THE ORCHESTRATOR (#600)

* feat(background-agent): add ConcurrencyManager for model-based limits

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* fix(background-agent): set default concurrency to 5

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

* feat(background-agent): support 0 as unlimited concurrency

Setting concurrency to 0 means unlimited (Infinity).
Works for defaultConcurrency, providerConcurrency, and modelConcurrency.

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

* feat(hooks): use auto flag for session resumption after compaction

- executor.ts: Added `auto: true` to summarize body, removed subsequent prompt_async call
- preemptive-compaction/index.ts: Added `auto: true` to summarize body, removed subsequent promptAsync call
- executor.test.ts: Updated test expectation to include `auto: true`

Instead of sending 'Continue' prompt after compaction, use SessionCompaction's `auto: true` feature which auto-resumes the session.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor(agents): update sisyphus orchestrator

Update Sisyphus agent orchestrator with latest changes.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor(features): update background agent manager

Update background agent manager with latest configuration changes.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor(features): update init-deep template

Update initialization template with latest configuration.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor(hooks): update hook constants and configuration

Update hook constants and configuration across agent-usage-reminder, keyword-detector, and claude-code-hooks.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor(tools): remove background-task tool

Remove background-task tool module completely:
- src/tools/background-task/constants.ts
- src/tools/background-task/index.ts
- src/tools/background-task/tools.ts
- src/tools/background-task/types.ts

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor(tools): update tool exports and main plugin entry

Update tool index exports and main plugin entry point after background-task tool removal.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(auth): update constants to match CLIProxyAPI (50min buffer, 2 endpoints)

- Changed ANTIGRAVITY_TOKEN_REFRESH_BUFFER_MS from 60,000ms (1min) to 3,000,000ms (50min)
- Removed autopush endpoint from ANTIGRAVITY_ENDPOINT_FALLBACKS (now 2 endpoints: daily → prod)
- Added comprehensive test suite with 6 tests covering all updated constants
- Updated comments to reflect CLIProxyAPI parity

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(auth): remove PKCE to match CLIProxyAPI

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

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

* feat(auth): implement port 51121 with OS fallback

Add port fallback logic to OAuth callback server:
- Try port 51121 (ANTIGRAVITY_CALLBACK_PORT) first
- Fallback to OS-assigned port on EADDRINUSE
- Add redirectUri property to CallbackServerHandle
- Return actual bound port in handle.port

Add comprehensive port handling tests (5 new tests):
- Should prefer port 51121
- Should return actual bound port
- Should fallback when port occupied
- Should cleanup and release port on close
- Should provide redirect URI with actual port

All 16 tests passing (11 existing + 5 new).

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* test(auth): add token expiry tests for 50-min buffer

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

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

* feat(agents): add Prometheus system prompt and planner methodology

Add prometheus-prompt.ts with comprehensive planner agent system prompt.
Update plan-prompt.ts with streamlined Prometheus workflow including:
- Context gathering via explore/librarian agents
- Metis integration for AI slop guardrails
- Structured plan output format

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(agents): add Metis plan consultant agent

Add Metis agent for pre-planning analysis that identifies:
- Hidden requirements and implicit constraints
- AI failure points and common mistakes
- Clarifying questions before planning begins

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(agents): add Momus plan reviewer agent

Add Momus agent for rigorous plan review against:
- Clarity and verifiability standards
- Completeness checks
- AI slop detection

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(agents): add Sisyphus-Junior focused executor agent

Add Sisyphus-Junior agent for focused task execution:
- Same discipline as Sisyphus, no delegation capability
- Used for category-based task spawning via sisyphus_task tool

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(agents): add orchestrator-sisyphus agent

Add orchestrator-sisyphus agent for complex workflow orchestration:
- Manages multi-agent workflows
- Coordinates between specialized agents
- Handles start-work command execution

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(skill-loader): add skill-content resolver for agent skills

Add resolveMultipleSkills() for resolving skill content to prepend to agent prompts.
Includes test coverage for resolution logic.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(agents): add category and skills support to buildAgent

Extend buildAgent() to support:
- category: inherit model/temperature from DEFAULT_CATEGORIES
- skills: prepend resolved skill content to agent prompt

Includes comprehensive test coverage for new functionality.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(agents): register new agents in index and types

- Export Metis, Momus, orchestrator-sisyphus in builtinAgents
- Add new agent names to BuiltinAgentName type
- Update AGENTS.md documentation with new agents

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(features): add boulder-state persistence

Add boulder-state feature for persisting workflow state:
- storage.ts: File I/O operations for state persistence
- types.ts: State interfaces
- Includes test coverage

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(skills): add frontend-ui-ux builtin skill

Add frontend-ui-ux skill for designer-turned-developer UI work:
- SKILL.md with comprehensive design principles
- skills.ts updated with skill template

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(tools): add sisyphus_task tool for category-based delegation

Add sisyphus_task tool supporting:
- Category-based task delegation (visual, business-logic, etc.)
- Direct agent targeting
- Background execution with resume capability
- DEFAULT_CATEGORIES configuration

Includes test coverage.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(background-agent): add resume capability and model field

- Add resume() method for continuing existing agent sessions
- Add model field to BackgroundTask and LaunchInput types
- Update launch() to pass model to session.prompt()
- Comprehensive test coverage for resume functionality

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(hooks): add task-resume-info hook

Add hook for injecting task resume information into tool outputs.
Enables seamless continuation of background agent sessions.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(hooks): add prometheus-md-only write restriction hook

Add hook that restricts Prometheus planner to writing only .md files
in the .sisyphus/ directory. Prevents planners from implementing.
Includes test coverage.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(hooks): add start-work hook for Sisyphus workflow

Add hook for detecting /start-work command and triggering
orchestrator-sisyphus agent for plan execution.
Includes test coverage.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(hooks): add sisyphus-orchestrator hook

Add hook for orchestrating Sisyphus agent workflows:
- Coordinates task execution between agents
- Manages workflow state persistence
- Handles agent handoffs

Includes comprehensive test coverage.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(hooks): export new hooks in index

Export new hooks:
- createPrometheusMdOnlyHook
- createTaskResumeInfoHook
- createStartWorkHook
- createSisyphusOrchestratorHook

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(todo-enforcer): add skipAgents option and improve permission check

- Add skipAgents option to skip continuation for specified agents
- Default skip: Prometheus (Planner)
- Improve tool permission check to handle 'allow'/'deny' string values
- Add agent name detection from session messages

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(config): add categories, new agents and hooks to schema

Update Zod schema with:
- CategoryConfigSchema for task delegation categories
- CategoriesConfigSchema for user category overrides
- New agents: Metis (Plan Consultant)
- New hooks: prometheus-md-only, start-work, sisyphus-orchestrator
- New commands: start-work
- Agent category and skills fields

Includes schema test coverage.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(commands): add start-work command

Add /start-work command for executing Prometheus plans:
- start-work.ts: Command template for orchestrator-sisyphus
- commands.ts: Register command with agent binding
- types.ts: Add command name to type union

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor(migration): add backup creation and category migration

- Create timestamped backup before migration writes
- Add migrateAgentConfigToCategory() for model→category migration
- Add shouldDeleteAgentConfig() for cleanup when matching defaults
- Add Prometheus and Metis to agent name map
- Comprehensive test coverage for new functionality

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(config-handler): add Sisyphus-Junior and orchestrator support

- Add Sisyphus-Junior agent creation
- Add orchestrator-sisyphus tool restrictions
- Rename Planner-Sisyphus to Prometheus (Planner)
- Use PROMETHEUS_SYSTEM_PROMPT and PROMETHEUS_PERMISSION

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(cli): add categories config for Antigravity auth

Add category model overrides for Gemini Antigravity authentication:
- visual: gemini-3-pro-high
- artistry: gemini-3-pro-high
- writing: gemini-3-pro-high

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor(sisyphus): update to use sisyphus_task and add resume docs

- Update example code from background_task to sisyphus_task
- Add 'Resume Previous Agent' documentation section
- Remove model name from Oracle section heading
- Disable call_omo_agent tool for Sisyphus

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor: update tool references from background_task to sisyphus_task

Update all references across:
- agent-usage-reminder: Update AGENT_TOOLS and REMINDER_MESSAGE
- claude-code-hooks: Update comment
- call-omo-agent: Update constants and tool restrictions
- init-deep template: Update example code
- tools/index.ts: Export sisyphus_task, remove background_task

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(hook-message-injector): add ToolPermission type support

Add ToolPermission type union: boolean | 'allow' | 'deny' | 'ask'
Update StoredMessage and related interfaces for new permission format.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(main): wire up new tools, hooks and agents

Wire up in main plugin entry:
- Import and create sisyphus_task tool
- Import and wire taskResumeInfo, startWork, sisyphusOrchestrator hooks
- Update tool restrictions from background_task to sisyphus_task
- Pass userCategories to createSisyphusTask

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* docs: update documentation for Prometheus and new features

Update documentation across all language versions:
- Rename Planner-Sisyphus to Prometheus (Planner)
- Add Metis (Plan Consultant) agent documentation
- Add Categories section with usage examples
- Add sisyphus_task tool documentation
- Update AGENTS.md with new structure and complexity hotspots
- Update src/tools/AGENTS.md with sisyphus_task category

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* build: regenerate schema.json with new types

Update JSON schema with:
- New agents: Prometheus (Planner), Metis (Plan Consultant)
- New hooks: prometheus-md-only, start-work, sisyphus-orchestrator
- New commands: start-work
- New skills: frontend-ui-ux
- CategoryConfigSchema for task delegation
- Agent category and skills fields

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* skill

* feat: add toast notifications for task execution

- Display toast when background task starts in BackgroundManager
- Display toast when sisyphus_task sync task starts
- Wire up prometheus-md-only hook initialization in main plugin

This provides user feedback in OpenCode TUI where task TUI is not visible.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(hooks): add read-only warning injection for Prometheus task delegation

When Prometheus (Planner) spawns subagents via task tools (sisyphus_task, task, call_omo_agent), a system directive is injected into the prompt to ensure subagents understand they are in a planning consultation context and must NOT modify files.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(hooks): add mandatory hands-on verification enforcement for orchestrated tasks

- sisyphus-orchestrator: Add verification reminder with tool matrix (playwright/interactive_bash/curl)

- start-work: Inject detailed verification workflow with deliverable-specific guidance

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

* docs(agents): clarify oracle and metis agent descriptions emphasizing read-only consultation roles

- Oracle: high-IQ reasoning specialist for debugging and architecture (read-only)
- Metis: updated description to align with oracle's consultation-only model
- Updated AGENTS.md with clarified agent responsibilities

* docs(orchestrator): emphasize oracle as read-only consultation agent

- Updated orchestrator-sisyphus agent descriptions
- Updated sisyphus-prompt-builder to highlight oracle's read-only consultation role
- Clarified that oracle provides high-IQ reasoning without write operations

* docs(refactor,root): update oracle consultation model in feature templates and root docs

- Updated refactor command template to emphasize oracle's read-only role
- Updated root AGENTS.md with oracle agent description emphasizing high-IQ debugging and architecture consultation
- Clarified oracle as non-write agent for design and debugging support

* feat(features): add TaskToastManager for consolidated task notifications

- Create task-toast-manager feature with singleton pattern

- Show running task list (newest first) when new task starts

- Track queued tasks status from ConcurrencyManager

- Integrate with BackgroundManager and sisyphus-task tool

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

* feat(hooks): add resume session_id to verification reminders for orchestrator subagent work

When subagent work fails verification, show exact sisyphus_task(resume="...")
command with session_id for immediate retry. Consolidates verification workflow
across boulder and standalone modes.

* refactor(hooks): remove duplicate verification enforcement from start-work hook

Verification reminders are now centralized in sisyphus-orchestrator hook,
eliminating redundant code in start-work. The orchestrator hook handles all
verification messaging across both boulder and standalone modes.

* test(hooks): update prometheus-md-only test assertions and formatting

Updated test structure and assertions to match current output format.
Improved test clarity while maintaining complete coverage of markdown
validation and write restriction behavior.

* orchestrator

* feat(skills): add git-master skill for atomic commits and history management

- Add comprehensive git-master skill for commit, rebase, and history operations
- Implements atomic commit strategy with multi-file splitting rules
- Includes style detection, branch analysis, and history search capabilities
- Provides three modes: COMMIT, REBASE, HISTORY_SEARCH

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* docs(agents): add pre-delegation planning section to Sisyphus prompt

- Add SISYPHUS_PRE_DELEGATION_PLANNING section with mandatory declaration rules
- Implements 3-step decision tree: Identify → Select → Declare
- Forces explicit category/agent/skill declaration before every sisyphus_task call
- Includes mandatory 4-part format: Category/Agent, Reason, Skills, Expected Outcome
- Provides examples (CORRECT vs WRONG) and enforcement rules
- Follows prompt engineering best practices: Clear, CoT, Structured, Examples

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor(tools): rename agent parameter to subagent_type in sisyphus_task

- Update parameter name from 'agent' to 'subagent_type' for consistency with call_omo_agent
- Update all references and error messages
- Remove deprecated 'agent' field from SisyphusTaskArgs interface
- Update git-master skill documentation to reflect parameter name change

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* feat(agents): change orchestrator-sisyphus default model to claude-sonnet-4-5

- Update orchestrator-sisyphus model from opus-4-5 to sonnet-4-5 for better cost efficiency
- Keep Prometheus using opus-4-5 for planning tasks

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* refactor(config): make Prometheus model independent from plan agent config

- Prometheus no longer inherits model from plan agent configuration
- Fallback chain: session default model -> claude-opus-4-5
- Removes coupling between Prometheus and legacy plan agent settings

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

* fix(momus): allow system directives in input validation

System directives (XML tags like <system-reminder>) are automatically
injected and should be ignored during input validation. Only reject
when there's actual user text besides the file path.

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

* feat(prometheus): enhance high accuracy mode with mandatory Momus loop

When user requests high accuracy:
- Momus review loop is now mandatory until 'OKAY'
- No excuses allowed - must fix ALL issues
- No maximum retry limit - keep looping until approved
- Added clear explanation of what 'OKAY' means

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

* feat(prometheus): enhance reference section with detailed guidance

References now include:
- Pattern references (existing code to follow)
- API/Type references (contracts to implement)
- Test references (testing patterns)
- Documentation references (specs and requirements)
- External references (libraries and frameworks)
- Explanation of WHY each reference matters

The executor has no interview context - references are their only guide.

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

* feat(git-master): add configurable commit footer and co-author options

Add git_master config with commit_footer and include_co_authored_by flags.
Users can disable Sisyphus attribution in commits via oh-my-opencode.json.

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

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

* feat(hooks): add single-task directive and system-reminder tags to orchestrator

Inject SINGLE_TASK_DIRECTIVE when orchestrator calls sisyphus_task to enforce
atomic task delegation. Wrap verification reminders in <system-reminder> tags
for better LLM attention.

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

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

* refactor: use ContextCollector for hook injection and remove unused background tools

Split changes:
- Replace injectHookMessage with ContextCollector.register() pattern for improved hook content injection
- Remove unused background task tools infrastructure (createBackgroundOutput, createBackgroundCancel)

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

* chore(context-injector): add debug logging for context injection tracing

Add DEBUG log statements to trace context injection flow:
- Log message transform hook invocations
- Log sessionID extraction from message info
- Log hasPending checks for context collector
- Log hook content registration to contextCollector

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

* fix(context-injector): prepend to user message instead of separate synthetic message

- Change from creating separate synthetic user message to prepending context
  directly to last user message's text part
- Separate synthetic messages were ignored by model (treated as previous turn)
- Prepending to clone ensures: UI shows original, model receives prepended content
- Update tests to reflect new behavior

* feat(prometheus): enforce mandatory todo registration on plan generation trigger

* fix(sisyphus-task): add proper error handling for sync mode and implement BackgroundManager.resume()

- Add try-catch for session.prompt() in sync mode with detailed error messages
- Sort assistant messages by time to get the most recent response
- Add 'No assistant response found' error handling
- Implement BackgroundManager.resume() method for task resumption
- Fix ConcurrencyManager type mismatch (model → concurrencyKey)

* docs(sisyphus-task): clarify resume usage with session_id and add when-to-use guidance

- Fix terminology: 'Task ID' → 'Session ID' in resume parameter docs
- Add clear 'WHEN TO USE resume' section with concrete scenarios
- Add example usage pattern in Sisyphus agent prompt
- Emphasize token savings and context preservation benefits

* fix(agents): block task/sisyphus_task/call_omo_agent from explore and librarian

Exploration agents should not spawn other agents - they are leaf nodes
in the agent hierarchy for codebase search only.

* refactor(oracle): change default model from GPT-5.2 to Claude Opus 4.5

* feat(oracle): change default model to claude-opus-4-5

* fix(sisyphus-orchestrator): check boulder session_ids before filtering sessions

Bug: continuation was not triggered even when boulder.json existed with
session_ids because the session filter ran BEFORE reading boulder state.

Fix: Read boulder state first, then include boulder sessions in the
allowed sessions for continuation.

* feat(task-toast): display skills and concurrency info in toast

- Add skills field to TrackedTask and LaunchInput types
- Show skills in task list message as [skill1, skill2]
- Add concurrency slot info [running/limit] in Running header
- Pass skills from sisyphus_task to toast manager (sync & background)
- Add unit tests for new toast features

* refactor(categories): rename high-iq to ultrabrain

* feat(sisyphus-task): add skillContent support to background agent launching

- Add optional skillContent field to LaunchInput type
- Implement buildSystemContent utility to combine skill and category prompts
- Update BackgroundManager to pass skillContent as system parameter
- Add comprehensive tests for skillContent optionality and buildSystemContent logic

🤖 Generated with assistance of oh-my-opencode

* Revert "refactor(tools): remove background-task tool"

This reverts commit 6dbc4c095badd400e024510554a42a0dc018ae42.

* refactor(sisyphus-task): rename background to run_in_background

* fix(oracle): use gpt-5.2 as default model

* test(sisyphus-task): add resume with background parameter tests

* feat(start-work): auto-select single incomplete plan and use system-reminder format

- Auto-select when only one incomplete plan exists among multiple
- Wrap multiple plans message in <system-reminder> tag
- Change prompt to 'ask user' style for agent guidance
- Add 'All Plans Complete' state handling

* feat(sisyphus-task): make skills parameter required

- Add validation for skills parameter (must be provided, use [] if empty)
- Update schema to remove .optional()
- Update type definition to make skills non-optional
- Fix existing tests to include skills parameter

* fix: prevent session model change when sending notifications

- background-agent: use only parentModel, remove prevMessage fallback
- todo-continuation: don't pass model to preserve session's lastModel
- Remove unused imports (findNearestMessageWithFields, fs, path)

Root cause: session.prompt with model param changes session's lastModel

* fix(sisyphus-orchestrator): register handler in event loop for boulder continuation

* fix(sisyphus_task): use promptAsync for sync mode to preserve main session

- session.prompt() changes the active session, causing UI model switch
- Switch to promptAsync + polling to avoid main session state change
- Matches background-agent pattern for consistency

* fix(sisyphus-orchestrator): only trigger boulder continuation for orchestrator-sisyphus agent

* feat(background-agent): add parentAgent tracking to preserve agent context in background tasks

- Add parentAgent field to BackgroundTask, LaunchInput, and ResumeInput interfaces
- Pass parentAgent through background task manager to preserve agent identity
- Update sisyphus-orchestrator to set orchestrator-sisyphus agent context
- Add session tracking for background agents to prevent context loss
- Propagate agent context in background-task and sisyphus-task tools

This ensures background/subagent spawned tasks maintain proper agent context for notifications and continuity.

🤖 Generated with assistance of oh-my-opencode

* fix(antigravity): sync plugin.ts with PKCE-removed oauth.ts API

Remove decodeState import and update OAuth flow to use simple state
string comparison for CSRF protection instead of PKCE verifier.
Update exchangeCode calls to match new signature (code, redirectUri,
clientId, clientSecret).

* fix(hook-message-injector): preserve agent info with two-pass message lookup

findNearestMessageWithFields now has a fallback pass that returns
messages with ANY useful field (agent OR model) instead of requiring
ALL fields. This prevents parentAgent from being lost when stored
messages don't have complete model info.

* fix(sisyphus-task): use SDK session.messages API for parent agent lookup

Background task notifications were showing 'build' agent instead of the
actual parent agent (e.g., 'Sisyphus'). The hook-injected message storage
only contains limited info; the actual agent name is in the SDK session.

Changes:
- Add getParentAgentFromSdk() to query SDK messages API
- Look up agent from SDK first, fallback to hook-injected messages
- Ensures background tasks correctly preserve parent agent context

* fix(sisyphus-task): use ctx.agent directly for parentAgent

The tool context already provides the agent name via ctx.agent.
The previous SDK session.messages lookup was completely wrong -
SDK messages don't store agent info per message.

Removes useless getParentAgentFromSdk function.

* feat(prometheus-md-only): allow .md files anywhere, only block code files

Prometheus (Planner) can now write .md files anywhere, not just .sisyphus/.
Still blocks non-.md files (code) to enforce read-only planning for code.

This allows planners to write commentary and analysis in markdown format.

* Revert "feat(prometheus-md-only): allow .md files anywhere, only block code files"

This reverts commit c600111597591e1862696ee0b92051e587aa1a6b.

* fix(momus): accept bracket-style system directives in input validation

Momus was rejecting inputs with bracket-style directives like [analyze-mode]
and [SYSTEM DIRECTIVE...] because it only recognized XML-style tags.

Now accepts:
- XML tags: <system-reminder>, <context>, etc.
- Bracket blocks: [analyze-mode], [SYSTEM DIRECTIVE...], [SYSTEM REMINDER...], etc.

* fix(sisyphus-orchestrator): inject delegation warning before Write/Edit outside .sisyphus

- Add ORCHESTRATOR_DELEGATION_REQUIRED strong warning in tool.execute.before
- Fix tool.execute.after filePath detection using pendingFilePaths Map
- before stores filePath by callID, after retrieves and deletes it
- Fixes bug where output.metadata.filePath was undefined

* docs: add orchestration, category-skill, and CLI guides

* fix(cli): correct category names in Antigravity migration (visual → visual-engineering)

* fix(sisyphus-task): prevent infinite polling when session removed from status

* fix(tests): update outdated test expectations

- constants.test.ts: Update endpoint count (2→3) and token buffer (50min→60sec)
- token.test.ts: Update expiry tests to use 60-second buffer
- sisyphus-orchestrator: Add fallback to output.metadata.filePath when callID missing

---------

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

docs/orchestration-guide.md

@@ -0,0 +1,131 @@
+# Oh-My-OpenCode Orchestration Guide
+
+This document provides a comprehensive guide to the orchestration system that implements Oh-My-OpenCode's core philosophy: **"Separation of Planning and Execution"**.
+
+## 1. Overview
+
+Traditional AI agents often mix planning and execution, leading to context pollution, goal drift, and AI slop (low-quality code).
+
+Oh-My-OpenCode solves this by clearly separating two roles:
+
+1. **Prometheus (Planner)**: A pure strategist who never writes code. Establishes perfect plans through interviews and analysis.
+2. **Sisyphus (Executor)**: An orchestrator who executes plans. Delegates work to specialized agents and never stops until completion.
+
+---
+
+## 2. Overall Architecture
+
+```mermaid
+graph TD
+    User[User Request] --> Prometheus
+    
+    subgraph Planning Phase
+        Prometheus[Prometheus<br>Planner] --> Metis[Metis<br>Consultant]
+        Metis --> Prometheus
+        Prometheus --> Momus[Momus<br>Reviewer]
+        Momus --> Prometheus
+        Prometheus --> PlanFile[/.sisyphus/plans/*.md]
+    end
+    
+    PlanFile --> StartWork[/start-work]
+    StartWork --> BoulderState[boulder.json]
+    
+    subgraph Execution Phase
+        BoulderState --> Sisyphus[Sisyphus<br>Orchestrator]
+        Sisyphus --> Oracle[Oracle]
+        Sisyphus --> Frontend[Frontend<br>Engineer]
+        Sisyphus --> Explore[Explore]
+    end
+```
+
+---
+
+## 3. Key Components
+
+### 🔮 Prometheus (The Planner)
+- **Model**: `anthropic/claude-opus-4-5`
+- **Role**: Strategic planning, requirements interviews, work plan creation
+- **Constraint**: **READ-ONLY**. Can only create/modify markdown files within `.sisyphus/` directory.
+- **Characteristic**: Never writes code directly, focuses solely on "how to do it".
+
+### 🦉 Metis (The Consultant)
+- **Role**: Pre-analysis and gap detection
+- **Function**: Identifies hidden user intent, prevents AI over-engineering, eliminates ambiguity.
+- **Workflow**: Metis consultation is mandatory before plan creation.
+
+### ⚖️ Momus (The Reviewer)
+- **Role**: High-precision plan validation (High Accuracy Mode)
+- **Function**: Rejects and demands revisions until the plan is perfect.
+- **Trigger**: Activated when user requests "high accuracy".
+
+### 🪨 Sisyphus (The Orchestrator)
+- **Model**: `anthropic/claude-opus-4-5` (Extended Thinking 32k)
+- **Role**: Execution and delegation
+- **Characteristic**: Doesn't do everything directly, actively delegates to specialized agents (Frontend, Librarian, etc.).
+
+---
+
+## 4. Workflow
+
+### Phase 1: Interview and Planning (Interview Mode)
+Prometheus starts in **interview mode** by default. Instead of immediately creating a plan, it collects sufficient context.
+
+1. **Intent Identification**: Classifies whether the user's request is Refactoring or New Feature.
+2. **Context Collection**: Investigates codebase and external documentation through `explore` and `librarian` agents.
+3. **Draft Creation**: Continuously records discussion content in `.sisyphus/drafts/`.
+
+### Phase 2: Plan Generation
+When the user requests "Make it a plan", plan generation begins.
+
+1. **Metis Consultation**: Confirms any missed requirements or risk factors.
+2. **Plan Creation**: Writes a single plan in `.sisyphus/plans/{name}.md` file.
+3. **Handoff**: Once plan creation is complete, guides user to use `/start-work` command.
+
+### Phase 3: Execution
+When the user enters `/start-work`, the execution phase begins.
+
+1. **State Management**: Creates `boulder.json` file to track current plan and session ID.
+2. **Task Execution**: Sisyphus reads the plan and processes TODOs one by one.
+3. **Delegation**: UI work is delegated to Frontend agent, complex logic to Oracle.
+4. **Continuity**: Even if the session is interrupted, work continues in the next session through `boulder.json`.
+
+---
+
+## 5. Commands and Usage
+
+### `/plan [request]`
+Invokes Prometheus to start a planning session.
+- Example: `/plan "I want to refactor the authentication system to NextAuth"`
+
+### `/start-work`
+Executes the generated plan.
+- Function: Finds plan in `.sisyphus/plans/` and enters execution mode.
+- If there's interrupted work, automatically resumes from where it left off.
+
+---
+
+## 6. Configuration Guide
+
+You can control related features in `oh-my-opencode.json`.
+
+```jsonc
+{
+  "sisyphus_agent": {
+    "disabled": false,           // Enable Sisyphus orchestration (default: false)
+    "planner_enabled": true,     // Enable Prometheus (default: true)
+    "replace_plan": true         // Replace default plan agent with Prometheus (default: true)
+  },
+  
+  // Hook settings (add to disable)
+  "disabled_hooks": [
+    // "start-work",             // Disable execution trigger
+    // "prometheus-md-only"      // Remove Prometheus write restrictions (not recommended)
+  ]
+}
+```
+
+## 7. Best Practices
+
+1. **Don't Rush**: Invest sufficient time in the interview with Prometheus. The more perfect the plan, the faster the execution.
+2. **Single Plan Principle**: No matter how large the task, contain all TODOs in one plan file (`.md`). This prevents context fragmentation.
+3. **Active Delegation**: During execution, delegate to specialized agents via `sisyphus_task` rather than modifying code directly.