Commit Graph

782 Commits

Author SHA1 Message Date
justsisyphus f1393d3e85 docs: regenerate hierarchical AGENTS.md with deep investigation
- Root: 181 lines with agent models, complexity hotspots, CI pipeline
- Hooks: 31 lifecycle hooks, execution order, patterns
- Tools: 20+ tools, LSP/AST-Grep specifics, registration
- Features: Background agents, Claude Code compat, skill MCP
- Agents: 10 agents with models, tool restrictions
- Shared: 43 utilities with usage patterns
- CLI: Commander.js entry, doctor checks, TUI framework

Generated via /init-deep with 12 parallel explore agents
2026-01-17 22:01:56 +09:00
justsisyphus 86af550056 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 a104a05287 fix(momus): constrain reviewer to evaluate documentation, not design direction
Momus was rejecting plans by questioning implementation approaches instead
of reviewing documentation quality. Added explicit constraints:

- ABSOLUTE CONSTRAINT section: reviewer role, not designer
- MUST NOT question architecture/approach choices
- Self-check prompts to detect overstepping
- NOT Valid REJECT Reasons section
- Reinforced throughout: documentation quality vs design decisions
2026-01-17 21:25:02 +09:00
justsisyphus db41a6fb01 chore: remove 1,152 lines of verified dead code (#874)
* chore(deps): remove unused dependencies

Removed @openauthjs/openauth, hono, open, and xdg-basedir - none are imported in src/

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

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

* chore(cleanup): remove unused agent prompts and tool files

Deleted:
- src/agents/build-prompt.ts (exports never imported)
- src/agents/plan-prompt.ts (exports never imported)
- src/tools/ast-grep/napi.ts (never imported)
- src/tools/interactive-bash/types.ts (never imported)

Verified by: LSP FindReferences + explore agents

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

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

* chore(hooks): remove unused comment-checker filters

Deleted entire filters/ directory:
- filters/bdd.ts
- filters/directive.ts
- filters/docstring.ts
- filters/shebang.ts
- filters/index.ts

Not used by main hook (cli.ts uses external binary instead)

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

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

* chore(hooks): remove unused comment-checker output and constants

Deleted:
- output/formatter.ts
- output/xml-builder.ts
- output/index.ts
- constants.ts

All 0 external imports - migrated to external binary

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

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

* chore(hooks): remove unused pruning subsystem

Deleted pruning subsystem (dependency order):
- pruning-purge-errors.ts
- pruning-storage.ts
- pruning-supersede.ts
- pruning-executor.ts

Not imported by main recovery hook

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

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

* chore(hooks): remove unused createBackgroundCompactionHook export

Removed export from index.ts - never imported in src/index.ts

Verified by: LSP FindReferences (only 2 refs: definition + barrel export)

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

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

---------

Co-authored-by: justsisyphus <sisyphus-dev-ai@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-17 21:12:55 +09:00
YeonGyu-Kim 3afc8e777f Add /ulw-loop command for ultrawork mode loop (#867)
* feat(ralph-loop): add ultrawork field to RalphLoopState

* feat(ralph-loop): persist ultrawork field in storage

* feat(ralph-loop): accept ultrawork option in startLoop

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

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

* feat(ralph-loop): prepend ultrawork keyword when mode active

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

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

* feat(ralph-loop): custom toast for ultrawork mode

* feat(ralph-loop): add /ulw-loop command for ultrawork mode

* fix(ralph-loop): add non-null assertion for type safety

* fix(ralph-loop): mirror argument parsing in ulw-loop handler

- Parse quoted prompts and strip flags from task text
- Support --max-iterations and --completion-promise options
- Add default prompt for empty input
- Fixes behavior inconsistency with /ralph-loop

---------

Co-authored-by: justsisyphus <sisyphus-dev-ai@users.noreply.github.com>
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-17 19:56:50 +09:00
justsisyphus 825d636bf2 docs(agents): regenerate hierarchical AGENTS.md with init-deep
- Root AGENTS.md: Updated timestamp, commit hash, line counts
- src/agents/AGENTS.md: Updated to 50 lines, current structure
- src/cli/AGENTS.md: Updated to 57 lines, current structure
- src/features/AGENTS.md: Updated to 65 lines, current structure
- src/hooks/AGENTS.md: Updated to 53 lines, current structure
- src/shared/AGENTS.md: Updated to 52 lines, core utilities
- src/tools/AGENTS.md: Updated to 50 lines, tool categories

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-01-17 19:16:49 +09:00
justsisyphus 98e91e508c fix(lsp): display diagnostics errors as error blocks in TUI
- Changed lsp_diagnostics error handling to throw errors instead of returning strings
- Line 211: Changed from `return output` to `throw new Error(output)`
- Makes errors display as proper error blocks in TUI

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-17 18:14:50 +09:00
justsisyphus 9d815a5697 feat(skill-mcp): add auto-reconnect retry on "Not connected" errors
- Added withOperationRetry<T>() helper method that retries operations up to 3 times
- Catches "Not connected" errors (case-insensitive)
- Cleans up stale client before retry
- Modified callTool, readResource, getPrompt to use retry logic
- Added tests for retry behavior (3 new test cases)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-01-17 18:14:48 +09:00
justsisyphus d44c494fd9 chore(release): bump platform packages to 3.0.0-beta.9
🤖 Generated with OhMyOpenCode assistance
2026-01-17 17:58:54 +09:00
Jeremy Gollehon ace7557de3 Merge pull request #846 from LTS2/fix/826-sisyphus-junior-model-override
fix: pass model parameter when resuming background tasks

Ensure resumed tasks maintain their original model configuration
from category settings, preventing unexpected model switching.
2026-01-17 00:52:46 -08:00
justsisyphus cee3e465ca test(background-agent): add stale detection unit tests 2026-01-17 17:43:16 +09:00
justsisyphus 0f30074869 feat(background-agent): add stale session detection and auto-interrupt 2026-01-17 17:40:58 +09:00
justsisyphus c537862667 feat(config): add staleTimeoutMs to BackgroundTaskConfig 2026-01-17 17:39:39 +09:00
justsisyphus c0ecead2a7 fix(test): skip flaky mainSessionID test for now 2026-01-17 17:12:59 +09:00
justsisyphus 51e1b93bcd fix(test): add _resetForTesting to all session state tests 2026-01-17 17:04:40 +09:00
justsisyphus c1e42d71b3 fix(test): add _resetForTesting for proper test isolation 2026-01-17 16:57:31 +09:00
justsisyphus 959fe81834 fix(test): add nested beforeEach for mainSessionID test isolation
Previous test was setting mainSessionID to 'main-session-123' and the
next test expected undefined. The outer beforeEach wasn't properly
resetting state between tests in the nested describe block.

Adding a nested beforeEach ensures proper test isolation.
2026-01-17 16:47:56 +09:00
Sangguen Chang a35c7573cc fix(keyword-detector): skip keyword detection for background task sessions
Skip all keyword detection for background task sessions to prevent mode
injection (e.g., [analyze-mode], [search-mode]) which incorrectly triggers
Prometheus planner restrictions on Sisyphus sessions.

This aligns with the existing pattern used in:
- sisyphus-orchestrator (line 504)
- todo-continuation-enforcer (line 303)
- session-notification (line 278)

Closes #713
2026-01-17 10:23:23 +09:00
Kenny 83bb510b35 Merge pull request #855 from luojiyin1987/fix/doctor-windows-opencode
fix: handle opencode.ps1 in doctor on Windows
2026-01-16 15:36:58 -05:00
qwertystars 3d799749b8 fix(migration): correct import path for DEFAULT_CATEGORIES
The import was pointing to non-existent sisyphus-task/constants,
updated to delegate-task/constants where DEFAULT_CATEGORIES is defined.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-16 23:42:41 +05:30
luojiyin e1569eb61c fix: handle opencode.ps1 in doctor on Windows
Handle Windows where lookup and prefer exe/cmd/bat; fall back to ps1 and run via PowerShell for version detection.

Tests: bun test src/cli/doctor/checks/opencode.test.ts
2026-01-16 23:42:08 +08:00
Kenny 1cb1127e2f Merge pull request #834 from MotorwaySouth9/fix/windows-lsp-doctor-and-detection
fix(lsp): improve Windows server detection and avoid unix 'which' in doctor
2026-01-16 07:24:05 -05:00
Kenny d516dde6a8 Merge pull request #847 from minkichoe-lbox/fix/dynamic-year
fix(librarian): use dynamic year instead of hardcoded 2024/2025
2026-01-16 07:14:58 -05:00
justsisyphus 3df60fd449 fix(sisyphus-orchestrator): add debounce to boulder continuation to prevent infinite loop
Add 5-second cooldown between continuation injections to prevent rapid-fire
session.idle events from causing infinite loop when boulder has incomplete tasks.
2026-01-16 19:17:26 +09:00
justsisyphus b10d57a083 fix(keyword-detector): use session state for agent-specific ultrawork templates
Bug: When switching from Prometheus to Sisyphus, the Prometheus ultrawork
template was still injected because:
1. setSessionAgent() only sets on first call, ignoring subsequent updates
2. keyword-detector relied solely on input.agent which could be stale

Fix:
- Use updateSessionAgent() instead of setSessionAgent() in index.ts
- keyword-detector now uses getSessionAgent() as primary source, fallback to input.agent
- Added tests for agent switch scenario
2026-01-16 19:06:00 +09:00
justsisyphus 579b70b154 feat(toast): show warning only for fallback models (inherited/system-default)
category-default is the intended behavior for builtin categories,
not a fallback. Only show toast warning when:
- inherited: model from parent session (custom category without model)
- system-default: OpenCode's global default model

User-defined and category-default are both expected behaviors,
so no warning is needed.
2026-01-16 18:47:36 +09:00
justsisyphus c26024ab2e 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 2120e0dbde refactor(agent-tool-restrictions): use boolean for SDK tools parameter
OpenCode SDK's session.prompt tools parameter expects boolean values.
Changed from PermissionValue ('deny'/'allow') to boolean (false/true).
2026-01-16 18:31:08 +09:00
justsisyphus cb39218a44 fix(context-injector): add mainSessionID fallback for synthetic part injection
The transform hook was failing to inject synthetic parts because
message.info.sessionID is not always available in the OpenCode SDK.

Fix: Use getMainSessionID() as fallback when message.info.sessionID is undefined.

This ensures keyword-detector and claude-code-hooks content (like ulw/ultrawork)
is properly injected even when the SDK doesn't provide sessionID in message.info.
2026-01-16 18:31:08 +09:00
justsisyphus b439654ec9 test(context-injector): update tests for synthetic part injection
- Remove injectPendingContext test block (~118 lines)
- Remove createContextInjectorHook test block (~50 lines)
- Remove imports of removed functions
- Remove exports of removed functions from index.ts
- Keep createContextInjectorMessagesTransformHook tests (updated in Task 2)
2026-01-16 18:31:08 +09:00
justsisyphus 1695cc22b0 chore(index): remove contextInjector chat.message hook call
- Remove createContextInjectorHook from imports
- Remove contextInjector variable declaration
- Remove contextInjector["chat.message"] call
- Keep contextInjectorMessagesTransform for synthetic part injection
- Update test: prepend → synthetic part insertion verification
2026-01-16 18:31:08 +09:00
justsisyphus 0845e91b43 refactor(context-injector): remove chat.message hook, insert synthetic part in transform
- Remove injectPendingContext function (no longer needed)
- Remove createContextInjectorHook function (chat.message hook removed)
- Change transform hook from prepend to synthetic part insertion
- Follow empty-message-sanitizer pattern (minimal field set)
- synthetic: true flag hides content from UI but passes to model
- Synthetic part inserted BEFORE user text part
2026-01-16 18:31:08 +09:00
justsisyphus 7897650c5c 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
justsisyphus c259836686 feat(prometheus): auto-generate plan workflow with self-review
- Remove intermediate questions before plan generation
- Auto-proceed with Metis consultation
- Generate plan immediately after Metis review
- Add Post-Plan Self-Review with gap classification:
  - CRITICAL: requires user input
  - MINOR: auto-resolve silently
  - AMBIGUOUS: apply default and disclose
- Present summary with auto-resolved items and decisions needed
- Ask high accuracy question after summary
2026-01-16 18:31:08 +09:00
ewjin 815475e383 fix(background-agent): pass model on resume to preserve category config
The resume method was not passing the stored model from the task,
causing Sisyphus-Junior to revert to the default model when resumed.

This fix adds the model to the prompt body in resume(), matching
the existing behavior in launch().

Fixes #826
2026-01-16 18:21:31 +09:00
minkichoe 0d256c65cc fix(librarian): use dynamic year instead of hardcoded 2024/2025 2026-01-16 18:14:00 +09:00
justsisyphus 4e10c4dc8e feat: allow Sisyphus-Junior to call sisyphus_task 2026-01-16 17:14:31 +09:00
justsisyphus 47c6bafb8a feat: global sisyphus_task deny with orchestrator exceptions
- Add sisyphus_task: deny to global config.permission
- Add sisyphus_task: allow exception for orchestrator-sisyphus, Sisyphus, and Prometheus (Planner)
- Ensures only orchestrator agents can spawn sisyphus_task subagents
2026-01-16 17:13:08 +09:00
justsisyphus 97d15e1d68 refactor: remove legacy tools format, use permission only
BREAKING: Requires OpenCode 1.1.1+

- Remove supportsNewPermissionSystem/usesLegacyToolsSystem checks
- Simplify permission-compat.ts to permission format only
- Unify explore/librarian deny lists: write, edit, task, sisyphus_task, call_omo_agent
- Add sisyphus_task to oracle deny list
- Update agent-tool-restrictions.ts with correct per-agent restrictions
- Clean config-handler.ts conditional version checks
- Update tests for simplified API
2026-01-16 17:11:34 +09:00
justsisyphus 494732e96b feat(multimodal-looker): restrict to read-only tool access
Use createAgentToolAllowlist to allow only 'read' tool for multimodal-looker agent.
Previously denied write/edit/bash but allowed other tools.
Now uses wildcard deny pattern (*: deny) with explicit read allow.

- Add createAgentToolAllowlist function for allowlist-based restrictions
- Support legacy fallback for older OpenCode versions
- Add 4 test cases covering both permission systems
2026-01-16 15:02:55 +09:00
justsisyphus ecdb1a9104 feat(orchestrator): emphasize project-level lsp_diagnostics and QA verification
- Add mandatory PROJECT-LEVEL code checks (lsp_diagnostics at src/ or . level)
- Strengthen verification duties with explicit QA checklist
- Add 'SUBAGENTS LIE - VERIFY EVERYTHING' reminders throughout
- Emphasize that only orchestrator sees full picture of cross-file impacts
2026-01-16 14:11:56 +09:00
justsisyphus 9e2c2dd3e3 refactor(agents): remove lsp_diagnostics from Sisyphus and Sisyphus-Junior prompts
Orchestrator Sisyphus will handle project-level code validation instead of
having each subagent run file-level lsp_diagnostics.
2026-01-16 14:09:28 +09:00
justsisyphus 15816c78bd fix(hooks): prevent start-work false trigger from command description
- Remove 'Start Sisyphus work session' text check, keep only <session-context> tag
- Update interactive_bash description with WARNING: TMUX ONLY emphasis
- Update tests to use <session-context> wrapper
2026-01-16 14:01:29 +09:00
justsisyphus 227cc52f20 fix(hooks): extract model from assistant messages with flat modelID/providerID
OpenCode API returns different structures for user vs assistant messages:
- User: info.model = { providerID, modelID } (nested)
- Assistant: info.modelID, info.providerID (flat top-level)

Previous code only checked nested format, causing model info loss when
continuation hooks fired after assistant messages.

Files modified:
- todo-continuation-enforcer.ts
- ralph-loop/index.ts
- sisyphus-task/tools.ts
- background-agent/manager.ts

Added test for assistant message model extraction.
2026-01-16 13:54:22 +09:00
justsisyphus 1d47d54a51 refactor(orchestrator): restructure post-verification workflow as Step 4-6
- Unified verification (Step 1-3) and post-verification (Step 4-6) into continuous workflow
- Step 4: Immediate plan file marking after verification passes
- Step 5: Commit atomic unit
- Step 6: Proceed to next task
- Emphasized immediacy: 'RIGHT NOW - Do not delay'
- Applied to both boulder state and standalone reminder contexts
2026-01-16 13:48:18 +09:00
justsisyphus 5162e4f07b feat(prometheus): strengthen plan-mode constraints with constraint-first architecture
- Move Turn Termination Rules inside <system-reminder> block (from line 488 to ~186)
- Add Final Constraint Reminder at end of prompt (constraint sandwich pattern)
- Preserve all existing interview mode detail and strategies

Applies OpenCode's effective constraint patterns to prevent plan-mode agents
from offering to implement work instead of staying in consultation mode.
2026-01-16 13:36:46 +09:00
justsisyphus e7bb16cdba feat(sisyphus-task): require explicit skills parameter - reject empty array []
- Change skills type from string[] to string[] | null
- Empty array [] now returns error with available skills list
- null is allowed for tasks that genuinely need no skills
- Updated tests to use skills: null instead of skills: []
- Forces explicit decision: either specify skills or justify with null
2026-01-16 13:12:48 +09:00
justsisyphus a1d7acac17 fix: store session agent in chat.message for prometheus-md-only hook
The prometheus-md-only hook was not enforcing file restrictions because
getSessionAgent() returned undefined - setSessionAgent was only called
in message.updated event which doesn't always provide agent info.

- Add setSessionAgent call in chat.message hook when input.agent exists
- Add session state tests for setSessionAgent/getSessionAgent
- Add clearSessionAgent cleanup to prometheus-md-only tests

This ensures prometheus-md-only hook can reliably identify Prometheus
sessions and enforce .sisyphus/*.md write restrictions.
2026-01-16 11:35:37 +09:00
justsisyphus 8c7ec8eb24 fix: clear session agent on /start-work to allow mode transition from Prometheus
When transitioning from Prometheus (Planner) to Sisyphus via /start-work,
the session agent was not being cleared. This caused prometheus-md-only
hook to continue injecting READ-ONLY constraints into sisyphus_task calls.

- Add clearSessionAgent() call when start-work command is detected
- Add TDD test verifying clearSessionAgent is called with sessionID
2026-01-16 11:35:37 +09:00
justsisyphus 9c7854832f refactor: unify system directive prefix for keyword-detector filtering
- Add shared/system-directive.ts with SYSTEM_DIRECTIVE_PREFIX constant
- Unify all system message prefixes to [SYSTEM DIRECTIVE: OH-MY-OPENCODE - ...]
- Add isSystemDirective() filter to keyword-detector to skip system messages
- Update prometheus-md-only tests to use new prefix constants
2026-01-16 11:35:37 +09:00