272 Commits

Author SHA1 Message Date
YeonGyu-Kim
18c161a9cd
Merge pull request #1620 from potb/acp-json-error
fix: switch session.prompt() to promptAsync() — delegate broken in ACP
2026-02-07 22:52:39 +09:00
Peïo Thibault
414cecd7df test: add promptAsync mocks to all test files for promptAsync migration 2026-02-07 14:41:46 +01:00
YeonGyu-Kim
ac6e7d00f2 fix(mcp-loader): also read ~/.claude/.mcp.json for CLI-managed user MCP config
PR #1616 replaced ~/.claude/.mcp.json with ~/.claude.json but both paths
should be read:
- ~/.claude.json: user/local scope MCP settings (mcpServers field)
- ~/.claude/.mcp.json: CLI-managed MCP servers (claude mcp add)

Fixes #814
2026-02-07 22:29:51 +09:00
Peïo Thibault
5f21ddf473 fix(background-agent): switch session.prompt to promptAsync 2026-02-07 13:42:20 +01:00
YeonGyu-Kim
2c394cd497
Merge pull request #1616 from code-yeongyu/fix/814-user-mcp-config
fix(mcp-loader): read user-level MCP config from ~/.claude.json (#814)
2026-02-07 20:09:53 +09:00
YeonGyu-Kim
cf29cd137e test: isolate user-level MCP config test from real homedir 2026-02-07 20:06:58 +09:00
YeonGyu-Kim
d3f8c7d288
Merge pull request #1615 from code-yeongyu/fix/1563-browser-provider-gating
fix(skill-loader): filter discovered skills by browserProvider (#1563)
2026-02-07 20:04:08 +09:00
YeonGyu-Kim
1760367a25 fix(mcp-loader): read user-level MCP config from ~/.claude.json (#814) 2026-02-07 20:01:16 +09:00
YeonGyu-Kim
747edcb6e6 fix(skill-loader): filter discovered skills by browserProvider (#1563) 2026-02-07 20:01:15 +09:00
YeonGyu-Kim
d44f5db1e2
Merge pull request #1608 from code-yeongyu/fix/114-cascade-cancel
fix: cascade cancel descendant tasks when parent session is deleted (#114)
2026-02-07 19:16:18 +09:00
YeonGyu-Kim
9040383da7 fix: cascade cancel descendant tasks when parent session is deleted (#114)
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-07 19:10:49 +09:00
YeonGyu-Kim
e4bbd6bf15 fix: allow string values for commit_footer config (#919) 2026-02-07 19:04:34 +09:00
YeonGyu-Kim
a691a3ac0a refactor: migrate delegate_task to task tool with metadata fixes
- Rename delegate_task tool to task across codebase (100 files)
- Update model references: claude-opus-4-6 → 4-5, gpt-5.3-codex → 5.2-codex
- Add tool-metadata-store to restore metadata overwritten by fromPlugin()
- Add session ID polling for BackgroundManager task sessions
- Await async ctx.metadata() calls in tool executors
- Add ses_ prefix guard to getMessageDir for performance
- Harden BackgroundManager with idle deferral and error handling
- Fix duplicate task key in sisyphus-junior test object literals
- Fix unawaited showOutputToUser in ast_grep_replace
- Fix background=true → run_in_background=true in ultrawork prompt
- Fix duplicate task/task references in docs and comments
2026-02-06 21:35:30 +09:00
YeonGyu-Kim
4692809b42 Regenerate AGENTS.md hierarchy with latest codebase state 2026-02-06 19:07:12 +09:00
YeonGyu-Kim
ca8ec494a3 docs: fix stale references in AGENTS.md files 2026-02-06 17:20:19 +09:00
YeonGyu-Kim
1f64920453 chore: update claude-opus-4-5 references to claude-opus-4-6 (excludes antigravity models) 2026-02-06 15:09:07 +09:00
YeonGyu-Kim
6cfaac97b2
Merge pull request #1477 from kaizen403/fix/boulder-agent-tracking
fix: track agent in boulder state to fix session continuation (fixes #927)
2026-02-05 17:41:05 +09:00
YeonGyu-Kim
48cb2033e2 fix(background-agent): gracefully handle aborted parent session in notifyParentSession
When the main session is aborted while background tasks are running,
notifyParentSession() would attempt to call session.messages() and
session.prompt() on the aborted parent session, causing exceptions
that could crash the TUI.

- Add isAbortedSessionError() helper to detect abort-related errors
- Add abort check in session.messages() catch block with early return
- Add abort check in session.prompt() catch block with early return
- Add test case covering aborted parent session scenario

Fixes TUI crash when aborting main session with running background tasks.
2026-02-05 11:31:54 +09:00
YeonGyu-Kim
a644d38623 fix: properly restore env vars using delete when originally undefined 2026-02-05 09:45:35 +09:00
YeonGyu-Kim
a459813888 Fix skill discovery priority and deduplication tests 2026-02-05 09:45:35 +09:00
YeonGyu-Kim
18e941b6be fix: correct skill priority order and improve test coverage
- Changed priority order to: opencode-project > opencode > project > user
  (OpenCode Global skills now take precedence over legacy Claude project skills)
- Updated JSDoc comments to reflect correct priority order
- Fixed test to use actual discoverSkills() for deduplication verification
- Changed test assertion from 'source' to 'scope' (correct field name)
2026-02-05 09:45:35 +09:00
YeonGyu-Kim
86ac39fb78 fix: include custom skills in delegate_task load_skills resolution
- Add deduplicateSkills() to prevent duplicate skill entries from multiple sources
- Priority order: opencode-project > project > opencode > user
- Add tests for deduplication behavior

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-05 09:45:35 +09:00
Rishi Vhavle
d8137c0c90 fix: track agent in boulder state to fix session continuation (fixes #927)
Add 'agent' field to BoulderState to track which agent (atlas) should
resume on session continuation. Previously, when user typed 'continue'
after interruption, Prometheus (planner) resumed instead of Sisyphus
(executor), causing all delegate_task calls to get READ-ONLY mode.

Changes:
- Add optional 'agent' field to BoulderState interface
- Update createBoulderState() to accept agent parameter
- Set agent='atlas' when /start-work creates boulder.json
- Use stored agent on boulder continuation (defaults to 'atlas')
- Add tests for new agent field functionality
2026-02-04 21:21:57 +05:30
YeonGyu-Kim
ce7478cde7
Merge pull request #1473 from code-yeongyu/feature/task-global-storage
feat(tasks): migrate storage to global config dir with ULTRAWORK_TASK_LIST_ID support
2026-02-04 15:56:31 +09:00
YeonGyu-Kim
8e349aad7e fix(tasks): use path.isAbsolute() for cross-platform path detection
Fixes Cubic AI review finding: startsWith('/') doesn't work on Windows
where absolute paths use drive letters (e.g., C:\).
2026-02-04 15:37:12 +09:00
YeonGyu-Kim
1712907057 docs(tasks): update AGENTS.md for global storage architecture 2026-02-04 15:15:08 +09:00
YeonGyu-Kim
bf31e7289e feat(tasks): migrate storage to global config dir with ULTRAWORK_TASK_LIST_ID support 2026-02-04 15:08:06 +09:00
YeonGyu-Kim
224afadbdb fix(skill-loader): respect disabledSkills in async skill resolution 2026-02-04 15:03:57 +09:00
YeonGyu-Kim
85932fadc7 test(skill-loader): fix test isolation by resetting skill content
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-04 14:51:56 +09:00
YeonGyu-Kim
f79f164cd5 fix(skill-loader): deterministic collision handling for skill names
- Separate directory and file entries, process directories first
- Use Map to deduplicate skills by name (first-wins)
- Directory skills (SKILL.md, {dir}.md) take precedence over file skills (*.md)
- Add test for collision scenario

Addresses Oracle P2 review feedback from PR #1254
2026-02-04 13:52:06 +09:00
YeonGyu-Kim
dee8cf1720
Merge pull request #1370 from misyuari/fix/refactor-skills
fix: update skill resolution to support disabled skills functionality
2026-02-04 13:47:26 +09:00
YeonGyu-Kim
8098e48658
Merge pull request #1254 from LeekJay/fix/nested-skill-discovery
feat(skill-loader): support nested skill directories
2026-02-04 13:40:03 +09:00
YeonGyu-Kim
1e383f44d9 fix(background-agent): abort session on model suggestion retry failure
When promptWithModelSuggestionRetry() fails, the session was not being aborted, causing the polling loop to wait forever for an idle state. Added session.abort() calls in startTask() and resume() catch blocks.

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-04 13:36:45 +09:00
Muhammad Noor Misyuari
374acb3ac6
fix: update tests to reflect changes in skill resolution for async handling and disabled skills 2026-02-03 15:19:08 +07:00
Muhammad Noor Misyuari
2236a940f8
fix: implement disabled skills functionality in skill resolution 2026-02-03 15:19:01 +07:00
YeonGyu-Kim
49c933961e fix(background-cancel): skip notification when user explicitly cancels tasks
- Add skipNotification option to cancelTask method
- Apply skipNotification to background_cancel tool
- Prevents unwanted notifications when user cancels via tool
2026-02-03 16:56:40 +09:00
YeonGyu-Kim
a651e7f073 docs(agents): regenerate AGENTS.md hierarchy with init-deep
- Root: preserve 3 CRITICAL sections (PR target, OpenCode source, English-only)
- Update all 10 AGENTS.md files with current codebase analysis
- Add complexity hotspots, agent models, anti-patterns
- Sync line counts and structure with actual implementation
2026-02-03 16:21:31 +09:00
YeonGyu-Kim
e36dde6e64
refactor(background-agent): optimize lifecycle and simplify tools (#1411)
* refactor(background-agent): optimize cache timer lifecycle and result handling

Ultraworked with Sisyphus

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

* refactor(background-task): simplify tool implementation and expand test coverage

Ultraworked with Sisyphus

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

* fix(background-task): fix BackgroundCancel tool parameter handling

Correct parameter names and types in BackgroundCancel tool to match actual usage patterns. Add comprehensive test coverage for parameter validation.

---------

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-03 12:11:45 +09:00
YeonGyu-Kim
ac9e22cce5 fix(prompts): add missing run_in_background and load_skills params to examples
All delegate_task examples now include required parameters to prevent
model confusion about parameter omission.

Fixes #1403
2026-02-03 10:50:26 +09:00
YeonGyu-Kim
159fccddcf refactor(background-agent): optimize cache timer lifecycle and result handling
Improve cache timer management in background agent manager and update result handler to properly handle cache state transitions
2026-02-02 21:07:20 +09:00
YeonGyu-Kim
92639ca38f feat(task): refactor to Claude Code style individual tools
- Split unified Task tool into individual tools (TaskCreate, TaskGet, TaskList, TaskUpdate)
- Update schema to Claude Code field names (subject, blockedBy, blocks, activeForm, owner, metadata)
- Add OpenCode Todo API sync layer (todo-sync.ts)
- Implement Todo sync on task create/update for continuation enforcement
- Add comprehensive tests for all tools (96 tests total)
- Update AGENTS.md documentation

Breaking Changes:
- Field names changed: title→subject, dependsOn→blockedBy, open→pending
- Tool names changed: task→task_create, task_get, task_list, task_update

Closes: todo-continuation-enforcer now sees Task-created items
2026-02-02 13:13:06 +09:00
YeonGyu-Kim
134dc7687e fix(task-tool): add task ID validation and improve lock acquisition safety
- Add task ID pattern validation (T-[A-Za-z0-9-]+) to prevent path traversal
- Refactor lock mechanism to use UUID-based IDs for reliable ownership tracking
- Implement atomic lock creation with stale lock detection and cleanup
- Add lock acquisition checks in create/update/delete handlers
- Expand task-reminder hook to track split tool names and clean up on session deletion
- Add comprehensive test coverage for validation and lock handling
2026-02-01 23:50:34 +09:00
YeonGyu-Kim
8d29a1c5c7
Implement unified Claude Tasks system with single multi-action tool (#1356)
* chore: pin bun-types to 1.3.6

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* chore: exclude test files and script from tsconfig

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor: remove sisyphus-swarm feature

Remove mailbox types and swarm config schema. Update docs.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor: remove legacy sisyphus-tasks feature

Remove old storage and types implementation, replaced by claude-tasks.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(claude-tasks): add task schema and storage utilities

- Task schema with Zod validation (pending, in_progress, completed, deleted)
- Storage utilities: getTaskDir, readJsonSafe, writeJsonAtomic, acquireLock
- Atomic writes with temp file + rename
- File-based locking with 30s stale threshold

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(tools/task): add task object schemas

Add Zod schemas for task CRUD operations input validation.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(tools): add TaskCreate tool

Create new tasks with sequential ID generation and lock-based concurrency.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(tools): add TaskGet tool

Retrieve task by ID with null-safe handling.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(tools): add TaskUpdate tool with claim validation

Update tasks with status transitions and owner claim validation.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(tools): add TaskList tool and exports

- TaskList for summary view of all tasks
- Export all claude-tasks tool factories from index

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(hooks): add task-reminder hook

Remind agents to use task tools after 10 turns without task operations.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(config): add disabled_tools setting and tasks-todowrite-disabler hook

- Add disabled_tools config option to disable specific tools by name
- Register tasks-todowrite-disabler hook name in schema

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(config-handler): add task_* and teammate tool permissions

Grant task_* and teammate permissions to atlas, sisyphus, prometheus, and sisyphus-junior agents.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(delegate-task): add execute option for task execution

Add optional execute field with task_id and task_dir for task-based delegation.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* fix(truncator): add type guard for non-string outputs

Prevent crashes when output is not a string by adding typeof checks.

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* chore: export config types and update task-resume-info

- Export SisyphusConfig and SisyphusTasksConfig types
- Add task_tool to TARGET_TOOLS list

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor(storage): remove team namespace, use flat task directory

* feat(task): implement unified task tool with all 5 actions

* fix(hooks): update task-reminder to track unified task tool

* refactor(tools): register unified task tool, remove 4 separate tools

* chore(cleanup): remove old 4-tool task implementation

* refactor(config): use new_task_system_enabled as top-level flag

- Add new_task_system_enabled to OhMyOpenCodeConfigSchema
- Remove enabled from SisyphusTasksConfigSchema (keep storage_path, claude_code_compat)
- Update index.ts to gate on new_task_system_enabled
- Update plugin-config.ts default for config initialization
- Update test configs in task.test.ts and storage.test.ts

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

* fix: resolve typecheck and test failures

- Add explicit ToolDefinition return type to createTask function
- Fix planDemoteConfig to use 'subagent' mode instead of 'all'

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-01 22:42:28 +09:00
YeonGyu-Kim
25dcd2a3f2 fix(background-agent): prevent concurrency slot leaks on task startup failures
Unify slot ownership: processKey() owns the slot until task.concurrencyKey is set.
Previously, startTask() released the slot on errors (session.create catch,
createResult.error), but processKey() catch block didn't release, causing slot
leaks when errors occurred between acquire() and task.concurrencyKey assignment.

Changes:
- Remove all pre-transfer release() calls in startTask()
- Add conditional release in processKey() catch: only if task.concurrencyKey not set
- Add validation for createResult.data?.id to catch malformed API responses

This fixes 'Task failed to start within timeout' errors caused by exhausted
concurrency slots that were never released.
2026-02-01 21:24:52 +09:00
YeonGyu-Kim
6bcc3c33f0 refactor(background-agent): show category in task completion notification
Add agent category info to the task completion notification for better
visibility of what category was used for the task.
2026-02-01 19:45:09 +09:00
YeonGyu-Kim
6080bc8caf refactor(delegate-task): improve session title format and add task_metadata block
- Change session title from 'Task: {desc}' to '{desc} (@{agent} subagent)'
- Move session_id to structured <task_metadata> block for better parsing
- Add category tracking to BackgroundTask type and LaunchInput
- Add tests for new title format and metadata block
2026-02-01 19:44:22 +09:00
YeonGyu-Kim
64825158a7
feat(agents): add Hephaestus - autonomous deep worker agent (#1287)
* refactor(keyword-detector): split constants into domain-specific modules

* feat(shared): add requiresAnyModel and isAnyFallbackModelAvailable

* feat(config): add hephaestus to agent schemas

* feat(agents): add Hephaestus autonomous deep worker

* feat(cli): update model-fallback for hephaestus support

* feat(plugin): add hephaestus to config handler with ordering

* test(delegate-task): update tests for hephaestus agent

* docs: update AGENTS.md files for hephaestus

* docs: add hephaestus to READMEs

* chore: regenerate config schema

* fix(delegate-task): bypass requiresModel check when user provides explicit config

* docs(hephaestus): add 4-part context structure for explore/librarian prompts

* docs: fix review comments from cubic (non-breaking changes)

- Move Hephaestus from Primary Agents to Subagents (uses own fallback chain)
- Fix Hephaestus fallback chain documentation (claude-opus-4-5 → gemini-3-pro)
- Add settings.local.json to claude-code-hooks config sources
- Fix delegate_task parameters in ultrawork prompt (agent→subagent_type, background→run_in_background, add load_skills)
- Update line counts in AGENTS.md (index.ts: 788, manager.ts: 1440)

* docs: fix additional documentation inconsistencies from oracle review

- Fix delegate_task parameters in Background Agents example (docs/features.md)
- Fix Hephaestus fallback chain in root AGENTS.md to match model-requirements.ts

* docs: clarify Hephaestus has no fallback (requires gpt-5.2-codex only)

Hephaestus uses requiresModel constraint - it only activates when gpt-5.2-codex
is available. The fallback chain in code is unreachable, so documentation
should not mention fallbacks.

* fix(hephaestus): remove unreachable fallback chain entries

Hephaestus has requiresModel: gpt-5.2-codex which means the agent only
activates when that specific model is available. The fallback entries
(claude-opus-4-5, gemini-3-pro) were unreachable and misleading.

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-02-01 19:26:57 +09:00
itsmylife44
6389da3cd6
fix(tmux): send Ctrl+C before kill-pane and respawn-pane to prevent orphaned processes (#1329)
* fix(tmux): send Ctrl+C before kill-pane and respawn-pane to prevent orphaned processes

* fix(tmux-subagent): prevent premature pane closure with stability detection

Implements stability detection pattern from background-agent to prevent
tmux panes from closing while agents are still working (issue #1330).

Problem: Session status 'idle' doesn't mean 'finished' - agent may still
be thinking/reasoning. Previous code closed panes immediately on idle.

Solution:
- Require MIN_STABILITY_TIME_MS (10s) before stability detection activates
- Track message count changes to detect ongoing activity
- Require STABLE_POLLS_REQUIRED (3) consecutive polls with same message count
- Double-check session status before closing

Changes:
- types.ts: Add lastMessageCount and stableIdlePolls to TrackedSession
- manager.ts: Implement stability detection in pollSessions()
- manager.test.ts: Add 4 tests for stability detection behavior

* test(tmux-subagent): improve stability detection tests to properly verify age gate

- First test now sets session age >10s and verifies 3 polls don't close
- Last test now does 5 polls to prove age gate prevents closure
- Added comments explaining what each poll does
2026-02-01 19:11:35 +09:00
YeonGyu-Kim
c73314f643 feat(skill-mcp-manager): enhance manager with improved test coverage
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-01 19:01:40 +09:00
YeonGyu-Kim
09e738c989 refactor(background-agent): optimize task timing and constants management
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-01 19:01:30 +09:00