Commit Graph

11 Commits

Author SHA1 Message Date
YeonGyu-Kim 90aa3e4489 Merge pull request #2589 from MoerAI/fix/plan-agent-continuation-loop
fix(todo-continuation-enforcer): add plan agent to DEFAULT_SKIP_AGENTS (fixes #2526)
2026-03-25 21:45:58 +09:00
YeonGyu-Kim 8aec4c5cb3 feat(hooks/todo-continuation-enforcer): enhance continuation message with skeptical verification guidance 2026-03-20 16:13:02 +09:00
MoerAI 2b6b08345a fix(todo-continuation-enforcer): add plan agent to DEFAULT_SKIP_AGENTS to prevent infinite loop
The todo-continuation-enforcer injects continuation prompts when
sessions go idle with pending todos. When Plan Mode agents (which are
read-only) create todo items, the continuation prompt contradicts
Plan Mode's STRICTLY FORBIDDEN directive, causing an infinite loop
where the agent acknowledges the conflict then goes idle, triggering
another injection.

Adding 'plan' to DEFAULT_SKIP_AGENTS prevents continuation injection
into Plan Mode sessions, matching the same exclusion pattern already
used for prometheus and compaction agents.

Fixes #2526
2026-03-16 11:07:28 +09:00
conversun 088844474a fix(todo-continuation-enforcer): tighten post-compaction guard with session-agent fallback
Refine continuation agent resolution to prefer session-state agent fallback while keeping compaction-specific protection. Replace sticky boolean compaction flag with a short-lived timestamp guard so unresolved agents are blocked only during the immediate post-compaction window, avoiding long-lived suppression and preserving existing continuation behavior.
2026-03-13 00:55:37 +08:00
YeonGyu-Kim 0ae4812bee fix(todo-continuation-enforcer): add stagnation limit constant
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-03-08 02:17:38 +09:00
YeonGyu-Kim 5e07dfe19b fix(atlas): allow Sisyphus as last agent when boulder targets atlas explicitly
The boulder continuation in event-handler.ts skipped injection whenever
the last agent was 'sisyphus' and the boulder state had agent='atlas'
set explicitly. The allowSisyphusWhenDefaultAtlas guard required
boulderAgentWasNotExplicitlySet=true, but start-work-hook.ts always
calls createBoulderState(..., 'atlas') which sets the agent explicitly.

This created a chicken-and-egg deadlock: boulder continuation needs
atlas to be the last agent, but the continuation itself is what switches
to atlas. With /start-work, the first iteration was always blocked.

Fix: drop the boulderAgentWasNotExplicitlySet constraint so Sisyphus is
always allowed when the boulder targets atlas (whether explicit or default).

Also reduce todo-continuation-enforcer CONTINUATION_COOLDOWN_MS from
30s to 5s to match atlas hook cooldown and recover interruptions faster.
2026-02-25 14:16:17 +09:00
YeonGyu-Kim 2a4009e692 fix: add post-max-failure recovery window for todo continuation 2026-02-16 15:27:00 +09:00
YeonGyu-Kim c2f22cd6e5 fix: apply cooldown on injection failure and cap retries 2026-02-16 15:00:41 +09:00
YeonGyu-Kim 7a3df05e47 fix(todo-continuation-enforcer): fire continuation for all sessions with incomplete todos
Remove boulder session restriction (f84ef532) and stagnation cap (10a60854)
that prevented continuation from firing in regular sessions.

Changes:
- Remove boulder/subagent session gate in idle-event.ts — continuation now
  fires for ANY session with incomplete todos, as originally intended
- Remove stagnation cap (MAX_UNCHANGED_CYCLES) — agent must keep rolling
  the boulder until all todos are complete, no giving up after 3 attempts
- Remove lastTodoHash and unchangedCycles from SessionState type
- Keep 30s cooldown (CONTINUATION_COOLDOWN_MS) as safety net against
  re-injection loops
- Update tests: remove boulder gate tests, update stagnation test to verify
  continuous injection, update non-main-session test to verify injection

42 tests pass, typecheck and build clean.
2026-02-13 18:50:53 +09:00
YeonGyu-Kim 10a60854dc perf(todo-continuation): add cooldown and stagnation cap to prevent re-injection loops 2026-02-13 11:54:32 +09:00
YeonGyu-Kim 119e18c810 refactor: wave 2 - split atlas, auto-update-checker, session-recovery, todo-enforcer, background-task hooks
- Extract atlas/ into 15 focused modules (hook, event handler, tool policies, types, etc.)
- Split auto-update-checker into checker/ and hook/ subdirectories with single-purpose files
- Decompose session-recovery into separate recovery strategy files per error type
- Extract todo-continuation-enforcer from monolith to directory with dedicated modules
- Split background-task/tools.ts into individual tool creator files
- Extract command-executor, tmux-utils into focused sub-modules
- Split config/schema.ts into domain-specific schema files
- Decompose cli/config-manager.ts into focused modules
- Rollback skill-mcp-manager, model-availability, index.ts splits that broke tests
- Fix all import path depths for moved files (../../ -> ../../../)
- Add explicit type annotations to resolve TS7006 implicit any errors

Typecheck: 0 errors
Tests: 2359 pass, 5 fail (all pre-existing)
2026-02-08 15:01:42 +09:00