molecule-core/workspace
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>
2026-04-26 16:05:04 -07:00
..
adapters feat(workspace): migrate a2a-sdk from 0.3.x to 1.0.0 (KI-009) (#1974) 2026-04-24 04:43:17 +00:00
builtin_tools fix(delegation): lazy-refresh QUEUED state from platform; live DELEGATION_* events 2026-04-26 16:05:04 -07:00
lib feat(workspace): pre-stop serialization for pause/resume (closes #1386) 2026-04-21 12:40:44 +00:00
molecule_audit chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00
plugins_registry feat(plugin): implement MCPServerAdaptor (issue #847) 2026-04-24 01:42:13 +00:00
policies chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00
scripts fix(git-token-helper): close TOCTOU window + stop swallowing chmod errors (closes #1552) 2026-04-26 08:22:29 -07:00
skill_loader chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00
tests fix(delegation): lazy-refresh QUEUED state from platform; live DELEGATION_* events 2026-04-26 16:05:04 -07:00
.coveragerc test(workspace): centralize pytest-cov config + 92% floor (closes #1817) 2026-04-26 06:21:22 -07:00
a2a_cli.py fix: apply #1124 env-var defaults + scrub F1088 credentials from INCIDENT_LOG.md (#1347) 2026-04-21 08:11:44 +00:00
a2a_client.py fix(a2a): review-driven hardening — prefix-anchored type check, error_detail cap, shared hint module 2026-04-24 23:47:44 -07:00
a2a_executor.py merge: resolve staging conflicts (a2a_proxy + workspace_crud) 2026-04-26 10:43:22 -07:00
a2a_mcp_server.py chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00
a2a_tools.py fix(a2a): review-driven hardening — prefix-anchored type check, error_detail cap, shared hint module 2026-04-24 23:47:44 -07:00
adapter_base.py feat: platform instructions system with global/team/workspace scope 2026-04-22 15:17:14 -07:00
agent.py chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00
agents_md.py chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00
build-all.sh fix: update workspace script comments for workspace-template → workspace rename 2026-04-18 01:48:05 -07:00
claude_sdk_executor.py chore: third-pass review polish — empty-stream gate test + Callable type 2026-04-25 08:52:32 -07:00
cli_executor.py fix(executors): move set_current_task inside try so active_tasks always decrements (#2026) 2026-04-24 18:03:12 +00:00
config.py fix(compliance): flip default mode to owasp_agentic (detect-only) 2026-04-24 11:52:09 -07:00
consolidation.py fix: apply #1124 env-var defaults + scrub F1088 credentials from INCIDENT_LOG.md (#1347) 2026-04-21 08:11:44 +00:00
coordinator.py fix: apply #1124 env-var defaults + scrub F1088 credentials from INCIDENT_LOG.md (#1347) 2026-04-21 08:11:44 +00:00
Dockerfile feat(workspace): 45-min gh-token refresh daemon + credential helper cache 2026-04-22 19:52:46 -07:00
entrypoint.sh fix(workspace): credential helper security hardening (#1797) 2026-04-23 18:14:55 +00:00
events.py chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00
executor_helpers.py feat(canvas+platform): chat attachments, model selection, deploy/delete UX 2026-04-24 13:27:51 -07:00
heartbeat.py feat(platform,workspace): SDK-wedge detection + workspace_status ENUM 2026-04-25 00:59:15 -07:00
hermes_executor.py feat(workspace): migrate a2a-sdk from 0.3.x to 1.0.0 (KI-009) (#1974) 2026-04-24 04:43:17 +00:00
initial_prompt.py chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00
main.py fix(workspace): tag self-originated A2A POSTs with X-Workspace-ID 2026-04-24 19:54:43 -07:00
molecule_ai_status.py fix: apply #1124 env-var defaults + scrub F1088 credentials from INCIDENT_LOG.md (#1347) 2026-04-21 08:11:44 +00:00
platform_auth.py fix(workspace): tag self-originated A2A POSTs with X-Workspace-ID 2026-04-24 19:54:43 -07:00
plugins.py chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00
preflight.py chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00
prompt.py fix(review): address code review blockers on tool-trace + instructions 2026-04-22 16:18:06 -07:00
pytest.ini fixup: lower coverage floor 92→86 to match post-omit measurement 2026-04-26 06:24:36 -07:00
rebuild-runtime-images.sh fix: update workspace script comments for workspace-template → workspace rename 2026-04-18 01:48:05 -07:00
requirements.txt feat(workspace): migrate a2a-sdk from 0.3.x to 1.0.0 (KI-009) (#1974) 2026-04-24 04:43:17 +00:00
shared_runtime.py fix: CWE-78 rm scope, go vet failures, delegation idempotency 2026-04-21 18:22:30 +00:00
transcript_auth.py chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00
watcher.py chore: open-source restructure — rename dirs, remove internal files, scrub secrets 2026-04-18 00:24:44 -07:00