mosaic/stack
1
0
Fork 0
Code Issues 10 Pull Requests Actions Packages Projects Releases 2 Wiki Activity

[ORCH-005] ClawdBot Failure Handling #100

New Issue
Closed
opened 2026-01-29 23:30:25 +00:00 by jason.woltje · 0 comments
jason.woltje commented 2026-01-29 23:30:25 +00:00
Owner
Copy Link

Phase 3: Failure Handling

Handle failures reported by Orchestrator service (`apps/orchestrator/`) (not detecting them ourselves).

Deliverables

[ ] Failure callback handler (Orchestrator reports task failed)
[ ] Retry configuration per task type (max retries, backoff)
[ ] Automatic retry dispatch (if retries remaining)
[ ] Escalation logic (notify user after max retries)
[ ] Checkpoint preservation (save last known state for potential resume)
[ ] Failure audit trail (full history in AgentTaskLog)

Failure Flow

Orchestrator reports failure → Callback received
                            → Log failure details
                            → Check retry config
                            → If retries remaining: re-dispatch
                            → If max retries: mark FAILED, notify user

Removed (handled by Orchestrator service)

• Stale agent detection — Orchestrator monitors its own agents
• Direct health monitoring — Orchestrator handles heartbeats
• Agent-level recovery — Orchestrator restarts failed agents

Dependencies

• #99 Task Dispatcher Service

Related

• #95 Agent Orchestration EPIC
• #114 Kill Authority Implementation
• ORCH-118 (Orchestrator resource cleanup)

## Phase 3: Failure Handling Handle failures **reported by Orchestrator service (\`apps/orchestrator/\`)** (not detecting them ourselves). ## Deliverables [ ] Failure callback handler (Orchestrator reports task failed) [ ] Retry configuration per task type (max retries, backoff) [ ] Automatic retry dispatch (if retries remaining) [ ] Escalation logic (notify user after max retries) [ ] Checkpoint preservation (save last known state for potential resume) [ ] Failure audit trail (full history in AgentTaskLog) ## Failure Flow ``` Orchestrator reports failure → Callback received → Log failure details → Check retry config → If retries remaining: re-dispatch → If max retries: mark FAILED, notify user ``` ## Removed (handled by Orchestrator service) • ~~Stale agent detection~~ — Orchestrator monitors its own agents • ~~Direct health monitoring~~ — Orchestrator handles heartbeats • ~~Agent-level recovery~~ — Orchestrator restarts failed agents ## Dependencies • #99 Task Dispatcher Service ## Related • #95 Agent Orchestration EPIC • #114 Kill Authority Implementation • ORCH-118 (Orchestrator resource cleanup)
jason.woltje added this to the M6-AgentOrchestration (0.0.6) milestone 2026-01-29 23:30:25 +00:00
jason.woltje added the apiapip0phase-3 labels 2026-01-29 23:30:25 +00:00
jason.woltje changed title from [ORCH-005] Agent Failure Recovery to [ORCH-005] ClawdBot Failure Handling 2026-01-30 03:04:05 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
ai
AI/LLM integration
 api
Backend/API work
 api
auth
Authentication
 database
database
Database/schema work
 devops
Docker/deployment
 docs
Documentation
 frontend
graph
knowledge-module
migration
Data migration
 orchestrator
Orchestrator service (apps/orchestrator/)
 p0
Critical priority
 p1
High priority
 p2
Medium priority
 p3
Low priority
 performance
Performance work
 phase-1
phase-2
phase-3
phase-4
phase-5
plugin
MoltBot plugin work
 search
security
Security-related
 setup
Initial setup
 testing
Testing/QA
 web
Frontend work
No Label api api p0 phase-3
Milestone
No items
No Milestone M6-AgentOrchestration (0.0.6)
Projects
Clear projects
No project
Assignees
Clear assignees
jason.woltje
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: mosaic/stack#100
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?