -r '.number')"
|
||||
[ -z "$num" ] && continue
|
||||
[ "$num" = "null" ] && continue
|
||||
local approved_count
|
||||
approved_count="$(curl --fail-with-body -sS \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Accept: application/json" \
|
||||
"${GITEA_API_URL}/repos/${REPO}/pulls/${num}/reviews" 2>/dev/null \
|
||||
| jq '[.[] | select(.state == "APPROVED" and (.dismissed // false) == false)] | length' \
|
||||
2>/dev/null || echo 0)"
|
||||
local mergeable
|
||||
mergeable="$(printf '%s' "$pr" | jq -r '.mergeable')"
|
||||
local merge_state="UNKNOWN"
|
||||
local review_decision="REVIEW_REQUIRED"
|
||||
if [ "$mergeable" = "true" ]; then
|
||||
if [ "$approved_count" -ge 1 ]; then
|
||||
merge_state="CLEAN"
|
||||
review_decision="APPROVED"
|
||||
else
|
||||
# mergeable but no approving review — exactly the wedge state
|
||||
# the alarm targets.
|
||||
merge_state="BLOCKED"
|
||||
review_decision="REVIEW_REQUIRED"
|
||||
fi
|
||||
else
|
||||
# not mergeable (conflicts, behind, failed checks) — different
|
||||
# failure mode, the author owns the fix; the alarm doesn't fire.
|
||||
merge_state="DIRTY"
|
||||
review_decision="REVIEW_REQUIRED"
|
||||
fi
|
||||
synthesized="$(printf '%s' "$synthesized" \
|
||||
| jq -c --argjson pr "$pr" \
|
||||
--arg ms "$merge_state" \
|
||||
--arg rd "$review_decision" \
|
||||
'. + [{
|
||||
number: $pr.number,
|
||||
title: $pr.title,
|
||||
createdAt: $pr.created_at,
|
||||
mergeStateStatus: $ms,
|
||||
reviewDecision: $rd,
|
||||
url: $pr.html_url
|
||||
}]')"
|
||||
done < <(printf '%s' "$prs_json" \
|
||||
| jq -c '.[] | select(.head.ref == "staging")' 2>/dev/null)
|
||||
|
||||
printf '%s\n' "$synthesized"
|
||||
gh pr list --repo "$REPO" \
|
||||
--base main --head staging --state open \
|
||||
--json number,title,createdAt,mergeStateStatus,reviewDecision,url
|
||||
}
|
||||
|
||||
# -----------------------------------------------------------------------------
|
||||
@ -280,40 +171,18 @@ post_comment() {
|
||||
if [ "$POST_COMMENT" != "true" ]; then
|
||||
return 0
|
||||
fi
|
||||
if [ -z "$GITEA_TOKEN" ]; then
|
||||
echo "::warning::GITEA_TOKEN unset — cannot post stale-alarm comment on PR #$pr_num" >&2
|
||||
return 0
|
||||
fi
|
||||
# Idempotency: only one alarm comment per PR. Look for the marker
|
||||
# string in existing comments before posting a new one. Gitea's
|
||||
# /repos/{owner}/{repo}/issues/{n}/comments returns the same shape
|
||||
# for issues + PRs (PRs are issues internally on Gitea, same as
|
||||
# GitHub's REST).
|
||||
# string in existing comments before posting a new one.
|
||||
local existing
|
||||
existing="$(curl --fail-with-body -sS \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Accept: application/json" \
|
||||
"${GITEA_API_URL}/repos/${REPO}/issues/${pr_num}/comments?limit=50" 2>/dev/null \
|
||||
| jq -r '.[] | select(.body | test("scripts/check-stale-promote-pr.sh per issue #2975")) | .id' \
|
||||
existing="$(gh pr view "$pr_num" --repo "$REPO" --json comments \
|
||||
--jq '.comments[] | select(.body | test("scripts/check-stale-promote-pr.sh per issue #2975")) | .databaseId' \
|
||||
| head -n1)"
|
||||
if [ -n "$existing" ]; then
|
||||
echo "::notice::PR #$pr_num already has a stale-alarm comment ($existing) — not re-posting"
|
||||
return 0
|
||||
fi
|
||||
local body
|
||||
body="$(comment_body "$age_h")"
|
||||
if curl --fail-with-body -sS \
|
||||
-X POST \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Accept: application/json" \
|
||||
-H "Content-Type: application/json" \
|
||||
"${GITEA_API_URL}/repos/${REPO}/issues/${pr_num}/comments" \
|
||||
-d "$(jq -nc --arg b "$body" '{body: $b}')" \
|
||||
>/dev/null 2>&1; then
|
||||
echo "::notice::Posted stale-alarm comment on PR #$pr_num (age=${age_h}h)"
|
||||
else
|
||||
echo "::warning::Failed to POST stale-alarm comment on PR #$pr_num" >&2
|
||||
fi
|
||||
comment_body "$age_h" | gh pr comment "$pr_num" --repo "$REPO" --body-file -
|
||||
echo "::notice::Posted stale-alarm comment on PR #$pr_num (age=${age_h}h)"
|
||||
}
|
||||
|
||||
# -----------------------------------------------------------------------------
|
||||
|
||||
@ -8,24 +8,27 @@
|
||||
# Requires: git, jq (lighter than python3 — ~2MB vs ~50MB in Alpine)
|
||||
#
|
||||
# Auth (optional):
|
||||
# Post-2026-05-08 (#192): every repo in manifest.json is public on
|
||||
# git.moleculesai.app. Anonymous clone works for the entire registered
|
||||
# set. The OSS-surface contract is recorded in manifest.json's _comment
|
||||
# — Layer-3 customer/private templates (e.g. reno-stars) are NOT in the
|
||||
# manifest; they are handled at provision-time via the per-tenant
|
||||
# credential resolver (internal#102 RFC).
|
||||
# When MOLECULE_GITEA_TOKEN is set, embed it as the basic-auth password so
|
||||
# private Gitea repos clone successfully. When unset, clone anonymously
|
||||
# (works only for repos that are public on git.moleculesai.app).
|
||||
#
|
||||
# MOLECULE_GITEA_TOKEN is therefore optional today. Kept supported for
|
||||
# two reasons: (a) historical CI configs that still inject
|
||||
# AUTO_SYNC_TOKEN remain harmless, (b) reserved for the case where a
|
||||
# private internal-only template is later registered via a ci-readonly
|
||||
# team grant — review must explicitly sign off on that, since it
|
||||
# violates the public-OSS-surface contract.
|
||||
# This is the path the publish-workspace-server-image.yml workflow uses:
|
||||
# it injects AUTO_SYNC_TOKEN (devops-engineer persona PAT, repo:read on
|
||||
# the molecule-ai org) so the in-CI pre-clone step succeeds for ALL
|
||||
# manifest entries — including the 5 private workspace-template-* repos
|
||||
# (codex, crewai, deepagents, gemini-cli, langgraph) and all 7
|
||||
# org-template-* repos.
|
||||
#
|
||||
# The token (when set) never enters the Docker image: this script runs
|
||||
# in the trusted CI context BEFORE `docker buildx build`, populates
|
||||
# The token never enters the Docker image: this script runs in the
|
||||
# trusted CI context BEFORE `docker buildx build`, populates
|
||||
# .tenant-bundle-deps/, then `Dockerfile.tenant` COPYs from there with
|
||||
# the .git directories already stripped (see line ~67 below).
|
||||
#
|
||||
# For backward compatibility — and so a fresh clone works without
|
||||
# secrets when (eventually) the workspace-template-* repos flip public —
|
||||
# the unset path remains a plain anonymous HTTPS clone. That path will
|
||||
# FAIL with "could not read Username" on private repos today; CI MUST
|
||||
# set MOLECULE_GITEA_TOKEN.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
@ -65,19 +68,22 @@ clone_category() {
|
||||
continue
|
||||
fi
|
||||
|
||||
# Post-2026-05-06 GitHub-org-suspension: clone from Gitea instead.
|
||||
# manifest.json paths still read "Molecule-AI/..." (the historic
|
||||
# github.com slug); Gitea lowercases the org part to "molecule-ai/".
|
||||
# Lowercase the org segment on the fly so we don't need to rewrite
|
||||
# every manifest entry.
|
||||
repo_gitea="$(echo "$repo" | awk -F/ '{ printf "%s", tolower($1); for (i=2; i<=NF; i++) printf "/%s", $i; print "" }')"
|
||||
|
||||
# Build the clone URL. When MOLECULE_GITEA_TOKEN is set (CI path)
|
||||
# embed it as basic-auth so private repos succeed. The username
|
||||
# part ("oauth2") is conventional and ignored by Gitea — only the
|
||||
# token-as-password is verified.
|
||||
#
|
||||
# manifest.json was migrated to lowercase org slugs on
|
||||
# 2026-05-07 (post-suspension reconciliation), so we use $repo
|
||||
# verbatim — no on-the-fly tolower transform needed.
|
||||
if [ -n "${MOLECULE_GITEA_TOKEN:-}" ]; then
|
||||
clone_url="https://oauth2:${MOLECULE_GITEA_TOKEN}@git.moleculesai.app/${repo}.git"
|
||||
display_url="https://oauth2:***@git.moleculesai.app/${repo}.git"
|
||||
clone_url="https://oauth2:${MOLECULE_GITEA_TOKEN}@git.moleculesai.app/${repo_gitea}.git"
|
||||
display_url="https://oauth2:***@git.moleculesai.app/${repo_gitea}.git"
|
||||
else
|
||||
clone_url="https://git.moleculesai.app/${repo}.git"
|
||||
clone_url="https://git.moleculesai.app/${repo_gitea}.git"
|
||||
display_url="$clone_url"
|
||||
fi
|
||||
|
||||
|
||||
@ -10,11 +10,11 @@
|
||||
# → PyPI auto-bumps molecule-ai-workspace-runtime patch version
|
||||
# → repository_dispatch fans out to 8 workspace-template-* repos
|
||||
# → each template repo rebuilds and re-tags
|
||||
# 153263036946.dkr.ecr.us-east-2.amazonaws.com/molecule-ai/workspace-template-<runtime>:latest
|
||||
# ghcr.io/molecule-ai/workspace-template-<runtime>:latest
|
||||
#
|
||||
# PATH 2: any merge to a workspace-template-* repo's main branch
|
||||
# → that repo's publish-image.yml fires
|
||||
# → 153263036946.dkr.ecr.us-east-2.amazonaws.com/molecule-ai/workspace-template-<runtime>:latest
|
||||
# → ghcr.io/molecule-ai/workspace-template-<runtime>:latest
|
||||
# gets re-tagged
|
||||
#
|
||||
# provisioner.go:296 RuntimeImages[runtime] reads `:latest` at every
|
||||
|
||||
@ -1,155 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# edge-429-probe.sh — capture 429 origin (workspace-server vs CF/Vercel edge)
|
||||
# during a simulated canvas-burst against a tenant subdomain.
|
||||
#
|
||||
# Issue molecule-core#62. The post-#60 verification step asks an
|
||||
# operator with CF/Vercel dashboard access to confirm whether the
|
||||
# layout-chunk 429s observed in DevTools were:
|
||||
# (a) workspace-server bucket overflow (closes once #60 deploys), or
|
||||
# (b) actual edge-layer rate-limiting (CF or Vercel).
|
||||
#
|
||||
# This script doesn't need dashboard access. It reproduces the burst
|
||||
# pattern locally and dumps every 429's response shape so the operator
|
||||
# can distinguish (a) from (b) by inspection: workspace-server emits a
|
||||
# JSON body, CF emits HTML, Vercel emits a different HTML. Headers tell
|
||||
# the same story (cf-ray vs x-vercel-*).
|
||||
#
|
||||
# Usage:
|
||||
# ./scripts/edge-429-probe.sh <tenant-host> [--burst N] [--waves N] [--pause SECS] [--out file]
|
||||
#
|
||||
# Example:
|
||||
# ./scripts/edge-429-probe.sh hongming.moleculesai.app --burst 80 --out /tmp/edge.txt
|
||||
#
|
||||
# The script is read-only against the target — it only issues GETs to
|
||||
# public-by-design endpoints. No mutating requests, no credential use.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
# ── Help / usage handling first, before positional capture ────────────────────
|
||||
case "${1:-}" in
|
||||
-h|--help|"")
|
||||
sed -n '/^# edge-429-probe.sh/,/^$/p' "$0" | sed 's/^# \{0,1\}//'
|
||||
exit 0
|
||||
;;
|
||||
esac
|
||||
|
||||
HOST="$1"; shift
|
||||
BURST=80
|
||||
WAVES=3
|
||||
WAVE_PAUSE=2
|
||||
OUT=""
|
||||
|
||||
while [ "${1:-}" != "" ]; do
|
||||
case "$1" in
|
||||
--burst) BURST="$2"; shift 2 ;;
|
||||
--waves) WAVES="$2"; shift 2 ;;
|
||||
--pause) WAVE_PAUSE="$2"; shift 2 ;;
|
||||
--out) OUT="$2"; shift 2 ;;
|
||||
-h|--help)
|
||||
sed -n '/^# edge-429-probe.sh/,/^$/p' "$0" | sed 's/^# \{0,1\}//'
|
||||
exit 0
|
||||
;;
|
||||
*) echo "unknown arg: $1" >&2; exit 2 ;;
|
||||
esac
|
||||
done
|
||||
|
||||
# ── Endpoint discovery ────────────────────────────────────────────────────────
|
||||
echo "→ Discovering a layout-chunk URL from canvas root..." >&2
|
||||
ROOT_BODY=$(curl -fsSL --max-time 10 "https://${HOST}/" 2>/dev/null || true)
|
||||
LAYOUT_PATH=$(echo "$ROOT_BODY" \
|
||||
| grep -oE '/_next/static/chunks/layout-[A-Za-z0-9_-]+\.js' \
|
||||
| head -1 || true)
|
||||
if [ -z "$LAYOUT_PATH" ]; then
|
||||
LAYOUT_PATH="/_next/static/chunks/layout-probe-not-found.js"
|
||||
echo " (no layout chunk discovered — using sentinel path; 404 on this is expected)" >&2
|
||||
else
|
||||
echo " layout chunk: $LAYOUT_PATH" >&2
|
||||
fi
|
||||
|
||||
# Probe URL: a generic activity endpoint. The rate-limiter middleware
|
||||
# runs BEFORE workspace-id validation, so unauth/invalid-id requests
|
||||
# still hit the bucket.
|
||||
ACTIVITY_PATH="/workspaces/00000000-0000-0000-0000-000000000000/activity?probe=edge-429"
|
||||
|
||||
# ── Fire one curl, write a single-line JSON-ish status record to stdout ──────
|
||||
# Inlined into xargs as a heredoc-style command rather than a function so
|
||||
# the function-export pitfalls (some shells lose `export -f` across xargs)
|
||||
# don't apply. Each output line is a parseable record; failed curls emit
|
||||
# a curl_err record so request volume is preserved.
|
||||
TMP_RESULTS="$(mktemp -t edge-429-probe.XXXXXX)"
|
||||
trap 'rm -f "$TMP_RESULTS"' EXIT
|
||||
|
||||
run_burst() {
|
||||
# $1 = path; $2 = label; $3 = wave_id
|
||||
local path="$1" label="$2" wave="$3"
|
||||
local i
|
||||
for i in $(seq 1 "$BURST"); do
|
||||
{
|
||||
out=$(curl -sS --max-time 10 -o /dev/null \
|
||||
-w 'status=%{http_code} size=%{size_download} time=%{time_total} server=%{header.server} cf_ray=%{header.cf-ray} x_vercel=%{header.x-vercel-id} retry_after=%{header.retry-after} content_type=%{header.content-type} x_ratelimit_limit=%{header.x-ratelimit-limit} x_ratelimit_remaining=%{header.x-ratelimit-remaining} x_ratelimit_reset=%{header.x-ratelimit-reset}\n' \
|
||||
"https://${HOST}${path}" 2>/dev/null) || out="status=curl_err"
|
||||
printf 'label=%s-%s-%s %s\n' "$label" "$wave" "$i" "$out" >> "$TMP_RESULTS"
|
||||
} &
|
||||
done
|
||||
wait
|
||||
}
|
||||
|
||||
emit() {
|
||||
if [ -n "$OUT" ]; then
|
||||
printf '%s\n' "$*" >> "$OUT"
|
||||
else
|
||||
printf '%s\n' "$*"
|
||||
fi
|
||||
}
|
||||
|
||||
if [ -n "$OUT" ]; then : > "$OUT"; fi
|
||||
|
||||
emit "# edge-429-probe report"
|
||||
emit "# host=$HOST burst=$BURST waves=$WAVES pause=${WAVE_PAUSE}s"
|
||||
emit "# layout_path=$LAYOUT_PATH"
|
||||
emit "# activity_path=$ACTIVITY_PATH"
|
||||
emit "# generated=$(date -u +%Y-%m-%dT%H:%M:%SZ)"
|
||||
emit ""
|
||||
|
||||
for wave in $(seq 1 "$WAVES"); do
|
||||
emit "## wave $wave"
|
||||
: > "$TMP_RESULTS"
|
||||
run_burst "$LAYOUT_PATH" "layout" "$wave"
|
||||
run_burst "$ACTIVITY_PATH" "activity" "$wave"
|
||||
while read -r line; do
|
||||
emit " $line"
|
||||
done < "$TMP_RESULTS"
|
||||
if [ "$wave" -lt "$WAVES" ]; then
|
||||
sleep "$WAVE_PAUSE"
|
||||
fi
|
||||
done
|
||||
|
||||
emit ""
|
||||
emit "## summary — how to read the report"
|
||||
emit "# status=429 + content_type starts with application/json + x_ratelimit_limit set"
|
||||
emit "# => workspace-server bucket overflow. Closes when #60 deploys."
|
||||
emit "# status=429 + cf_ray set + content_type=text/html"
|
||||
emit "# => Cloudflare WAF / rate-limit. Audit dashboard rules per #62."
|
||||
emit "# status=429 + x_vercel set + content_type=text/html"
|
||||
emit "# => Vercel edge / Bot Fight Mode. Audit Vercel project per #62."
|
||||
emit "# status=429 with no server/cf_ray/x_vercel"
|
||||
emit "# => corporate proxy or VPN. Not actionable in this repo."
|
||||
|
||||
if [ -n "$OUT" ]; then
|
||||
echo "→ Report written to $OUT" >&2
|
||||
# Match only data lines (begin with two-space indent + "label="),
|
||||
# not the summary's reference text which also mentions "status=429".
|
||||
# grep -c outputs "0" + exits 1 when zero matches; `|| true` masks
|
||||
# the exit status so set -e doesn't trip without losing the count.
|
||||
total=$(grep -c '^ label=' "$OUT" 2>/dev/null || true)
|
||||
total429=$(grep -c '^ label=.*status=429' "$OUT" 2>/dev/null || true)
|
||||
total=${total:-0}
|
||||
total429=${total429:-0}
|
||||
echo "→ Totals: ${total429} of ${total} requests returned 429" >&2
|
||||
if [ "${total429}" -gt 0 ]; then
|
||||
echo "→ Per-label 429 counts:" >&2
|
||||
grep '^ label=.*status=429' "$OUT" \
|
||||
| sed -E 's/^ label=([^-]+).*/ \1/' \
|
||||
| sort | uniq -c >&2
|
||||
fi
|
||||
fi
|
||||
@ -19,15 +19,9 @@ Exit codes:
|
||||
0 — no collisions
|
||||
1 — collision detected; output names the conflicting PR(s) for the author
|
||||
|
||||
Designed to run from a Gitea Actions PR check. Reads PR metadata via direct
|
||||
HTTP calls to Gitea's REST API (`/api/v1/`), which on the molecule-ai fleet
|
||||
lives at https://git.moleculesai.app. Runs in under 10s against a typical PR.
|
||||
|
||||
Post-2026-05-06 (Gitea migration, issue #75): the previous version called
|
||||
the GitHub CLI (``gh pr list``, ``gh pr diff``). On Gitea those calls hit
|
||||
either the GraphQL endpoint (HTTP 405) or /api/v3 (HTTP 404). This module
|
||||
now talks to /api/v1 directly via urllib so it works against any Gitea
|
||||
host without a `gh` install or extra dependencies.
|
||||
Designed to run from a GitHub Actions PR check. Reads PR metadata via the
|
||||
GitHub CLI (gh) which is preinstalled on ubuntu-latest runners. Runs in
|
||||
under 10s against a typical PR.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@ -37,70 +31,12 @@ import os
|
||||
import re
|
||||
import subprocess
|
||||
import sys
|
||||
import urllib.error
|
||||
import urllib.parse
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
|
||||
MIGRATIONS_DIR = "workspace-server/migrations"
|
||||
MIGRATION_FILE_RE = re.compile(r"^(\d+)_[^/]+\.(up|down)\.sql$")
|
||||
|
||||
|
||||
def _gitea_api_url() -> str:
|
||||
"""Resolve the Gitea API base URL.
|
||||
|
||||
act_runner forwards github.server_url as GITHUB_SERVER_URL; for the
|
||||
molecule-ai fleet that's https://git.moleculesai.app. Append /api/v1
|
||||
to get the REST root. Override directly via GITEA_API_URL for tests
|
||||
or non-default hosts.
|
||||
"""
|
||||
env_override = os.environ.get("GITEA_API_URL", "").rstrip("/")
|
||||
if env_override:
|
||||
return env_override
|
||||
server = os.environ.get("GITHUB_SERVER_URL", "https://git.moleculesai.app").rstrip("/")
|
||||
return f"{server}/api/v1"
|
||||
|
||||
|
||||
def _gitea_token() -> str:
|
||||
"""Resolve the Gitea token from env. GITEA_TOKEN wins; falls back
|
||||
to GITHUB_TOKEN (set by act_runner) and GH_TOKEN (operator habit
|
||||
from the GitHub era)."""
|
||||
return (
|
||||
os.environ.get("GITEA_TOKEN")
|
||||
or os.environ.get("GITHUB_TOKEN")
|
||||
or os.environ.get("GH_TOKEN")
|
||||
or ""
|
||||
)
|
||||
|
||||
|
||||
def _gitea_get(path: str, params: dict[str, str] | None = None) -> bytes | None:
|
||||
"""GET against /api/v1; returns response body or None on HTTP error.
|
||||
|
||||
Errors return None (not raise) because callers handle missing data
|
||||
by emitting an actionable workflow message rather than crashing the
|
||||
PR check on a transient API blip.
|
||||
"""
|
||||
base = _gitea_api_url()
|
||||
qs = ""
|
||||
if params:
|
||||
qs = "?" + urllib.parse.urlencode(params)
|
||||
url = f"{base}/{path.lstrip('/')}{qs}"
|
||||
req = urllib.request.Request(url)
|
||||
token = _gitea_token()
|
||||
if token:
|
||||
req.add_header("Authorization", f"token {token}")
|
||||
req.add_header("Accept", "application/json")
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=20) as resp: # noqa: S310
|
||||
return resp.read()
|
||||
except urllib.error.HTTPError as e:
|
||||
sys.stderr.write(f"Gitea API HTTP {e.code} on {path}: {e.reason}\n")
|
||||
return None
|
||||
except (urllib.error.URLError, TimeoutError) as e:
|
||||
sys.stderr.write(f"Gitea API network error on {path}: {e}\n")
|
||||
return None
|
||||
|
||||
|
||||
def run(cmd: list[str], check: bool = True) -> str:
|
||||
"""Run a subprocess and return stdout. Raise on non-zero when check=True."""
|
||||
result = subprocess.run(cmd, capture_output=True, text=True)
|
||||
@ -160,49 +96,32 @@ def open_prs_with_migration_prefix(
|
||||
repo: str, prefix: int, exclude_pr: int
|
||||
) -> list[dict]:
|
||||
"""Return open PRs (other than `exclude_pr`) that add a migration with
|
||||
`prefix`. Walks open PRs via Gitea's `/repos/{owner}/{repo}/pulls` and
|
||||
pulls each one's changed-file list via `/pulls/{n}/files`. The cost is
|
||||
bounded by open-PR count, which is small (<100) on this repo. The
|
||||
return shape mimics the GitHub CLI's `--json number,headRefName`:
|
||||
``[{"number": int, "headRefName": str}, ...]``.
|
||||
`prefix`. Uses `gh pr diff` per PR — we only need to walk PRs that are
|
||||
actually in flight, so the cost is bounded by open-PR count.
|
||||
"""
|
||||
body = _gitea_get(
|
||||
f"repos/{repo}/pulls",
|
||||
{"state": "open", "limit": "50"},
|
||||
)
|
||||
if body is None:
|
||||
# Best-effort: a transient Gitea blip shouldn't fail the PR
|
||||
# check (the base-branch collision check runs locally and is
|
||||
# the more common failure mode).
|
||||
return []
|
||||
prs = json.loads(body)
|
||||
out = run([
|
||||
"gh", "pr", "list", "--repo", repo, "--state", "open",
|
||||
"--json", "number,headRefName", "--limit", "100",
|
||||
])
|
||||
prs = json.loads(out)
|
||||
matches: list[dict] = []
|
||||
for pr in prs:
|
||||
num = pr["number"]
|
||||
if num == exclude_pr:
|
||||
continue
|
||||
# Gitea returns the head ref under .head.ref (REST shape);
|
||||
# GitHub CLI's --json headRefName flattens it. Normalize on
|
||||
# the way out so callers see the historical shape.
|
||||
head_ref_name = (pr.get("head") or {}).get("ref", "")
|
||||
files_body = _gitea_get(f"repos/{repo}/pulls/{num}/files", {"limit": "100"})
|
||||
if files_body is None:
|
||||
continue
|
||||
try:
|
||||
files = json.loads(files_body)
|
||||
except json.JSONDecodeError:
|
||||
files = run([
|
||||
"gh", "pr", "diff", str(num), "--repo", repo, "--name-only",
|
||||
], check=False)
|
||||
except Exception: # noqa: BLE001
|
||||
continue
|
||||
for f in files:
|
||||
# Gitea's /pulls/{n}/files returns objects with `.filename`
|
||||
# (same as GitHub's REST). Older Gitea versions emit
|
||||
# `.name` instead — handle both.
|
||||
raw = f.get("filename") or f.get("name") or ""
|
||||
for raw in files.splitlines():
|
||||
path = Path(raw.strip())
|
||||
if not path.name:
|
||||
continue
|
||||
m = MIGRATION_FILE_RE.match(path.name)
|
||||
if m and int(m.group(1)) == prefix:
|
||||
matches.append({"number": num, "headRefName": head_ref_name})
|
||||
matches.append(pr)
|
||||
break
|
||||
return matches
|
||||
|
||||
@ -219,10 +138,7 @@ def main() -> int:
|
||||
pr_number = int(pr_number_env)
|
||||
base_ref = os.environ.get("BASE_REF", "origin/staging")
|
||||
head_ref = os.environ.get("HEAD_REF", "HEAD")
|
||||
# Default kept lowercase to match the Gitea-canonical org name
|
||||
# (post-2026-05-06 migration). Tests + workflow context override
|
||||
# via GITHUB_REPOSITORY which act_runner sets per-run.
|
||||
repo = os.environ.get("GITHUB_REPOSITORY", "molecule-ai/molecule-core")
|
||||
repo = os.environ.get("GITHUB_REPOSITORY", "Molecule-AI/molecule-core")
|
||||
|
||||
added = migrations_in_diff(base_ref, head_ref)
|
||||
if not added:
|
||||
|
||||
@ -51,7 +51,7 @@ log "pulling latest images for: ${RUNTIMES[*]}"
|
||||
PULLED=()
|
||||
FAILED=()
|
||||
for rt in "${RUNTIMES[@]}"; do
|
||||
IMG="153263036946.dkr.ecr.us-east-2.amazonaws.com/molecule-ai/workspace-template-$rt:latest"
|
||||
IMG="ghcr.io/molecule-ai/workspace-template-$rt:latest"
|
||||
if docker pull "$IMG" >/dev/null 2>&1; then
|
||||
log " ✓ $rt"
|
||||
PULLED+=("$rt")
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue
Block a user