forked from molecule-ai/molecule-core
f7ad5a82f7
6 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Hongming Wang
|
dd57a840b6 |
fix: comprehensive a2a-sdk 1.x migration sweep across workspace/
Audited every a2a-sdk surface in workspace/ against the installed
1.0.2 wheel. Found and fixed:
main.py (the live workspace startup path):
• create_jsonrpc_routes(rpc_url='/', enable_v0_3_compat=True) —
rpc_url required in 1.x; v0.3 compat enables inbound legacy
clients (`"role": "user"` lowercase) without forcing them to
upgrade. Pairs with the outbound rename below.
a2a_executor.py:
• TextPart/FilePart/FileWithUri removed in 1.x. Part is now a
flat proto message: Part(text=…) / Part(url=…, filename=…,
media_type=…). Updated the file-attachment branch (only
reachable when an agent emits files; the harness's PONG path
didn't exercise this, but it's a latent crash).
• Message field names: messageId/taskId/contextId →
message_id/task_id/context_id (proto3 snake_case).
• Role enum: Role.agent → Role.ROLE_AGENT (proto enum).
Outbound JSON-RPC payloads (8 files):
• "role": "user" → "role": "ROLE_USER" — proto3 JSON serialization
is strict about enum values. Sites: a2a_client, a2a_cli, main
(initial+idle prompts), heartbeat, builtin_tools/a2a_tools,
builtin_tools/delegation. Wire JSON keys stay camelCase
(proto3 default), only the role enum value changed.
google-adk/adapter.py:
• new_agent_text_message → new_text_message (4 sites). This
adapter's directory has a hyphen, so it can't be imported as a
Python module — effectively dead code, but the wheel ships the
file and a future fix should keep it correct against 1.x.
Why one PR instead of seven: every previous a2a-sdk migration find
landed as its own publish → cascade → harness → next-bug cycle.
Today's audit ran every a2a-sdk symbol/type/method in workspace/
against the installed 1.0.2 wheel in a single sweep + tested the
critical paths (Message construction, Part construction, Role enum
parsing) against the actual SDK. Should be the last migration PR.
Verified locally:
python3 scripts/build_runtime_package.py --version 0.1.99 \
--out /tmp/build-final
pip install /tmp/build-final
python -c "import molecule_runtime.main; \
from molecule_runtime.a2a_executor import LangGraphA2AExecutor"
→ ✓ all imports clean against a2a-sdk 1.0.2
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Hongming Wang
|
5071454074 |
fix(delegation): lazy-refresh QUEUED state from platform; live DELEGATION_* events
Critical follow-up to PR #2126's review. Two real bugs: 1. **Runtime QUEUED never resolved.** Platform's drain stitch updates the platform's delegate_result row when a queued delegation finally completes, but never pushes back to the runtime. The LLM polling check_delegation_status saw status="queued" forever — combined with the new docstring guidance ("queued → wait, peer will reply"), the model would wait indefinitely on a state that never resolves. Strictly worse than pre-PR behavior where it would have at least bypassed. 2. **Live updates dead code.** delegation.go writes activity rows by direct INSERT INTO activity_logs, bypassing the LogActivity helper that fires ACTIVITY_LOGGED. Adding "delegation" to the canvas's ACTIVITY_LOGGED filter (PR #2126 first cut) was inert — initial GET worked, live updates did not. Fix: (1) Runtime side, workspace/builtin_tools/delegation.py: - New `_refresh_queued_from_platform(task_id)` async helper that pulls /workspaces/<self>/delegations and finds the platform-side delegate_result row for our task_id. - check_delegation_status calls _refresh when local status is QUEUED, so the LLM's poll itself drives state convergence. - Best-effort: GET failure leaves local state untouched, next poll retries. - Docstring updated to reflect the actual behavior ("polls transparently — keep polling and you'll see the flip"). - 4 new tests cover: QUEUED → completed via refresh; QUEUED → failed via refresh; refresh keeps QUEUED when platform hasn't resolved; refresh swallows network errors safely. (2) Canvas side, AgentCommsPanel.tsx WS push handler: - Listens for DELEGATION_SENT / DELEGATION_STATUS / DELEGATION_COMPLETE / DELEGATION_FAILED in addition to ACTIVITY_LOGGED. - Each event's payload synthesized into an ActivityEntry shape so toCommMessage's existing delegation branch maps it. Status derived: STATUS uses payload.status, COMPLETE → "completed", FAILED → "failed", SENT → "pending". - The ACTIVITY_LOGGED branch keeps the "delegation" type accepted as a no-op-today / future-proof path: if delegation handlers are ever refactored to call LogActivity, this lights up automatically without another canvas change. Doesn't change: the docstring guidance ("queued → wait, don't bypass") is now actually load-bearing because the refresh path will deliver the eventual outcome. Without the refresh, the guidance was a trap. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Hongming Wang
|
057876cb0c |
fix(delegation): runtime handles 202+queued; canvas surfaces delegation rows
Two bugs that compounded into the "Director does the work itself" UX:
1. workspace/builtin_tools/delegation.py: _execute_delegation only
handled HTTP 200 in the response branch. When the peer's a2a-proxy
returned HTTP 202 + {queued: true} (single-SDK-session bottleneck
on the peer), the loop fell through. Two iterations later the
`if "error" in result` check tried to access an unbound `result`,
the goroutine ended quietly, and the delegation stayed at FAILED
with error="None". The LLM checking status saw "failed" + the
platform's "Delegation queued — target at capacity" log line in
chat context, concluded the peer was permanently unavailable, and
bypassed delegation to do the work itself.
Fix: explicit 202+queued branch. Adds DelegationStatus.QUEUED,
marks the local delegation as QUEUED, mirrors to the platform,
and returns cleanly without retrying. The retry loop is for
transient transport errors — queueing is a real ack, not a failure
to retry against (retrying would just re-queue the same task).
check_delegation_status docstring extended with explicit per-status
guidance: pending/in_progress → wait, queued → wait (peer busy on
prior task, reply WILL arrive), completed → use result, failed →
real error in error field; only fall back on failed, never queued.
2. canvas/src/components/tabs/chat/AgentCommsPanel.tsx: filter dropped
every delegation row because it whitelisted only a2a_send /
a2a_receive. activity_type='delegation' rows (written by the
platform's /delegate handler with method='delegate' or
'delegate_result') never reached toCommMessage. User saw "No
agent-to-agent communications yet" while 6+ delegations existed
in the DB.
Fix: include "delegation" in the both the initial filter and the
WS push filter, plus a delegation branch in toCommMessage that
maps the row as outbound (always — platform proxies on our behalf)
and uses summary as the primary text source.
Tests:
- 3 new Python tests cover the 202+queued path: status becomes
QUEUED not FAILED; no retry on queued (counted by URL match
against the A2A target since the mock is shared across all
AsyncClient calls); bare 202 without {queued:true} still
falls through to the existing retry-then-FAILED path.
- 3 new TS tests cover the delegation mapper: 'delegate' row
maps as outbound to target with summary text; queued
'delegate_result' preserves status='queued' (load-bearing for
the LLM's wait-vs-bypass decision); missing target_id returns
null instead of rendering a ghost.
Does NOT solve: the underlying single-SDK-session bottleneck that
causes peers to queue in the first place. Tracked as task #102
(parallel SDK sessions per workspace) — real architectural work.
This PR makes the runtime handle the queueing correctly so the LLM
doesn't bail out, and makes the delegations visible in Agent Comms
so operators can see what's happening.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
Hongming Wang
|
65b531acf6 |
fix(workspace): tag self-originated A2A POSTs with X-Workspace-ID
Workspace runtime fired four classes of A2A request to the platform
without the X-Workspace-ID header that identifies the source
workspace: heartbeat self-messages, initial_prompt, idle-loop fires,
and peer-to-peer A2A from runtime tools. The platform's a2a_receive
logger keys source_id off that header — without it, every such row
was written with source_id=NULL, which the canvas's My Chat tab
filters as ?source=canvas (i.e. "user typed this") and rendered the
internal triggers as if the human user had sent them. The
"Delegation results are ready..." heartbeat trigger was visible to
end users in the chat history; delegate_task A2A calls between agents
were misclassified the same way.
Centralise the header construction in a new platform_auth helper
self_source_headers(workspace_id) that returns auth_headers() PLUS
{X-Workspace-ID: <id>}. Apply it to:
- heartbeat.py self-message (refactored from inline header dict)
- main.py initial_prompt POST
- main.py idle_prompt POST
- a2a_client.py send_a2a_message (peer A2A from runtime)
- builtin_tools/a2a_tools.py delegate_task (was missing ALL headers)
Tests:
- test_heartbeat.py asserts the X-Workspace-ID header is set on
the self-message POST.
- test_a2a_tools_module.py asserts the same on delegate_task POSTs;
FakeClient.post mocks updated to accept the headers kwarg.
Production effect lands the moment workspace containers are rebuilt
with this code; existing rows in activity_logs keep their NULL
source_id (legacy data). The canvas-side filter (#follow-up)
covers the historical-rows case until backfill.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||
|
molecule-ai[bot]
|
3bef6af241 |
fix: apply #1124 env-var defaults + scrub F1088 credentials from INCIDENT_LOG.md (#1347)
- PLATFORM_URL: replace unreachable http://platform:8080 mesh-only default with Docker-aware detection (host.docker.internal in containers, localhost for local dev) across all workspace Python modules and the git-token-helper shell script. - WORKSPACE_ID: add fail-fast validation in main.py (SystemExit if empty) consistent with coordinator.py / a2a_cli.py patterns already in place. - INCIDENT_LOG.md: replace all 3 F1088 credential types with ***REDACTED*** (sk-cp- 2x, github_pat_ 2x, ADMIN_TOKEN base64 3x). Fixes #1124, #1333. Co-authored-by: Molecule AI Dev Lead <dev-lead@agents.moleculesai.app> |
||
|
Hongming Wang
|
d8026347e5 |
chore: open-source restructure — rename dirs, remove internal files, scrub secrets
Renames: - platform/ → workspace-server/ (Go module path stays as "platform" for external dep compat — will update after plugin module republish) - workspace-template/ → workspace/ Removed (moved to separate repos or deleted): - PLAN.md — internal roadmap (move to private project board) - HANDOFF.md, AGENTS.md — one-time internal session docs - .claude/ — gitignored entirely (local agent config) - infra/cloudflare-worker/ → Molecule-AI/molecule-tenant-proxy - org-templates/molecule-dev/ → standalone template repo - .mcp-eval/ → molecule-mcp-server repo - test-results/ — ephemeral, gitignored Security scrubbing: - Cloudflare account/zone/KV IDs → placeholders - Real EC2 IPs → <EC2_IP> in all docs - CF token prefix, Neon project ID, Fly app names → redacted - Langfuse dev credentials → parameterized - Personal runner username/machine name → generic Community files: - CONTRIBUTING.md — build, test, branch conventions - CODE_OF_CONDUCT.md — Contributor Covenant 2.1 All Dockerfiles, CI workflows, docker-compose, railway.toml, render.yaml, README, CLAUDE.md updated for new directory names. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |