3554d86bac
fix: enforce continuation-aware completion gating
2026-02-17 16:01:57 +09:00
0e1c55c5cb
fix: harden run completion checks and graceful timeout
2026-02-17 16:01:57 +09:00
873c29f3d9
fix: gate run event traces behind --verbose
2026-02-17 16:01:57 +09:00
94dc6f14f5
Merge pull request #1845 from iyoda/refactor/consolidate-port-utils
...
refactor(mcp-oauth): consolidate duplicate port utilities into shared/port-utils
2026-02-17 15:59:51 +09:00
a8addb0e63
Merge pull request #1907 from BowTiedSwan/fix/json-retry-loop
...
feat(hooks): add json-error-recovery hook to prevent infinite retry loops
2026-02-17 15:59:44 +09:00
e86afe44f8
Merge pull request #1911 from jkoelker/preserve-default-agent
...
fix(config): normalize configured default_agent
2026-02-17 15:59:36 +09:00
85afcb5f0f
fix(config): scope default_agent normalization to Sisyphus mode
2026-02-17 15:50:08 +09:00
eb775d1a94
fix(hooks): harden json-error-recovery matching and scope
2026-02-17 15:46:21 +09:00
b957659da8
release: v3.7.1
2026-02-17 05:32:02 +00:00
4e84f43ba1
chore: add propertyNames constraints to JSON schema
2026-02-17 14:29:06 +09:00
1f46e73fa3
refactor: remove 3 orphaned files and prefix unused parameter
2026-02-17 14:09:12 +09:00
eef47d794d
refactor: remove 3 orphaned files from call-omo-agent and delegate-task
2026-02-17 14:08:44 +09:00
37d7247075
refactor: remove 16 orphaned files from background-agent
2026-02-17 14:08:38 +09:00
10c98519da
refactor: remove orphaned modules/ directory from background-task
2026-02-17 14:08:30 +09:00
304faf71ca
refactor: remove 3 orphaned files and unused import from tmux-subagent
2026-02-17 14:08:28 +09:00
d22c2f8a49
refactor: remove 3 orphaned files from background-agent/spawner
2026-02-17 14:08:12 +09:00
304a40a423
release: v3.7.0
2026-02-17 04:35:13 +00:00
7db82512be
refactor(prompts): replace markdown tables with bullet lists, harden Oracle protection
...
Convert all markdown tables in Sisyphus and dynamic-agent-prompt-builder
to plain bullet lists for cleaner prompt rendering.
Add explicit Oracle safeguards:
- Hard Block: background_cancel(all=true) when Oracle running
- Hard Block: delivering final answer before collecting Oracle result
- Anti-Pattern: background_cancel(all=true) and skipping Oracle
- Oracle section: NEVER cancel, collect via background_output first
- Background Result Collection: split cancel/wait into separate steps
with explicit NEVER use background_cancel(all=true) instruction
2026-02-17 13:26:37 +09:00
c470de57c3
docs: fix ultrabrain model reference in category-skill-guide (GPT-5.2→GPT-5.3 Codex)
2026-02-17 11:32:36 +09:00
2b728d5715
docs: fix agent model references in all READMEs (Opus 4.5→4.6, GPT 5.2 Codex→5.3, Librarian→GLM-4.7, Explore→Grok Code Fast 1)
2026-02-17 11:32:26 +09:00
5adf2bc632
docs: fix model references across guide docs (Opus 4.5→4.6, GPT-5.2 Codex→5.3, Atlas model, add deep category, fix dot notation)
2026-02-17 11:31:22 +09:00
ef26a31648
docs: fix agent fallback chains, provider chains, and category tables to match model-requirements.ts
...
- features.md: update explore primary model (grok-code-fast-1), fix all agent fallback chains
- configurations.md: add missing deep category, fix all agent/category provider chains, add hephaestus to available agents, update model names to match actual code
2026-02-17 11:28:32 +09:00
5eb354acc6
docs: fix structural counts in AGENTS.md (hook handlers 7→8, tool dirs 14→15, core hooks 33→32, session hooks 20→19, config merge order)
2026-02-17 11:26:28 +09:00
0a3c1bdd0f
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
28a5587144
Merge pull request #1910 from code-yeongyu/fix/1753-context-window-hardcoded
...
fix: use ModelCacheState for context window limit instead of env var (#1753 )
2026-02-17 10:53:58 +09:00
21144ed1e3
fix: read anthropic 1m flag from live model cache state
2026-02-17 10:51:01 +09:00
d979bd945a
test: cover model-cache and env fallback context limits
2026-02-17 10:51:01 +09:00
ce5e6857ad
fix: use model cache context flag for runtime context limits
2026-02-17 10:51:01 +09:00
98d23abd5c
Merge pull request #1912 from code-yeongyu/fix/1694-fallback-wiring
...
fix: wire fallback availability into runtime export path (#1694 )
2026-02-17 10:50:50 +09:00
8e55f4ee5d
fix: export fallback availability from traced module
2026-02-17 10:47:09 +09:00
d1ce02e116
fix(config): normalize configured default_agent
...
Agent keys are remapped to display names, so preserving `default_agent`
values could still select a missing key at runtime.
This regression surfaced after d94a739203
2026-02-17 01:45:47 +00:00
6e4e0f8fd0
Merge pull request #1909 from code-yeongyu/fix/1694-fallback-model-ids
...
fix: add logging and validation to fallback chain model resolution (#1694 )
2026-02-17 10:38:14 +09:00
fcf3adf43a
fix: add fallback resolution warnings for unavailable models
2026-02-17 10:29:48 +09:00
6abe98fb4c
fix(tmux): stop layout override after spawn, use configured main pane size
...
Remove applyLayout(select-layout main-vertical) call after spawn which
was destroying grid arrangements by forcing vertical stacking. Now only
enforceMainPaneWidth is called, preserving the grid created by manual
split directions. Also fix enforceMainPaneWidth to use config's
main_pane_size percentage instead of hardcoded 50%.
2026-02-17 09:50:17 +09:00
34f212c2cb
fix(tmux): use actual pane dimensions and configured min width for grid calculation
...
Agent area width now uses real mainPane.width instead of hardcoded 50%
ratio. Grid planning, split availability, and spawn target finding now
respect user's agent_pane_min_width config instead of hardcoded
MIN_PANE_WIDTH=52, enabling 2-column grid layouts on narrower terminals.
2026-02-17 09:48:18 +09:00
bbb89c5465
update: always wait for Oracle results instead of blanket background_cancel(all=true)
2026-02-17 09:42:59 +09:00
081f31bfc8
feat(hooks): add json-error-recovery hook to prevent infinite retry loops
2026-02-16 21:35:58 +02:00
36e44ab3c1
@xinpengdr has signed the CLA in code-yeongyu/oh-my-opencode#1906
2026-02-16 19:01:47 +00:00
2f345655e9
Merge pull request #1905 from code-yeongyu/fix/tmux-split-stability
...
fix: stabilize tmux split and session readiness handling
2026-02-17 03:49:30 +09:00
c7ed266806
fix: stop tracking sessions that never become ready
...
When session readiness times out, immediately close the spawned pane and skip tracking to prevent stale mappings from causing reopen and close anomalies.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-02-17 03:40:55 +09:00
b29d3ce382
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
3974fce4fb
fix: align split targeting with configured pane width
...
Use the configured agent pane width consistently in split target selection and avoid close+spawn churn by replacing the oldest pane when eviction is required.
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode )
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai >
2026-02-17 03:40:37 +09:00
51c29887eb
refactor: route status porcelain map parsing through line parser
2026-02-17 03:29:10 +09:00
5a3350f00e
test: add dedicated status porcelain line parser with coverage
2026-02-17 03:29:01 +09:00
2287392203
update: Hephaestus completion guarantee, Sisyphus-Junior Hephaestus-style rewrite, snake_case tools
...
Hephaestus:
- Add Completion Guarantee section with Codex-style persistence framing
- Add explicit explore/librarian call syntax examples (subagent_type, not category)
- Use positive 'keep going until resolved' over negative 'NEVER stop'
- Fix tool names: TaskCreate/TaskUpdate → task_create/task_update
Sisyphus-Junior GPT:
- Full Hephaestus-style rewrite: autonomy, reporting, parallelism, tool usage
- Remove Blocked & Allowed Tools section and 'You work ALONE' messaging
- Add Progress Updates, Ambiguity Protocol, Code Quality sections
- Fix tool names: TaskCreate/TaskUpdate → task_create/task_update
Sisyphus-Junior Default:
- Remove buildConstraintsSection and blocked actions messaging
- Fix tool names: TaskCreate/TaskUpdate → task_create/task_update
Tests: update all assertions for new prompt structure (31/31 pass)
2026-02-17 03:12:32 +09:00
3e06d280a9
fix: prevent overlapping poll cycles in managers
...
Guarding polling re-entry avoids stacked async polls under slow responses, and unref on pending-call cleanup timer reduces idle wakeups.
2026-02-17 03:06:40 +09:00
14374095af
update: soften Hephaestus brevity bias — replace 'brief/briefly' with 'clear' throughout
...
Replace 7 instances of brief/briefly that caused over-terse behavior:
- 'briefly restate' → 'restate'
- 'brief summary' → 'clear summary'
- 'briefly state the WHY' → 'explain the WHY' (×2)
- 'brief context' → 'clear context'
- 'Brief updates' → 'Clear updates (a few sentences)'
- 'keep it brief and clear' → 'keep it clear and helpful'
2026-02-17 02:58:42 +09:00
d2ae3999a2
update: Hephaestus prompt — restore intent gate, strengthen parallelism and reporting
...
- Restore Assumptions Check and When to Challenge the User from Sisyphus intent gate
- Add proactive explore/librarian firing to CORRECT behavior list
- Strengthen parallel execution with GPT-5.2 tool_usage_rules (parallelize ALL independent calls)
- Embed reporting into each Execution Loop step (Tell user pattern)
- Strengthen Progress Updates with plain-language and WHY-not-just-WHAT guidance
- Add post-edit reporting to Output Contract and After Implementation
- Fix Output Contract preamble conflict (skip empty preambles, but DO report actions)
2026-02-17 02:56:22 +09:00
71e4f975bb
refactor: diet Hephaestus prompt — remove redundancy, add progress updates and skill examples
...
- Remove router nudge (reasoning configuration section)
- Remove redundant sections: Role & Agency, Judicious Initiative, Success
Criteria, Response Compaction, Soft Guidelines
- Merge Identity + Core Principle into compact Identity section
- Restore autonomous behavior policy (FORBIDDEN/CORRECT) from Role & Agency
- Add Progress Updates section with friendly tone and concrete examples
- Add Skill Loading Examples table (frontend-ui-ux, playwright, git-master, tauri)
- Condense Parallel Execution, Execution Loop, Verification, Failure Recovery
- Update Output Contract with friendly communication style
651 → 437 lines (33% reduction), behavior preserved
2026-02-17 02:46:11 +09:00
289fcdffe8
fix: skip startup toasts in CLI run mode for auto-update-checker
...
Add OPENCODE_CLI_RUN_MODE environment variable check to skip all startup
toasts and version checks when running in CLI mode. This prevents
notification spam during automated CLI run sessions.
Includes comprehensive test coverage for CLI run mode behavior.
🤖 Generated with OhMyOpenCode assistance
2026-02-17 02:34:39 +09:00
YeonGyu-Kim