Commit Graph

23 Commits

Author SHA1 Message Date
Maxim Harizanov 36861e0b58 fix(copilot): mark internal hook injections as agent-initiated
Apply the internal initiator marker to automated continuation, recovery, babysitter, stop-hook, and hook-message injections so Copilot attribution consistently sets x-initiator=agent for system-generated prompts.
2026-02-19 13:17:02 +02:00
YeonGyu-Kim f3ba126d45 test(todo-continuation-enforcer): cover isContinuationStopped race during countdown
Adds a regression test for the race where /stop-continuation fires after
handleSessionIdle passes the flag check but before injectContinuation runs.
Verifies no injection occurs when the flag becomes true mid-countdown.
2026-02-19 14:08:03 +09:00
YeonGyu-Kim 944e64a1f9 fix(todo-continuation-enforcer): check isContinuationStopped in injectContinuation to close race window
When /stop-continuation is invoked during the 2s countdown, the stop flag
was never checked inside injectContinuation, so the injection would still
fire after the countdown elapsed.

Propagate isContinuationStopped from handleSessionIdle through startCountdown
into injectContinuation, where it is now re-checked before any API call.
2026-02-19 14:07:52 +09:00
YeonGyu-Kim 4d79577088 docs: add module-level AGENTS.md for config-manager, keyword-detector, ralph-loop, session-recovery, todo-continuation-enforcer
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-02-19 10:46:40 +09:00
YeonGyu-Kim dba7a1e07c fix(run): inherit main-session tool permissions for continuation prompts 2026-02-18 21:10:21 +09:00
YeonGyu-Kim 8ea24d26d2 chore: upgrade claude-sonnet-4-5 to claude-sonnet-4-6 across codebase 2026-02-18 15:51:24 +09:00
YeonGyu-Kim 3659c50350 fix(cli-run): rely on continuation markers for completion
Use hook-written continuation marker state to gate run completion checks and remove the noisy event-stream shutdown timeout log in run mode.
2026-02-17 17:50:47 +09:00
YeonGyu-Kim 49b6c108e2 Normalize agent name comparisons to handle display name keys
Hooks and tools now use getAgentConfigKey() to resolve agent names (which may
be display names like 'Atlas (Plan Executor)') to lowercase config keys
before comparison.

- session-utils: orchestrator check uses getAgentConfigKey
- atlas event-handler: boulder agent matching uses config keys
- category-skill-reminder: target agent check uses config keys
- todo-continuation-enforcer: skipAgents comparison normalized
- subagent-resolver: resolves 'metis' -> 'Metis (Plan Consultant)' for lookup
2026-02-16 20:43:09 +09:00
YeonGyu-Kim 0b10245c34 refactor: create normalizeSDKResponse helper and replace scattered patterns across 37 files 2026-02-16 18:20:19 +09:00
YeonGyu-Kim ca622cbfb9 feat: migrate hook callers to SDK message finders on SQLite backend 2026-02-16 16:13:40 +09:00
YeonGyu-Kim 1d5920235f refactor(shared): consolidate 13+ getMessageDir copies into single shared function 2026-02-16 16:13:39 +09:00
YeonGyu-Kim ed098925b5 fix(todo): make Todo id field optional for OpenCode beta compatibility
- Make id field optional in all Todo interfaces (TodoInfo, Todo, TodoItem)
- Fix null-unsafe comparisons in todo-sync.ts to handle missing ids
- Add test case for todos without id field preservation
- All tests pass and typecheck clean
2026-02-16 16:13:39 +09:00
YeonGyu-Kim a747d0f253 fix: add post-max-failure recovery window for todo continuation 2026-02-16 15:27:00 +09:00
YeonGyu-Kim 0a2ec5d251 fix: apply cooldown on injection failure and cap retries 2026-02-16 15:00:41 +09:00
YeonGyu-Kim 9a1d228a36 test(todo-continuation-enforcer): stabilize fake timers 2026-02-14 22:06:18 +09:00
YeonGyu-Kim 119f314a47 Merge pull request #1817 from code-yeongyu/fix/todo-continuation-always-fire
fix(todo-continuation-enforcer): fire continuation for all sessions with incomplete todos
2026-02-14 11:43:10 +09:00
YeonGyu-Kim db76a1a531 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 7e5d866875 Merge pull request #1787 from popododo0720/fix/memory-leak-session-messages-caching
fix: reduce session.messages() calls with event-based caching to prevent memory leaks
2026-02-13 18:44:00 +09:00
YeonGyu-Kim 91d96765dc perf(todo-continuation): add cooldown and stagnation cap to prevent re-injection loops 2026-02-13 11:54:32 +09:00
popododo0720 e61a93faf8 fix: reduce session.messages() calls with event-based caching to prevent memory leaks
- Replace session.messages() fetch in context-window-monitor with message.updated event cache
- Replace session.messages() fetch in preemptive-compaction with message.updated event cache
- Add per-session transcript cache (5min TTL) to avoid full rebuild per tool call
- Remove session.messages() from background-agent polling (use event-based progress)
- Add TTL pruning to todo-continuation-enforcer session state Map
- Add setInterval.unref() to tool-input-cache cleanup timer

Fixes #1222
2026-02-12 11:38:11 +09:00
YeonGyu-Kim caee5ebc18 docs: document intentional design decisions in atlas, todo-continuation, and delegation hooks 2026-02-10 22:00:54 +09:00
YeonGyu-Kim c9364f7b6b fix(todo-continuation-enforcer): require boulder session for continuation
The todo-continuation-enforcer was firing boulder continuation in ALL main
sessions with incomplete todos, regardless of whether /start-work was ever
executed. This caused unwanted BOULDER CONTINUATION directives in sessions
that never invoked /start-work.

Changes:
- Add readBoulderState check in idle-event.ts to verify session is registered
  in boulder.json's session_ids array
- Change filter condition from main session check to boulder session check
- Add 4 new test cases for boulder session gate behavior
- Update all existing 41 tests to set up boulder state appropriately

Now boulder continuation only fires when:
1. Session is in boulder.json's session_ids (/start-work was executed), OR
2. Session is a background task session (subagent)

TDD cycle:
- RED: 2 new tests failed as expected (no boulder check in implementation)
- GREEN: Implementation added, all 41 tests pass
- REFACTOR: Full test suite 2513 pass, typecheck & build clean
2026-02-10 22:00:53 +09:00
YeonGyu-Kim cea97f896b 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