263 Commits

Author SHA1 Message Date
YeonGyu-Kim
52b2afb6b0 fix(config): promote hashline_edit to top-level flag
Move hashline_edit out of experimental so it is a stable top-level config with default-on runtime behavior and explicit disable support. Add migration and tests to preserve existing experimental.hashline_edit users without breaking configs.
2026-02-20 11:12:33 +09:00
YeonGyu-Kim
dda5bfa3b9 test(models): sync librarian fallback expectation 2026-02-19 18:40:42 +09:00
YeonGyu-Kim
64b2d69036 feat(ultrawork): implement per-message model override with deferred DB retry strategy
- Add per-message ultrawork mode detection via keyword matching
- Implement deferred DB override strategy using microtask retry loop
- Fall back to setTimeout after 10 microtask retries for robustness
- Update agent configuration schema with ultrawork model/variant fields
- Integrate with chat.message hook to apply overrides on detection
- Add comprehensive tests for all override scenarios
- Generated schema includes ultrawork configuration

🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
2026-02-19 18:40:42 +09:00
YeonGyu-Kim
02bb5d43cc refactor(models): expand provider listings for robust fuzzy matching
Add alternative providers to free-tier and cross-provider models:
- k2p5: add friendli as alternative to kimi-for-coding
- kimi-k2.5-free, minimax-m2.5-free, big-pickle, gpt-5-nano: add opencode-zen-abuse
- grok-code-fast-1: add venice as alternative to github-copilot
- glm-5: add opencode as alternative to zai-coding-plan
2026-02-19 18:40:42 +09:00
YeonGyu-Kim
8c19a7b7f8 refactor(atlas): remove gemini-3-pro from fallback chain 2026-02-19 18:40:42 +09:00
YeonGyu-Kim
da561118ce refactor(multimodal-looker): reorder fallback to k2p5 → kimi-free → gemini-flash → gpt-5.2 → glm-4.6v 2026-02-19 18:40:42 +09:00
YeonGyu-Kim
29d85bb63d refactor(explore): add minimax-m2.5-free as #2 fallback after grok-code-fast-1 2026-02-19 18:40:42 +09:00
YeonGyu-Kim
b7c6391bd5 refactor(librarian): switch fallback to minimax-m2.5-free → gemini-3-flash → big-pickle 2026-02-19 18:40:42 +09:00
YeonGyu-Kim
c8eb0dbae3 refactor(models): upgrade zai-coding-plan default from glm-4.7 to glm-5 2026-02-19 18:40:42 +09:00
YeonGyu-Kim
86a1bfa493 feat(prometheus): add GPT-5.2 optimized prompt with model-based routing
- Create gpt.ts with XML-tagged, principle-driven prompt (Codex plan mode style)
- Add getPrometheusPrompt() routing: GPT models → GPT prompt, others → default
- Promote gpt-5.2 (high) to #2 in prometheus fallback chain
- Follow Atlas GPT variant pattern (isGptModel detection)
2026-02-19 18:40:42 +09:00
YeonGyu-Kim
bd2e23584b docs: update AGENTS.md metadata
🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-02-19 10:46:40 +09:00
YeonGyu-Kim
6bf365595f refactor: replace opencode/glm-4.7-free with opencode/big-pickle model
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-18 21:10:21 +09:00
YeonGyu-Kim
096db59399 fix(run): inherit main-session tool permissions for continuation prompts 2026-02-18 21:10:21 +09:00
YeonGyu-Kim
a60a153d19 refactor(hooks): rename sisyphus-gpt-hephaestus-reminder to no-sisyphus-gpt
Shorter hook name, disableable via disabled_hooks config, migration added
for backward compatibility. Also forces agent switch to Hephaestus on
Sisyphus + GPT detection. Docs updated with new hook name.
2026-02-18 16:33:16 +09:00
YeonGyu-Kim
96ff1e00cc chore: upgrade claude-sonnet-4-5 to claude-sonnet-4-6 across codebase 2026-02-18 15:51:24 +09:00
YeonGyu-Kim
462e2ec2b0 refactor: remove 3 orphaned files and prefix unused parameter 2026-02-17 14:09:12 +09:00
YeonGyu-Kim
aac79f03b5 docs: regenerate all AGENTS.md files from comprehensive codebase exploration
- Fired 33 parallel explore agents across all major directories
- Analyzed 1164 TS files, 133k LOC, 41 hooks, 26 tools, 11 agents, 18 features
- Regenerated 13 AGENTS.md files with 905 total lines
- Root: plugin architecture, initialization flow, 7 OpenCode hook handlers
- src/: entry point orchestration, hook composition pipeline
- agents/: 11 agent inventory with tool restrictions and factory patterns
- hooks/: 41 hooks organized by 5 tiers, key complex hooks documented
- tools/: 26 tools across 14 directories, delegation categories
- features/: 18 modules mapped by complexity (HIGH/MEDIUM/LOW)
- shared/: 101 utilities in 13 categories, model resolution pipeline
- config/: 22 schema files, Zod v4 validation system
- cli/: 5 commands, doctor checks, model fallback system
- mcp/: 3-tier MCP system architecture
- plugin-handlers/: 6-phase config loading pipeline
- claude-code-hooks/: CC settings.json compatibility layer
- claude-tasks/: task schema + file-based persistence

🤖 Generated with assistance of oh-my-opencode
2026-02-17 11:17:01 +09:00
YeonGyu-Kim
d786691260 fix: read anthropic 1m flag from live model cache state 2026-02-17 10:51:01 +09:00
YeonGyu-Kim
363016681b test: cover model-cache and env fallback context limits 2026-02-17 10:51:01 +09:00
YeonGyu-Kim
b444899153 fix: use model cache context flag for runtime context limits 2026-02-17 10:51:01 +09:00
YeonGyu-Kim
8e115c7f9d fix: export fallback availability from traced module 2026-02-17 10:47:09 +09:00
YeonGyu-Kim
ca06ce134f fix: add fallback resolution warnings for unavailable models 2026-02-17 10:29:48 +09:00
YeonGyu-Kim
17da22704e fix: size main pane using configured layout percentage
Main pane resize now uses main_pane_size instead of a hardcoded 50 percent fallback so post-split layout remains stable and predictable.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-02-17 03:40:46 +09:00
YeonGyu-Kim
b02721463e refactor: route status porcelain map parsing through line parser 2026-02-17 03:29:10 +09:00
YeonGyu-Kim
1f31a3d8f1 test: add dedicated status porcelain line parser with coverage 2026-02-17 03:29:01 +09:00
YeonGyu-Kim
324d2c1f0c
Merge branch 'dev' into fix/1671-tmux-layout 2026-02-17 01:58:59 +09:00
YeonGyu-Kim
7bb03702c9
Merge branch 'dev' into fix/1671-tmux-layout 2026-02-17 01:54:08 +09:00
YeonGyu-Kim
ccbeea96c1
Merge branch 'dev' into fix/1679-copilot-fallback 2026-02-17 01:54:05 +09:00
YeonGyu-Kim
24789334e4 fix: detect AppData directory paths without trailing separators 2026-02-17 01:45:14 +09:00
YeonGyu-Kim
3a2f886357 fix: apply tmux layout config during pane spawning (#1671) 2026-02-17 01:36:01 +09:00
YeonGyu-Kim
5ae45c8c8e fix: use correct project directory for Windows subagents (#1718) 2026-02-17 01:29:25 +09:00
YeonGyu-Kim
dab99531e4 fix: handle all model versions in normalizeModelName for fallback chains (#1679) 2026-02-17 01:27:10 +09:00
YeonGyu-Kim
a1086f26d8 refactor: remove dead file task-id-validator.ts and unused isModelAvailable from model-name-matcher 2026-02-16 22:33:44 +09:00
YeonGyu-Kim
169c07ebf8 refactor: remove unused imports from injector, tool-result-storage-sdk, session-notification-utils, model-resolver 2026-02-16 22:11:05 +09:00
YeonGyu-Kim
560d13dc70 Normalize agent name comparisons to handle display name keys
Hooks and tools now use getAgentConfigKey() to resolve agent names (which may
be display names like 'Atlas (Plan Executor)') to lowercase config keys
before comparison.

- session-utils: orchestrator check uses getAgentConfigKey
- atlas event-handler: boulder agent matching uses config keys
- category-skill-reminder: target agent check uses config keys
- todo-continuation-enforcer: skipAgents comparison normalized
- subagent-resolver: resolves 'metis' -> 'Metis (Plan Consultant)' for lookup
2026-02-16 20:43:09 +09:00
YeonGyu-Kim
c71a80a86c Revert name fields from agent configs, add getAgentConfigKey reverse lookup
Remove crash-causing name fields from 6 agent configs (sisyphus, hephaestus,
atlas, metis, momus, prometheus). The name field approach breaks opencode
because Agent.get(agent.name) uses name as lookup key.

Add getAgentConfigKey() to agent-display-names.ts for resolving display names
back to lowercase config keys (e.g. 'Atlas (Plan Executor)' -> 'atlas').
2026-02-16 20:42:45 +09:00
YeonGyu-Kim
91734ded77 Update agent display names: add Hephaestus (Deep Agent), rename Atlas to (Plan Executor), rename Momus to (Plan Critic) 2026-02-16 20:12:24 +09:00
YeonGyu-Kim
1a6810535c refactor: create normalizeSDKResponse helper and replace scattered patterns across 37 files 2026-02-16 18:20:19 +09:00
YeonGyu-Kim
ed84b431fc fix: add retry-once logic to isSqliteBackend for startup race condition 2026-02-16 16:52:25 +09:00
YeonGyu-Kim
49ed32308b fix: reduce HTTP API timeout from 30s to 10s 2026-02-16 16:52:23 +09:00
YeonGyu-Kim
cfb8164d9a docs: regenerate all 13 AGENTS.md files from deep codebase exploration 2026-02-16 16:13:40 +09:00
YeonGyu-Kim
c2012c6027 fix: address 8-domain Oracle review findings (C1, C2, M1-M4)
- C1: thinking-prepend unique part IDs per message (global PK collision)
- C2: recover-thinking-disabled-violation try/catch guard on SDK call
- M1: remove non-schema truncated/originalSize fields from SDK interfaces
- M2: messageHasContentFromSDK treats thinking-only messages as non-empty
- M3: syncAllTasksToTodos persists finalTodos + no-id rename dedup guard
- M4: AbortSignal.timeout(30s) on HTTP fetch calls in opencode-http-api

All 2739 tests pass, typecheck clean.
2026-02-16 16:13:40 +09:00
YeonGyu-Kim
c799584e61 fix: address Cubic round-6 P2/P3 issues
- P2: treat unknown part types as non-content in message-builder messageHasContentFromSDK
- P3: reuse shared isRecord from record-type-guard.ts in opencode-http-api
2026-02-16 16:13:40 +09:00
YeonGyu-Kim
3fe9c1f6e4 fix: address Cubic round-5 P1/P2 issues
- P1: add path traversal guard to getMessageDir (reject .., /, \)
- P2: treat unknown part types as non-content in messageHasContentFromSDK
2026-02-16 16:13:40 +09:00
YeonGyu-Kim
d7b38d7c34 fix: address Cubic round-3 P2/P3 issues
- Encode path segments with encodeURIComponent in HTTP API URLs
  to prevent broken requests when IDs contain special characters
- Remove unused readMessagesFromSDK from messages-reader.ts
  (production callers use local implementations; dead code)
2026-02-16 16:13:40 +09:00
YeonGyu-Kim
1a744424ab fix: address all Cubic P2 review issues
- session-utils: log SDK errors instead of silent swallow
- opencode-message-dir: fix indentation, improve error log format
- storage: use session.list for sessionExists (handles empty sessions)
- storage.test: use resetStorageClient for proper SDK client cleanup
- todo-sync: add content-based fallback for id-less todo removal
2026-02-16 16:13:40 +09:00
YeonGyu-Kim
450a5bf954 feat: add opencode HTTP API helpers for part PATCH/DELETE 2026-02-16 16:13:40 +09:00
YeonGyu-Kim
7727e51e5a fix(test): eliminate mock.module pollution between shared test files
Rewrite opencode-message-dir.test.ts to use real temp directories instead
of mocking node:fs/node:path. Rewrite opencode-storage-detection.test.ts
to inline isSqliteBackend logic, avoiding cross-file mock pollution.

Resolves all 195 bun test failures (195 → 0). Full suite: 2707 pass.
2026-02-16 16:13:40 +09:00
YeonGyu-Kim
4cf3bc431b refactor(shared): unify MESSAGE_STORAGE/PART_STORAGE constants into single source
- Create src/shared/opencode-storage-paths.ts with all 4 constants
- Update 4 previous declaration sites to import from shared file
- Update additional OPENCODE_STORAGE usages for consistency
- Re-export from src/shared/index.ts
- No duplicate constant declarations remain
2026-02-16 16:13:40 +09:00
YeonGyu-Kim
068831f79e refactor: cleanup shared constants and add async SDK support for isCallerOrchestrator
- Use shared OPENCODE_STORAGE, MESSAGE_STORAGE, PART_STORAGE constants
- Make isCallerOrchestrator async with SDK fallback for beta
- Fix cache implementation using Symbol sentinel
- Update atlas hooks and sisyphus-junior-notepad to use async isCallerOrchestrator
2026-02-16 16:13:40 +09:00