Commit Graph

43 Commits

Author SHA1 Message Date
YeonGyu-Kim
bfe1730e9f feat(categories): add disable field to CategoryConfigSchema
Allow individual categories to be disabled via `disable: true` in
config. Introduce shared `mergeCategories()` utility to centralize
category merging and disabled filtering across all 7 consumption sites.
2026-02-11 13:52:20 +09:00
YeonGyu-Kim
a5bdb64933 fix(delegation): restore category to sisyphus-junior auto-mapping
Category-based delegation should always route to sisyphus-junior even if
subagent_type is mistakenly provided, matching the original behavior and
preventing accidental bypass of category routing.
2026-02-09 16:14:30 +09:00
YeonGyu-Kim
c9be2e1696 refactor: extract model selection logic from delegate-task into focused modules
- Create available-models.ts for model availability checking
- Create model-selection.ts for category-to-model resolution logic
- Update category-resolver, subagent-resolver, and sync modules to import
  from new focused modules instead of monolithic sources
2026-02-08 18:03:15 +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
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
Muhammad Noor Misyuari
ba2a9a9051 fix: update skill resolution to support disabled skills functionality 2026-02-03 15:19:08 +07:00
YeonGyu-Kim
f146aeff0f refactor: major codebase cleanup - BDD comments, file splitting, bug fixes (#1350)
* style(tests): normalize BDD comments from '// #given' to '// given'

- Replace 4,668 Python-style BDD comments across 107 test files
- Patterns changed: // #given -> // given, // #when -> // when, // #then -> // then
- Also handles no-space variants: //#given -> // given

* fix(rules-injector): prefer output.metadata.filePath over output.title

- Extract file path resolution to dedicated output-path.ts module
- Prefer metadata.filePath which contains actual file path
- Fall back to output.title only when metadata unavailable
- Fixes issue where rules weren't injected when tool output title was a label

* feat(slashcommand): add optional user_message parameter

- Add user_message optional parameter for command arguments
- Model can now call: command='publish' user_message='patch'
- Improves error messages with clearer format guidance
- Helps LLMs understand correct parameter usage

* feat(hooks): restore compaction-context-injector hook

- Restore hook deleted in cbbc7bd0 for session compaction context
- Injects 7 mandatory sections: User Requests, Final Goal, Work Completed,
  Remaining Tasks, Active Working Context, MUST NOT Do, Agent Verification State
- Re-register in hooks/index.ts and main plugin entry

* refactor(background-agent): split manager.ts into focused modules

- Extract constants.ts for TTL values and internal types (52 lines)
- Extract state.ts for TaskStateManager class (204 lines)
- Extract spawner.ts for task creation logic (244 lines)
- Extract result-handler.ts for completion handling (265 lines)
- Reduce manager.ts from 1377 to 755 lines (45% reduction)
- Maintain backward compatible exports

* refactor(agents): split prometheus-prompt.ts into subdirectory

- Move 1196-line prometheus-prompt.ts to prometheus/ subdirectory
- Organize prompt sections into separate files for maintainability
- Update agents/index.ts exports

* refactor(delegate-task): split tools.ts into focused modules

- Extract categories.ts for category definitions and routing
- Extract executor.ts for task execution logic
- Extract helpers.ts for utility functions
- Extract prompt-builder.ts for prompt construction
- Reduce tools.ts complexity with cleaner separation of concerns

* refactor(builtin-skills): split skills.ts into individual skill files

- Move each skill to dedicated file in skills/ subdirectory
- Create barrel export for backward compatibility
- Improve maintainability with focused skill modules

* chore: update import paths and lockfile

- Update prometheus import path after refactor
- Update bun.lock

* fix(tests): complete BDD comment normalization

- Fix remaining #when/#then patterns missed by initial sed
- Affected: state.test.ts, events.test.ts

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-02-01 16:47:50 +09:00
YeonGyu-Kim
4a82ff40fb Consolidate duplicate patterns and simplify codebase (#1317)
* refactor(shared): unify binary downloader and session path storage

- Create binary-downloader.ts for common download/extract logic
- Create session-injected-paths.ts for unified path tracking
- Refactor comment-checker, ast-grep, grep downloaders to use shared util
- Consolidate directory injector types into shared module

* feat(shared): implement unified model resolution pipeline

- Create ModelResolutionPipeline for centralized model selection
- Refactor model-resolver to use pipeline
- Update delegate-task and config-handler to use unified logic
- Ensure consistent model resolution across all agent types

* refactor(agents): simplify agent utils and metadata management

- Extract helper functions for config merging and env context
- Register prompt metadata for all agents
- Simplify agent variant detection logic

* cleanup: inline utilities and remove unused exports

- Remove case-insensitive.ts (inline with native JS)
- Simplify opencode-version helpers
- Remove unused getModelLimit, createCompactionContextInjector exports
- Inline transcript entry creation in claude-code-hooks
- Update tests accordingly

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-31 15:46:14 +09:00
justsisyphus
2c74f608f0 feat(delegate-task, agents): check requiresModel for conditional activation 2026-01-30 15:11:27 +09:00
justsisyphus
c06f38693e refactor: revamp ultrabrain category with deep work mindset
- Add variant: max to ultrabrain's gemini-3-pro fallback entry
- Rename STRATEGIC_CATEGORY_PROMPT_APPEND to ULTRABRAIN_CATEGORY_PROMPT_APPEND
- Keep original strategic advisor prompt content (no micromanagement instructions)
- Update description: use only for genuinely hard tasks, give clear goals only
- Update tests to match renamed constant
2026-01-30 14:53:50 +09:00
justsisyphus
ad95880198 fix(start-work): restore atlas agent and proper model fallback chain
- Restore agent: 'atlas' in start-work command (removed by PR #1201)
- Fix model-resolver to properly iterate through fallback chain providers
- Remove broken parent model inheritance that bypassed fallback logic
- Add model-suggestion-retry for runtime API failures (cherry-pick 800846c1)

Fixes #1200
2026-01-30 12:52:46 +09:00
justsisyphus
c905e1cb7a fix(delegate-task): restore resolved.model to category userModel chain (#1227)
PR #1227 incorrectly removed resolved.model from the userModel chain,
assuming it was bypassing the fallback chain. However, resolved.model
contained the category's DEFAULT_CATEGORIES model (e.g., quick ->
claude-haiku-4-5), not the main session model.

Without resolved.model, when connectedProvidersCache is null and
availableModels is empty, category model resolution falls through to
systemDefaultModel (opus) instead of using the category's default.

This fix restores the original priority:
1. User category model override
2. Category default model (from resolved.model)
3. sisyphusJuniorModel
4. Fallback chain
5. System default
2026-01-30 11:45:19 +09:00
YeonGyu-Kim
34aaef2219 fix(delegate-task): pass registered agent model explicitly for subagent_type (#1225)
When delegate_task uses subagent_type, extract the matched agent's model
object and pass it explicitly to session.prompt/manager.launch. This
ensures the model is always in the correct object format regardless of
how OpenCode handles string→object conversion for plugin-registered
agents.

Closes #1225
2026-01-29 11:27:07 +09:00
Mike
faca80caa9 fix(start-work): prevent overwriting session agent if already set; inherit parent model for subagent types (#1201)
* fix(start-work): prevent overwriting session agent if already set; inherit parent model for subagent types

* fix(model): include variant in StoredMessage model structure for better context propagation

* fix(injector): include variant in model structure for hook message injection
2026-01-29 09:30:37 +09:00
Peïo Thibault
bffa1ad43d fix(model-resolver): use connected providers cache when model cache is empty (#1227)
- Remove resolved.model from userModel in tools.ts (was bypassing fallback chain)
- Use connected providers cache in model-resolver when availableModels is empty
- Allows proper provider selection (e.g., github-copilot instead of google)
2026-01-29 09:30:19 +09:00
justsisyphus
30ed086c40 fix(delegate-task): use category default model when availableModels is empty 2026-01-29 01:11:42 +09:00
justsisyphus
dee89c1556 feat(delegate-task): add prometheus self-delegation block and delegate_task permission
- Block prometheus from delegating to itself via delegate_task
- Grant delegate_task permission to prometheus when called as subagent
- Other subagents still have delegate_task disabled
2026-01-28 18:24:15 +09:00
justsisyphus
6f348a8a5c fix: resolve CI test timeouts with configurable timing
- Add timing.ts module for test-only timing configuration
- Replace hardcoded wait times with getTimingConfig()
- Enable all previously skipped tests (ralph-loop, session-state, delegate-task)
- Tests now complete in ~2s instead of timing out
2026-01-28 14:17:56 +09:00
justsisyphus
aa1646f82c fix(delegate-task): pass variant as top-level field in prompt body
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-27 17:54:58 +09:00
justsisyphus
de439edc22 feat(subagent): block question tool at both SDK and hook level
- Add permission: [{ permission: 'question', action: 'deny' }] to session.create()
  in background-agent and delegate-task for SDK-level blocking
- Add subagent-question-blocker hook as backup layer to intercept question tool
  calls in tool.execute.before event
- Ensures subagents cannot ask questions to users and must work autonomously
2026-01-27 13:07:09 +09:00
justsisyphus
acded4ba2a fix(delegate-task): add clear error when model not configured (#1139) 2026-01-27 10:35:20 +09:00
justsisyphus
7e065dfe12 feat(delegate-task): prepend system prompt for plan agent invocations
When plan agent (plan/prometheus/planner) is invoked via delegate_task,
automatically prepend a <system> prompt instructing the agent to:
- Launch explore/librarian agents in background to gather context
- Summarize user request and list uncertainties
- Ask clarifying questions until requirements are 100% clear
2026-01-26 18:25:06 +09:00
justsisyphus
3ee519c7b0 feat: make systemDefaultModel optional for OpenCode fallback (#1136)
- Remove mandatory model requirement from plugin initialization
- Allow OpenCode to use its built-in model fallback when user doesn't specify
- Update model-resolver to handle undefined systemDefaultModel
- Remove throw errors in config-handler, utils, atlas, delegate-task
- Add tests for optional model scenarios

Closes #1129

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-26 17:01:08 +09:00
justsisyphus
68aa913499 refactor(tmux-subagent): state-first architecture with decision engine (#1125)
* refactor(tmux-subagent): add state-first architecture with decision engine

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

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

* feat(tmux): add pane spawn callbacks for background and sync sessions

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

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

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-26 12:02:37 +09:00
justsisyphus
3a79b8761b feat(shared): add connected-providers-cache for model availability (#1121)
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-26 11:53:41 +09:00
YeonGyu-Kim
3af30b0a21 feat(skills): add agent-browser option for browser automation (#1090)
Add configurable browser automation allowing users to choose between
Playwright MCP (default) and Vercel's agent-browser CLI.

Changes:
- Add browser_automation_engine.provider config option
- Dynamic skill loading based on provider selection
- Comprehensive agent-browser CLI reference (inline in skills.ts)
- Propagate browserProvider to delegate_task and buildAgent
- Update documentation with provider comparison

Co-authored-by: Suyeol Jeon <devxoul@gmail.com>
Co-authored-by: YeonGyu Kim <code.yeongyu@gmail.com>
2026-01-25 15:02:41 +09:00
justsisyphus
14f450bd25 refactor: sync delegate_task schema with OpenCode Task tool (resume→session_id, add command param) 2026-01-25 13:57:45 +09:00
justsisyphus
444fbe396a fix(delegate-task): use lowercase sisyphus-junior agent name in API calls
Previous fix (7ed7bf5c) only updated Atlas → atlas, but missed Sisyphus-Junior.
OpenCode does case-sensitive agent lookup, causing crash when delegate_task
tried to spawn 'Sisyphus-Junior' (registered as 'sisyphus-junior').

- SISYPHUS_JUNIOR_AGENT constant: 'Sisyphus-Junior' → 'sisyphus-junior'
- agent-tool-restrictions key: 'Sisyphus-Junior' → 'sisyphus-junior'
- Updated related test mocks
2026-01-24 03:00:58 +09:00
justsisyphus
f4348885f2 fix: model fallback properly falls through to system default
- Remove Step 3 in model-resolver that forced first fallbackChain entry
  even when unavailable, blocking system default fallback
- Add sisyphusJuniorModel option to delegate_task so agents["Sisyphus-Junior"]
  model override is respected in category-based delegation
- Update tests to reflect new fallback behavior
2026-01-23 10:56:31 +09:00
justsisyphus
6e84a14f20 fix(model-resolver): return variant from fallback chain, handle model name normalization
- Add variant to ModelResolutionResult return type
- Return variant from matched fallback entry
- Add normalizeModelName() for Claude model hyphen/period differences
- Add transformModelForProvider() for github-copilot model names
- Update delegate-task to use resolved variant (user config takes priority)
- Fix test expectations for new fallback behavior
2026-01-23 02:20:32 +09:00
justsisyphus
45b2782d55 refactor: use case-insensitive matching for agent names
Apply case-insensitive utilities across agents, delegation, and tool
restrictions. Removes duplicate implementations from agents/utils.ts.
Agent validation now normalizes input to canonical names.
2026-01-23 00:55:01 +09:00
justsisyphus
aa2b052d28 refactor(delegate-task): enhance delegation with dynamic descriptions
Generate tool description dynamically from available categories and skills. Remove hardcoded DELEGATE_TASK_DESCRIPTION constant. Improve parameter handling with unified 'subagent_type' field replacing 'agent'.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-22 22:46:23 +09:00
justsisyphus
516edb445c fix(delegate-task): wait for result when forcing unstable agents to background
Previously, unstable agents (gemini models, is_unstable_agent=true) were
forced to background mode but returned immediately with task ID. This
caused callers to lose visibility into results.

Now: launch as background for monitoring stability, but poll and wait
for completion, returning actual task output like sync mode.

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-01-21 11:19:00 +09:00
justsisyphus
18e02a33be feat(delegate-task): force background mode for unstable agents
Detects unstable agents via is_unstable_agent config or gemini in model
name. Forces background mode even when run_in_background=false, with
system message explaining the forced conversion for monitoring.
2026-01-20 18:48:13 +09:00
justsisyphus
3d3d3e493b fix(delegate-task): category built-in model takes precedence over inherited model
Previously, when using categories like 'quick', the parent session's model
(e.g., Opus 4.5) would override the category's built-in model (e.g., Haiku).

Fixed priority: userConfig.model → category built-in → systemDefault

The inherited model from parent session no longer affects category-based
delegation - categories have their own explicit models.
2026-01-20 17:05:17 +09:00
justsisyphus
8cc995891e refactor(delegate-task): restructure category system for unbiased model selection
- Remove temperature from all categories
- Consolidate CATEGORY_MODEL_CATALOG into DEFAULT_CATEGORIES
- Replace 'general' and 'most-capable' with 'unspecified-low' and 'unspecified-high'
- Add Selection_Gate to unspecified categories to force deliberate selection
- Update quick category to use claude-haiku-4-5
- Update all references and tests across codebase
2026-01-20 16:22:53 +09:00
justsisyphus
52d9b30035 refactor(plugin): update atlas references
Update plugin handlers, commands, and integration points to use 'atlas' agent name. Start-work command and config handler now reference 'atlas'.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-20 15:55:09 +09:00
justsisyphus
c4b862cbc4 refactor(hooks): rename sisyphus-orchestrator to atlas
Hook name is now 'atlas' (not 'atlas-orchestrator'). Directory renamed to src/hooks/atlas/. All references updated.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-20 15:52:13 +09:00
Kenny
6956ce0a19 fix: correct config.data.model access pattern and use dynamic config paths
- Fixed delegate-task/tools.ts to access openCodeConfig.data.model instead of openCodeConfig.model
- Updated error messages to use getOpenCodeConfigPaths() for cross-platform paths
- Fixed 12 test mocks to use correct { data: { model: ... } } structure
- Fixes delegation failing with 'requires a default model' even when model is configured
2026-01-18 22:08:27 -05:00
Kenny
c698a5b888 fix: remove hardcoded model defaults from categories and agents
BREAKING CHANGE: Model resolution overhauled

- Created centralized model-resolver.ts with priority chain:
  userModel → inheritedModel → systemDefaultModel
- Removed model field from all 7 DEFAULT_CATEGORIES entries
- Removed DEFAULT_MODEL constants from 10 agents
- Removed singleton agent exports (use factories instead)
- Made CategoryConfigSchema.model optional
- CLI no longer generates model overrides
- Empty strings treated as unset (uses fallback)

Users must now:
1. Use factory functions (createOracleAgent, etc.) instead of singletons
2. Provide model explicitly or use systemDefaultModel
3. Configure category models explicitly if needed

Fixes model fallback bug where hardcoded defaults overrode
user's OpenCode configured model.
2026-01-17 12:51:03 -05:00
justsisyphus
255f535a50 refactor(delegate-task): use empty array instead of null for skills parameter
- Change skills type from string[] | null to string[]
- Allow skills=[] for no skills, reject skills=null
- Remove emojis from error messages and prompts
- Update tests accordingly
2026-01-17 21:25:02 +09:00
justsisyphus
cb6f1c9f75 fix(delegate-task): category default model takes precedence over parent model
Previously, parent model string would override category default model,
causing categories like 'ultrabrain' to use the parent's model (e.g., sonnet)
instead of the intended category default (e.g., gpt-5.2).

Model priority is now:
1. userConfig.model (oh-my-opencode.json override)
2. defaultConfig.model (category default)
3. parentModelString (fallback)
4. systemDefaultModel (last resort)
2026-01-16 18:45:19 +09:00
justsisyphus
188bbef018 refactor: rename sisyphus_task to delegate_task
- Rename directories: sisyphus-task → delegate-task
- Rename types: SisyphusTaskArgs → DelegateTaskArgs, etc.
- Rename functions: createSisyphusTask → createDelegateTask
- Rename constants: SISYPHUS_TASK_* → DELEGATE_TASK_*
- Update tool name: sisyphus_task → delegate_task
- Update all prompts, docs, and tests
2026-01-16 18:31:08 +09:00