350 Commits

Author SHA1 Message Date
YeonGyu-Kim
3d4ed912d7 fix(look-at): use synchronous prompt to fix race condition (#1620 regression)
PR #1620 migrated all prompt calls from session.prompt (blocking) to
session.promptAsync (fire-and-forget HTTP 204). This broke look_at which
needs the multimodal-looker response to be available immediately after
the prompt call returns.

Fix: add promptSyncWithModelSuggestionRetry() that uses session.prompt
(blocking) with model suggestion retry support. look_at now uses this
sync variant while all other callers keep using promptAsync.

- Add promptSyncWithModelSuggestionRetry to model-suggestion-retry.ts
- Switch look_at from promptWithModelSuggestionRetry to sync variant
- Add comprehensive tests for the new sync function
- No changes to other callers (delegate-task, background-agent)
2026-02-08 02:36:27 +09:00
Peïo Thibault
414cecd7df test: add promptAsync mocks to all test files for promptAsync migration 2026-02-07 14:41:46 +01:00
Peïo Thibault
fad7354b13 fix(look-at): remove isJsonParseError band-aid (root cause fixed) 2026-02-07 13:46:03 +01:00
Peïo Thibault
55dc64849f fix(tools): switch session.prompt to promptAsync in delegate-task and call-omo-agent 2026-02-07 13:43:06 +01:00
Peïo Thibault
46e02b9457 fix(hooks): switch session.prompt to promptAsync in all hooks 2026-02-07 13:42:24 +01:00
YeonGyu-Kim
89b1205ccf
Merge pull request #1607 from code-yeongyu/fix/358-skill-description-truncation
fix: use character limit instead of sentence split for skill description (#358)
2026-02-07 19:17:27 +09:00
YeonGyu-Kim
c81384456c
Merge pull request #1606 from code-yeongyu/fix/658-tools-ctx-directory
fix: use ctx.directory instead of process.cwd() in tools for Desktop app support
2026-02-07 19:12:25 +09:00
YeonGyu-Kim
c688e978fd fix: update session-manager tests to use factory pattern 2026-02-07 19:10:14 +09:00
YeonGyu-Kim
a0201e17b9 fix: use character limit instead of sentence split for skill description (#358)
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-07 19:08:08 +09:00
YeonGyu-Kim
476f154ef5 fix: use ctx.directory instead of process.cwd() in tools for Desktop app support
Convert grep, glob, ast-grep, and session-manager tools from static exports to factory functions that receive PluginInput context. This allows them to use ctx.directory instead of process.cwd(), fixing issue #658 where tools search from wrong directory in OpenCode Desktop app.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-07 19:04:31 +09:00
YeonGyu-Kim
2bb82c250c fix: expand ALLOWED_AGENTS to include all subagent-capable agents 2026-02-07 18:57:47 +09:00
YeonGyu-Kim
7fdbabb264 fix: don't fallback to system 'sg' command for ast-grep
On Linux systems, 'sg' is a mailutils command, not ast-grep. The previous
fallback would silently run the wrong binary when ast-grep wasn't found.

Changes:
- getSgCliPath() now returns string | null instead of string
- Fallback changed from 'sg' to null
- Call sites now check for null and return user-facing error with
  installation instructions
- checkEnvironment() updated to handle null path

Fixes #1365
2026-02-07 18:46:01 +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
f1b2f6f3f7
Merge pull request #1556 from code-yeongyu/fix/1265-sisyphus-junior-model-inheritance
fix(config): stop sisyphus-junior from inheriting UI-selected model
2026-02-06 18:57:42 +09:00
YeonGyu-Kim
3a0d7e8dc3 fix(config): stop sisyphus-junior from inheriting UI-selected model 2026-02-06 17:44:47 +09:00
YeonGyu-Kim
6b560ebf9e fix(delegate-task): make plan agent categories/skills dynamic
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-06 17:31:13 +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
4c7215404e chore: update gpt-5.2-codex references to gpt-5.3-codex 2026-02-06 15:08:33 +09:00
YeonGyu-Kim
b8d7723f0a feat(agents): improve Hephaestus autonomous problem-solving behavior
- Add Core Principle section emphasizing autonomous recovery over asking
- Enhance Role & Agency with explicit wall-hitting protocol (3+ approaches before asking)
- Transform Failure Recovery from '3 consecutive failures' to 'autonomous recovery first'
- Relax Output Contract to allow creative problem-solving when blocked
- Remove conflicting 'ask when uncertain' guideline (conflicts with EXPLORE-FIRST)
2026-02-05 22:14:53 +09:00
YeonGyu-Kim
8ff9c24623 fix(lsp): use Node.js child_process on Windows to avoid Bun spawn segfault
Bun has unfixed segfault issues on Windows when spawning subprocesses
(oven-sh/bun#25798, #26026, #23043). Even upgrading to Bun v1.3.6+
does not resolve the crashes.

Instead of blocking LSP on Windows with version checks, use Node.js
child_process.spawn as fallback. This allows LSP to work on Windows
regardless of Bun version.

Changes:
- Add UnifiedProcess interface bridging Bun Subprocess and Node ChildProcess
- Use Node.js spawn on Windows, Bun spawn on other platforms
- Add CWD validation before spawn to prevent libuv null dereference
- Add binary existence pre-check on Windows with helpful error messages
- Enable shell: true for Node spawn on Windows for .cmd/.bat resolution
- Remove ineffective Bun version blocking (v1.3.5 check)
- Add tests for CWD validation and start() error handling

Closes #1047
Ref: oven-sh/bun#25798
2026-02-05 15:57:20 +09:00
YeonGyu-Kim
71ac09bb63 fix: use process.cwd() instead of ctx.directory for glob/grep tools
ToolContext type from @opencode-ai/plugin/tool does not include
a 'directory' property, causing typecheck failure after rebase from dev.

Changed to use process.cwd() which is the same pattern used in
session-manager/tools.ts.
2026-02-05 02:23:48 +09:00
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
8d0fa97b72
Merge pull request #1471 from high726/fix/look-at-clipboard-image-support
feat(look_at): add image_data parameter for clipboard/pasted image support
2026-02-04 15:55:29 +09:00
YeonGyu-Kim
d66e39a887 refactor(tasks): consolidate task-list path resolution to use getTaskDir 2026-02-04 15:12:28 +09:00
YeonGyu-Kim
d14f32f2d5
Merge pull request #1470 from Lynricsy/fix/categories-model-precedence
fix(delegate-task): honor explicit category model over sisyphus-junior
2026-02-04 13:52:25 +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
51c7fee34c
Merge pull request #1280 from Zacks-Zhang/fix/fix-stale-lsp-diagnostics
fix(lsp): prevent stale diagnostics by syncing didChange
2026-02-04 13:35:07 +09:00
YeonGyu-Kim
5dabb8a198
Merge pull request #1393 from ualtinok/dev
fix: grep and glob tools usage without path param under Opencode Desktop
2026-02-04 13:34:52 +09:00
lihaitao
d099b0255f feat(look_at): add image_data parameter for clipboard/pasted image support
Closes #704

Add support for base64-encoded image data in the look_at tool,
enabling analysis of clipboard/pasted images without requiring
a file path.

Changes:
- Add optional image_data parameter to LookAtArgs type
- Update validateArgs to accept either file_path or image_data
- Add inferMimeTypeFromBase64 function to detect image format
- Add try/catch around atob() to handle invalid base64 gracefully
- Update execute to handle both file path and data URL inputs
- Add comprehensive tests for image_data functionality
2026-02-04 12:24:00 +08:00
Lynricsy
1411ca255a
fix(delegate-task): honor explicit category model over sisyphus-junior 2026-02-04 11:51:20 +08:00
YeonGyu-Kim
4330f25fee revert(call-omo-agent): remove metis/momus from ALLOWED_AGENTS
call_omo_agent is for lightweight exploration agents (explore, librarian).
metis/momus are consultation agents that should be invoked via delegate_task.

Reverts part of #1462 that incorrectly added metis/momus to call_omo_agent.
2026-02-04 11:38:24 +09:00
YeonGyu-Kim
49a4a1bf9e
fix(call-omo-agent): allow Prometheus to call Metis and Momus (#1462)
* fix(call-omo-agent): allow Prometheus to call Metis and Momus

* fix(call-omo-agent): update help text and remove unrelated bun.lock

- Update subagent_type description to include metis and momus
- Remove unrelated bun.lock changes (keeps PR scope tight)
- Addresses Oracle review feedback
2026-02-04 11:27:14 +09:00
YeonGyu-Kim
5ffecb60c9
fix(skill-mcp): avoid propertyNames for Gemini compatibility (#1465)
- Replace record(string, unknown) with object({}) in arguments schema
- record() generates propertyNames which Gemini rejects with 400 error
- object({}) generates plain { type: 'object' } without propertyNames
- Runtime parseArguments() already handles arbitrary object keys

Fixes #1315
2026-02-04 11:26:34 +09:00
YeonGyu-Kim
b954afca90
fix(model-requirements): use supported variant for gemini-3-pro (#1463)
* fix(model-requirements): use supported variant for gemini-3-pro

* fix(delegate-task): update artistry variant to high for gemini-3-pro

- Update DEFAULT_CATEGORIES artistry variant from 'max' to 'high'
- Update related test comment
- gemini-3-pro only supports low/high thinking levels, not max
- Addresses Oracle review feedback
2026-02-04 11:26:17 +09:00
Muhammad Noor Misyuari
ba2a9a9051
fix: update skill resolution to support disabled skills functionality 2026-02-03 15:19:08 +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
d7679e148e feat(delegate-task): add actionable TODO list template to plan agent prompt
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-03 15:58:06 +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
dea13a37a6
feat(task-system): add experimental task system with Claude Code spec alignment (#1415)
* feat(hooks): add tasks-todowrite-disabler hook to block TodoRead/TodoWrite

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

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

* feat(task-tools): add parallel execution guidance to descriptions

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

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

* refactor(index): migrate task system to experimental.task_system flag

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

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

* docs: update AGENTS.md for experimental task system

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

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

* fix(task-tests): align test field names with Claude Code spec (subject, blockedBy, addBlockedBy)

* fix: address Cubic review feedback

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

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

* fix: add optional chaining for tasksTodowriteDisabler null check

---------

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-03 12:11:23 +09:00
YeonGyu-Kim
8441f70c2b
fix(delegate-task): honor sisyphus-junior model override precedence (#1404) 2026-02-03 10:41:26 +09:00
ismeth
527c21ea90 fix(tools): for overridden tools (glob, grep) path should use ctx.directory. OpenCode Desktop might not send path as a param and cwd might resolve to "/" 2026-02-02 11:34:33 +01:00
YeonGyu-Kim
76623454de test(task): improve todo-sync tests with bun-types and inline assertions
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
2026-02-02 16:50:13 +09:00
YeonGyu-Kim
0ea92124a7 feat(task): add real-time single-task todo sync via OpenCode API
- Add syncTaskTodoUpdate function for immediate todo updates
- Integrate with TaskCreate and TaskUpdate tools
- Preserve existing todos when updating single task
- Add comprehensive tests for new sync function

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-02-02 15:05:07 +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
6288251a67 refactor(task): update schema to Claude Code field names (subject, blockedBy, blocks, etc.) 2026-02-02 13:13:06 +09:00
YeonGyu-Kim
b71fe66a7e feat(task): implement TaskUpdate tool with additive blocks/blockedBy and metadata merge 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