Classify question type BEFORE synthesizing instead of after. Adds 6
signal-based synthesis formats (AUDIT, COMPARISON, DECISION, ROADMAP,
ARCHITECTURE, RESEARCH) so council output shape matches the question
being asked. CONVERSATIONAL path now suggests a natural follow-up.
- Remove COUNCIL_MEMBER_PROMPT from temp file content since it's already
provided as the council member's system prompt via agent config, saving
~350+ tokens per council member per invocation
- Add startup cleanup for stale athena-council-*.md files older than 30
minutes in .sisyphus/tmp/ to handle cases where process exits before
setTimeout cleanup fires
- Remove redundant intermediate permission object spread in createAthenaAgent
- Fix test style: it() -> test(), add #given/#then prefixes per conventions
Both modes now inject explicit instructions: solo warns against subagent usage, delegation provides concrete call_omo_agent examples. Delegation is now the recommended default to reduce context window pressure on council members.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Extract sendPostCompactionContinuation to dedicated file — council members now resume after compaction instead of silently failing. Refresh lastUpdate before async validation in both idle handler and polling path to prevent stale timeout from racing with completion detection.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
- Add background_output to council-member allowlist (fixes delegation deadlock)
- Replace empty catch with error logging in prepare-council-prompt
- Remove unnecessary type assertion in agent.ts
- Remove dead hasAgentToolRestrictions function
- Fix incorrect test assertions (undefined vs false semantics)
- Add barrel export for athena module
- Add guard function test coverage (5 tests)
- Add parity test for triple-sync restrictions (9 tests)
- Add session.compacted handler in BackgroundManager to prevent premature
task completion after compaction (defer first post-compaction idle)
- Explicitly block TodoWrite/TodoRead for council members in all sync
points (AgentConfig permission + session tools + prompt instructions)
- Add council member prefix check to todo-continuation-enforcer skip list
to prevent infinite continuation loops on completed council members
- Add optional analysis mode (solo/delegation) question to Athena setup:
solo = thorough but heavier, delegation = fast via explore/librarian
- Allow call_omo_agent in council member allow-list for delegation mode
- Update COUNCIL_MEMBER_PROMPT with TodoWrite prohibition and delegation
addendum for when delegation mode is selected
- Update prepare_council_prompt tool with mode parameter
Council members now use an allow-list (read, grep, glob, lsp_*, ast_grep_search)
instead of a deny-list. Prompt file moved from /tmp/ to .sisyphus/tmp/ so no
external_directory permission is needed. COUNCIL_MEMBER_PROMPT is included in
the temp file for self-contained council member instructions.
Athena saves the analysis prompt to a temp file once, then launches each
council member with a short "Read <path> for your instructions" prompt.
This eliminates repeated prompt text across N task calls while preserving
individual clickable task panes in the TUI.
- Regenerate model-fallback snapshots to include athena agent config
- Fix createBuiltinAgents positional arg index for disableOmoEnv
(shifted from index 12 to 13 by new councilConfig param)
- Fix utils.test.ts, config-handler.test.ts arg positions
- Make directory required in SkillLoadOptions, getAllSkills, and async
skill template resolvers to prevent unsafe process.cwd() fallback
- Remove dead skill export and process.cwd() fallback in skill tool
- Replace kimi-for-coding/k2p5 with kimi-for-coding/kimi-k2.5 in
council-members-generator
- Check context.abort in background-wait and background-output polling loops
- Remove legacy kimi-for-coding/k2p5 from athena fallback chain
- Pass ctx.directory from tool-registry to createSkillTool instead of process.cwd()
- Use case-insensitive casing in duplicate name test to verify actual logic
- Align permission type with SDK AgentConfig pattern (as AgentConfig["permission"])
- Move duplicate-name validation from schema to runtime for graceful fallback
- Place skipped members details before 'end your turn' in council guard prompt
The file no longer contains any fallback/handoff logic after the Athena
NLP removal — only generic terminal-event helpers (isTerminalFinishValue,
isTerminalStepFinishPart). Name now matches content.
The fallback scanned Athena's message text for natural-language handoff
phrases ("switching to Atlas", etc.) and synthetically created a pending
switch when the switch_agent tool wasn't called. In practice this path
never fired in real sessions — Athena always correctly called the tool.
Removes ~135 lines of Athena-coupled code, keeping the generic
switch_agent → apply path fully intact.
Fixes from multi-model council audit (7 members, 19 findings, 9 selected):
- Use parseModelString() for cross-provider Anthropic thinking config (#3)
- Update stale AGENTS.md athena directory listing (#4)
- Replace prompt in appendMissingCouncilPrompt instead of appending (#5)
- Extract duplicated session cleanup logic in agent-switch hook (#6)
- Surface skipped council members when >=2 valid members exist (#9)
- Expand fallback handoff regex with negation guards (#11)
- Remove dead council-member agent from agentSources and tests (#12)
- Make runtime council member duplicate check case-insensitive (#14)
- Fix false-positive schema tests by adding required name field (#18)
Use parsed.providerID/modelID in council member description instead of
raw model string (eliminates dead variable). Track skipped members with
reasons and surface them in the missing-council guard prompt so users
see why their council failed to register.
- Add council config guard prompt: when Athena has no valid council members,
inject a STOP instruction telling the user how to configure council members
instead of failing messily with generic agents
- Make council member 'name' field mandatory (was optional with auto-naming)
- Remove humanizeModelId and UPPERCASE_TOKENS — no more fragile auto-naming
- Replace throw on duplicate names with log + skip (graceful degradation)
- Update schema, types, tests (87 pass), and documentation
Skill discovery in the task tool failed to find project-level skills in
OpenCode Desktop because:
1. resolveSkillContent() never passed directory to the skill resolution
functions, causing them to fall back to process.cwd() which differs
from the project directory in Desktop mode.
2. getAllSkills() cache key only included browserProvider, not directory.
A first call with the wrong directory would cache stale results that
all subsequent calls (even with correct directory) would return.
3. The error message used discoverSkills() (discovered only) instead of
getAllSkills() (discovered + builtins), hiding builtin skills from
the Available list.
Changes:
- skill-resolver.ts: accept and pass directory; use getAllSkills for error msg
- tools.ts: pass options.directory to resolveSkillContent
- skill-discovery.ts: include directory in cache key; rename cache variable
- skill/types.ts + tools.ts: add directory to SkillLoadOptions for consistency
Add fallback for CLI run mode when Question tool is denied: auto-select all council members and auto-choose action by question type. Improve synthesis with numbered findings, question type classification (ACTIONABLE/INFORMATIONAL/CONVERSATIONAL), and multi-select finding selection.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Three registration improvements: gate council member registration on Athena enablement, throw on duplicate council member keys instead of silent overwrite, and disable council mode when valid members drop below 2 after model parsing.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Replace deprecated Zod .merge(z.object({...})) with .extend({...}) for AthenaOverrideConfigSchema. Add council-member to AgentOverridesSchema to match OverridableAgentNameSchema.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
processedFallbackMessages was only cleaned up on session.deleted, not session.error. This could leak memory for errored sessions. Mirrors the existing session.deleted cleanup pattern.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
ATHENA_RESTRICTIONS only denied write and edit, missing call_omo_agent that the agent factory already denies. This caused 6 callers of getAgentToolRestrictions() to get incomplete restrictions.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Allow per-member temperature overrides in council config. Adds temperature field to CouncilMemberSchema (0-2 range), CouncilMemberConfig type, and auto-generated JSON schema.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
The hasPendingCouncilMembers guard now matches the 'Council: ' prefix from COUNCIL_MEMBER_KEY_PREFIX instead of the old task.agent === 'council-member' check.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Athena's system prompt now instructs it to launch council members via task(subagent_type=..., run_in_background=true) and collect results with background_wait. Council member prompt enhanced with structured analysis instructions. Deny call_omo_agent for Athena to prevent tool confusion.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Each council member from config is now registered as a named agent (e.g. 'Council: Claude Opus 4.6') via registerCouncilMemberAgents(). Adds humanizeModelId() to derive friendly display names from model IDs. Athena's prompt gets the member list appended so it can call task(subagent_type=...) for each.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Remove the entire custom tool implementation (constants, launcher, session-waiter, tool-helpers, tools, types, and all tests). Council members are now launched via the standard task tool.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Delete the orchestrator that launched council members via the custom athena_council tool. This logic is now replaced by standard task() calls from Athena's prompt.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Athena now uses background_wait (race-style) to collect council results with incremental progress instead of sequential background_output calls or rapid polling. Updated both the system prompt and tool description to guide Athena to the correct waiting pattern.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
New tool that takes multiple task IDs and blocks until ANY one completes (Promise.race pattern). Returns the completed task's result plus a progress summary with remaining IDs. Enables Athena to show incremental council progress without polling.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
- Add both agents to inventory table with model, mode, and fallback info
- Add tool restrictions for Athena (write, edit) and Council-Member
- Add athena/ directory structure to the STRUCTURE section
- Update agent count from 11 to 13
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
ismeth