Commit Graph

1254 Commits

Author SHA1 Message Date
ismeth 62cf707502 fix: resolve 11 council-audited violations across athena subsystem
- Add switch_agent to athena-junior deny list (P1 defense-in-depth)
- Add terminal status check to waitForSessionIds polling loop
- Add athena-junior to OverridableAgentNameSchema and AgentOverridesSchema
- Add explicit retry workflow instructions to non-interactive prompt Step 9
- Fix JSON schema generation to exclude defaulted fields from required arrays
- Fix docs example for non_interactive_member_list (remove Council: prefix)
- Use segment-aware regex in path-policy.ts to block fake.sisyphus/ paths
- Add defensive path resolution and contract validation for prompt_file
- Add explicit .optional() to AthenaOverrideConfigSchema fields for clarity
- Fix traversal check precision for .. prefixed directory names
2026-04-15 16:48:49 +09:00
ismeth 6db83b937f fix: resolve 7 council-validated PR violations
- Fix misleading background_wait instructions to show loop pattern with
  remaining_task_ids (race semantics, not block-all)
- Fix wrong Gemini model string: gemini-3-pro-preview → gemini-3-pro
- Add getMainSessionID() fallback when input.sessionID is undefined
- Narrow .gitignore packages/ to only ignore built binaries
- Fix contradictory config doc: non_interactive_members 'all' → 'custom'
- Add athena-junior to keyword-detector exclusion check
- Add .trim() before .toUpperCase() in resolveCouncilIntent
- Update snapshots for model string change
2026-04-15 16:48:48 +09:00
ismeth 34faa7c67c refactor(switch-agent): replace deferred hook system with direct session.create + promptAsync
Adopt the opencode-handoff pattern: switch_agent now creates a new session
and sends the context via promptAsync immediately in the tool's execute
function, then navigates the TUI to the new session.

Removes ~1700 LOC of complexity: persistent state management, event-based
hook monitoring, retry logic, session idle waiting, apply verification,
and terminal detection — all replaced by 3 SDK calls.

Deleted: src/features/agent-switch/ (14 files), src/hooks/agent-switch/ (4 files)
Updated: Athena prompt to announce handoff before calling switch_agent
2026-04-15 16:48:01 +09:00
ismeth 75f07b4d8e fix(agent-switch): add missing session.create mock to hook tests 2026-04-15 16:47:57 +09:00
ismeth da446979f6 test(athena): add tests for intent addendums, hook enforcement, restriction parity, and council prompt regression 2026-04-15 16:43:48 +09:00
ismeth 6b450b42db feat(athena): add intent parameter to prepare_council_prompt + wire hook into plugin system + update exports 2026-04-15 16:43:17 +09:00
ismeth 386645ea6b refactor(athena): strip audit bias from council member prompt + add intent addendums + write boundary hook + relax restrictions 2026-04-15 16:43:17 +09:00
ismeth fb543f88d5 fix(athena): harden council members — compaction recovery, block TodoWrite, analysis mode
- 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
2026-04-15 16:41:02 +09:00
ismeth 0205601b6c rename: fallback-handoff.ts → terminal-detection.ts
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.
2026-04-15 16:34:01 +09:00
ismeth a6a9b83531 refactor(agent-switch): remove Athena-specific NLP fallback from hook
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.
2026-04-15 16:34:01 +09:00
ismeth 9f541ed3ee fix(athena): address 9 council-audit findings — dead code, bugs, and hardening
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)
2026-04-15 16:34:01 +09:00
ismeth 0679167cc7 fix(agent-switch): correct off-by-one in fallback message cap 2026-04-15 16:33:52 +09:00
ismeth f068494fb9 fix(athena): update stale test snapshots and keyword-detector log assertions 2026-04-15 16:32:26 +09:00
ismeth e59857a827 fix(agent-switch): clear fallback markers on session.error
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>
2026-04-15 16:32:16 +09:00
ismeth 5769a48a94 fix(athena): update council member guards for new agent key format
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>
2026-04-15 16:31:01 +09:00
ismeth d8006b0782 fix(athena): reduce keyword-detector log noise for Athena sessions
Only log keyword skipping when there are actual keywords to skip, not on every Athena message.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-15 16:22:28 +09:00
ismeth c4de47245e fix(athena): enable retry and bound growth for agent-switch fallback markers
Delete marker from processedFallbackMessages on failure so message can be retried. Add MAX_PROCESSED_FALLBACK_MARKERS=500 with eviction to prevent unbounded Set growth.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-15 16:22:28 +09:00
ismeth a1645ad6ee fix(prompts): normalize agent names for continuation injections 2026-04-15 16:22:28 +09:00
ismeth 8de10c1f2b fix(agent-switch): make handoff durable and sync CLI TUI selection 2026-04-15 16:18:19 +09:00
ismeth 72f4669c7f fix(athena): use getAgentConfigKey for keyword-detector Athena exclusion
The previous check used currentAgent?.toLowerCase() === 'athena' which failed

after display name remapping stored the agent as 'Athena (Council)' in session

state. Now uses getAgentConfigKey() to resolve display names back to config keys,

matching the established pattern used by other hooks (atlas, todo-continuation, etc.).

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-15 15:56:56 +09:00
ismeth 84185490f9 refactor(athena): rename session_handoff to switch_agent to avoid confusion with /handoff command
Rename across all layers to eliminate naming ambiguity:
- Tool: session_handoff → switch_agent
- Hook: agent-handoff → agent-switch
- Feature: agent-handoff/ → agent-switch/
- Types: SessionHandoffArgs → SwitchAgentArgs, PendingHandoff → PendingSwitch
- Functions: setPendingHandoff → setPendingSwitch, consumePendingHandoff → consumePendingSwitch

/handoff = inter-session context summary (existing command)
switch_agent = intra-session active agent change (our new tool)
2026-04-15 15:47:13 +09:00
ismeth 7db0f110ee feat(athena): add session handoff with Question tool for Atlas/Prometheus routing
After Athena synthesizes council findings, presents user with Question tool
TUI to choose: Atlas (fix now), Prometheus (create plan), or no action.
On selection, session_handoff tool stores intent + calls updateSessionAgent(),
then agent-handoff hook fires on session.idle to switch the main session's
active agent via promptAsync with synthesis context.
2026-04-15 15:45:46 +09:00
ismeth cbdff96f66 fix(athena): force council-first behavior — unconditional prompt + skip keyword injection
The old prompt said 'when requiring multi-model analysis' which let Athena
decide to skip the council and do direct analysis herself. Combined with
keyword-detector injecting [search-mode] telling her to 'launch explore
agents and use Grep directly', Athena never called athena_council.

Two fixes:
1. System prompt now unconditionally requires athena_council as FIRST action
   - Explicitly prohibits Read/Grep/Glob/LSP/call_omo_agent
   - Identity is 'orchestrator, not analyst'
2. keyword-detector skips ALL injections for Athena agent
   - search/analyze/ultrawork modes conflict with council orchestration
   - Same pattern as isPlannerAgent() skip for Prometheus
2026-04-15 15:42:15 +09:00
YeonGyu-Kim 1d8f8a03ca Merge pull request #3437 from code-yeongyu/fix/bug-batch-2
fix: Git Bash shell detection, legacy agent name resolution, backup spam
2026-04-15 10:53:46 +09:00
YeonGyu-Kim 62c60ae9d8 fix: numeric skill names, ultrawork missing run_in_background, ZWSP agent lookups
- #3354: Coerce data.name to String in loadSkillFromPath/loadSkillFromPathAsync
  to prevent crash when YAML parses numeric skill names (e.g., name: 12306)

- #3416: Add required run_in_background parameter to all task() examples in
  ultrawork prompts (default, gpt, gemini, planner) to match tool schema

- #3379/#3417/#3418/#3337/#3335: Strip ZWSP (U+200B) before agent name
  comparisons in agent-tool-restrictions, sync-prompt-sender, tool-execute-after,
  tool-execute-before, oracle-verification-detector, call-omo-agent,
  recovery-prompt-config, and agent-variant to prevent ZWSP-prefixed display
  names from breaking exact-match lookups
2026-04-15 10:46:41 +09:00
YeonGyu-Kim 0dab3116b7 fix: resolve 3 bugs (#3366, #3272, #3222)
- shell-env: detect Git Bash via MSYSTEM env var when SHELL is unset (#3366)
  On some Git Bash installations SHELL is not set but MSYSTEM (MINGW64/MSYS)
  is always present. Check MSYSTEM before PSModulePath to avoid emitting
  PowerShell syntax in bash shells.

- session-state: resolve legacy agent names in resolveRegisteredAgentName (#3272)
  Historical sessions stored agent names like 'Sisyphus (Ultraworker)' which
  don't match the current registered format. Fall back to getAgentConfigKey
  for legacy/parenthesized name resolution before returning the raw name.

- config-migration: skip backup when file content is unchanged (#3222)
  Compare serialized config with existing file content before creating a
  timestamped .bak file. Only create backup when the on-disk content
  actually differs from the migrated content.
2026-04-15 10:43:44 +09:00
YeonGyu-Kim 051ab840d6 Merge pull request #3348 from code-yeongyu/refactor/ulw-repo-cleanup-20260411
refactor: simplify nullish guards and remove dead no-op paths
2026-04-12 18:04:43 +09:00
YeonGyu-Kim c5c5bc36bc fix(delegate-task): consume fallback chain on sendSyncPrompt failure (#2691)
setSessionFallbackChain stored the fallback chain but the sync path
never consumed it when sendSyncPrompt returned an error. Added a
retry loop that iterates getNextFallback() until the prompt succeeds
or the chain is exhausted, preserving the finally-block cleanup.

🤖 Generated with OhMyOpenCode assistance
https://github.com/code-yeongyu/oh-my-opencode
2026-04-12 02:30:32 +09:00
YeonGyu-Kim 796a646c63 fix(non-interactive-env): use detectShellType instead of hardcoded win32 check (#3310, #3338)
Hardcoded platform check forced PowerShell env syntax on Windows
regardless of the actual shell. Replaced with detectShellType() so
Git Bash, WSL, and similar environments use unix prefixes while
native PowerShell continues to get powershell prefixes.

🤖 Generated with OhMyOpenCode assistance
https://github.com/code-yeongyu/oh-my-opencode
2026-04-12 02:29:28 +09:00
YeonGyu-Kim 2d8b4a9d53 fix(anthropic-effort): skip effort injection for github-copilot provider (#3270)
github-copilot routes Claude models but rejects the Anthropic effort
parameter. Added an explicit guard so effort is no longer injected
when the provider ID is github-copilot, while preserving native
Anthropic provider support.

🤖 Generated with OhMyOpenCode assistance
https://github.com/code-yeongyu/oh-my-opencode
2026-04-12 02:29:18 +09:00
YeonGyu-Kim 7e96af5f28 fix(atlas): exclude node_modules from verification git diff --stat (#3215)
Atlas verification reminders instructed 'git diff --stat' which
included node_modules noise in the output. Added pathspec exclude
to both VERIFICATION_REMINDER and VERIFICATION_REMINDER_GEMINI
templates.

🤖 Generated with OhMyOpenCode assistance
https://github.com/code-yeongyu/oh-my-opencode
2026-04-12 02:29:08 +09:00
YeonGyu-Kim d7b4bec58b fix(hooks,tools): replace /plan example with prometheus delegation and rename code-review example to review-work (#2633, #3285, #2873)
- context-info-builder referenced a non-existent /plan command;
  now directs users to the Prometheus agent for planning
- skill tool description example referenced 'code-review' which
  does not exist; changed to 'review-work' (actual built-in skill)
- skill tool execute path now surfaces the missing host permission
  gap so callers understand OpenCode plugin context limits

🤖 Generated with OhMyOpenCode assistance
https://github.com/code-yeongyu/oh-my-opencode
2026-04-12 02:28:58 +09:00
YeonGyu-Kim 6713b30cc1 refactor(hooks): drop no-op directory injector callbacks
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-12 00:07:10 +09:00
YeonGyu-Kim 0c5cd3a1c4 chore(agents): update all AGENTS.md generation dates to 2026-04-11
🤖 Generated with OhMyOpenCode assistance
2026-04-11 22:33:22 +09:00
YeonGyu-Kim 522f8aab6c fix: move Haiku check before variant check for reliability
Addresses cubic-dev-ai review feedback. The Haiku early-return now
runs immediately after model validation, ensuring it's always reached
regardless of any upstream variant normalization.
2026-04-11 13:44:35 +09:00
YeonGyu-Kim 7c154c6659 fix(anthropic-effort): skip effort injection for Haiku models (#3308)
Haiku models do not support the effort parameter and return API errors
when it is passed. The hook now explicitly checks for Haiku model
patterns and skips effort injection, preventing silent title generation
failures.

Added EFFORT_UNSUPPORTED_PATTERN and isEffortUnsupportedModel() to
detect and skip Haiku models.

Fixes #3308
2026-04-11 13:06:24 +09:00
YeonGyu-Kim e54f747916 fix(tests): replace as any with typed PluginInput mocks 2026-04-10 18:47:17 +09:00
YeonGyu-Kim ca9b5fde40 test(hooks): update claude-code, comment-checker, and rules-injector tests
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-10 15:53:33 +09:00
YeonGyu-Kim 8a4eacfd24 test(hooks): update multiple hook test suites
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-10 15:53:32 +09:00
YeonGyu-Kim 0e74f5a749 fix(hooks): improve comment checker CLI runner
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-10 15:53:20 +09:00
YeonGyu-Kim 08c4757824 fix(hooks): improve auto update checker
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-10 15:53:19 +09:00
YeonGyu-Kim 111cf6d1a9 fix(hooks): improve session last agent tracking
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-10 15:53:13 +09:00
YeonGyu-Kim 25abda684c fix(hooks): improve image resizer implementation
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-10 15:53:12 +09:00
YeonGyu-Kim 5a762ba2ca fix(hooks): improve rules injector implementation
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-10 15:53:10 +09:00
YeonGyu-Kim e86b4f4c2b fix(keyword-detector): stop starting ralph loop for ulw
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-10 11:40:46 +09:00
YeonGyu-Kim 959229d9b7 test(keyword-detector): add plain ulw no-loop regressions
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-10 11:40:14 +09:00
YeonGyu-Kim 33ac57ba7a refactor: update remaining modules to use plugin-identity constants
Update various modules to use centralized constants from plugin-identity:
- get-local-version/formatter: Use PUBLISHED_PACKAGE_NAME
- run/session-resolver: Use PUBLISHED_PACKAGE_NAME
- background-agent/task-poller: Use PUBLISHED_PACKAGE_NAME
- mcp-oauth/provider: Use PUBLISHED_PACKAGE_NAME
- auto-update-checker/constants: Use ACCEPTED_PACKAGE_NAMES
- comment-checker/downloader: Use PUBLISHED_PACKAGE_NAME
- legacy-plugin-toast/hook: Use PLUGIN_NAME
- shared/data-path: Use CACHE_DIR_NAME
- shared/external-plugin-detector: Use ACCEPTED_PACKAGE_NAMES
- shared/logger: Use LOG_FILENAME
- tools/ast-grep/downloader: Use PUBLISHED_PACKAGE_NAME
- tools/call-omo-agent/tools: Use PUBLISHED_PACKAGE_NAME
- tools/delegate-task/category-resolver: Use PUBLISHED_PACKAGE_NAME
- tools/grep/constants: Use PUBLISHED_PACKAGE_NAME
- tools/grep/downloader: Use PUBLISHED_PACKAGE_NAME
- tools/lsp/lsp-client-wrapper: Use PUBLISHED_PACKAGE_NAME

🤖 Generated with assistance of OhMyOpenCode
2026-04-10 11:16:16 +09:00
YeonGyu-Kim d00a6bbf16 fix(keyword-detector): always trigger ultrawork keywords 2026-04-10 11:15:23 +09:00
YeonGyu-Kim f36231a8a6 fix(keyword-detector): trigger ulw shorthand anywhere 2026-04-10 11:12:56 +09:00
YeonGyu-Kim 5f90b238e0 fix(keyword-detector): restore ulw trigger after greeting prefixes 2026-04-10 11:09:01 +09:00