luna/oh-my-opencode
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,774 Commits 102 Branches 0 Tags
a7262000ffdff63682aff4ade534de077930b89c
Commit Graph

1774 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
dan a7262000ff fix(auth): opencode desktop server unauthorized bugfix on subagent spawn (#1399) 
* fix(auth): opencode desktop server unauthorized bugfix on subagent spawn

* refactor(auth): add runtime guard and throw on SDK mismatch

- Add JSDoc with SDK API documentation reference
- Replace silent failure with explicit Error throw when OPENCODE_SERVER_PASSWORD is set but client structure is incompatible
- Add runtime type guard for SDK client structure
- Add tests for error cases (missing _client, missing setConfig)
- Remove unrelated bun.lock changes

Co-authored-by: dan-myles <dan-myles@users.noreply.github.com>

---------

Co-authored-by: YeonGyu-Kim <code.yeon.gyu@gmail.com>
Co-authored-by: dan-myles <dan-myles@users.noreply.github.com>
 2026-02-04 11:07:02 +09:00
Rishi Vhavle 2dc241cbbe fix: block bash commands in Prometheus mode to respect permission config (#1449) 
Fixes #1428 - Prometheus bash bypass security issue
 2026-02-04 11:06:54 +09:00
YeonGyu-Kim df784c4f83 fix(non-interactive-env): use detectShellType() instead of hardcoded 'unix' (#1459) 
The shellType was hardcoded to 'unix' which breaks on native Windows shells
(cmd.exe, PowerShell) when running without Git Bash or WSL.

This change uses the existing detectShellType() function to dynamically
determine the correct shell type, enabling proper env var syntax for all
supported shell environments.
 2026-02-04 10:52:46 +09:00
github-actions[bot] 99f83a844f @kaizen403 has signed the CLA in code-yeongyu/oh-my-opencode#1449 2026-02-03 20:44:35 +00:00
github-actions[bot] 3905adf5ea @wydrox has signed the CLA in code-yeongyu/oh-my-opencode#1436 2026-02-03 16:39:46 +00:00
github-actions[bot] c93027ef66 @filipemsilv4 has signed the CLA in code-yeongyu/oh-my-opencode#1435 2026-02-03 14:38:23 +00:00
github-actions[bot] 26a70f5ada @sk0x0y has signed the CLA in code-yeongyu/oh-my-opencode#1434 2026-02-03 14:21:40 +00:00
github-actions[bot] ff43ef3f50 @Stranmor has signed the CLA in code-yeongyu/oh-my-opencode#1432 2026-02-03 13:53:27 +00:00
github-actions[bot] 3bc3a3dcf0 @ualtinok has signed the CLA in code-yeongyu/oh-my-opencode#1393 2026-02-03 12:43:21 +00:00
github-actions[bot] c1e08c939a @ilarvne has signed the CLA in code-yeongyu/oh-my-opencode#1422 2026-02-03 08:15:51 +00:00
github-actions[bot] ad4bec384f release: v3.2.2 2026-02-03 07:59:49 +00:00
YeonGyu-Kim ce482f82b4 fix(background-cancel): skip notification when user explicitly cancels tasks 
- Add skipNotification option to cancelTask method
- Apply skipNotification to background_cancel tool
- Prevents unwanted notifications when user cancels via tool
 2026-02-03 16:56:40 +09:00
YeonGyu-Kim 242c63a2fb docs: add Task system documentation 
- Document TaskCreate, TaskGet, TaskList, TaskUpdate tools
- Note that these tools follow Claude Code internal specs but are not officially documented by Anthropic
- Include schema, dependency system, and usage examples
 2026-02-03 16:35:49 +09:00
YeonGyu-Kim dc0eceadce feat(tasks-todowrite-disabler): add strong emphasis to register tasks before working 
Add warning that even trivial tasks must be registered with TaskCreate
before starting work - no direct work without task tracking.
 2026-02-03 16:27:58 +09:00
YeonGyu-Kim a0a73971e1 docs(agents): regenerate AGENTS.md hierarchy with init-deep 
- Root: preserve 3 CRITICAL sections (PR target, OpenCode source, English-only)
- Update all 10 AGENTS.md files with current codebase analysis
- Add complexity hotspots, agent models, anti-patterns
- Sync line counts and structure with actual implementation
 2026-02-03 16:21:31 +09:00
YeonGyu-Kim 4aa95e6f83 feat(delegate-task): add actionable TODO list template to plan agent prompt 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-02-03 15:58:06 +09:00
YeonGyu-Kim 4b16fbee05 feat(auto-slash-command): add builtin commands support and improve part extraction 
- Add builtin commands to command discovery with 'builtin' scope
- Improve extractPromptText to prioritize slash command parts
- Add findSlashCommandPartIndex helper for locating slash commands
- Add CommandExecuteBefore hook support
 2026-02-03 14:33:53 +09:00
YeonGyu-Kim 3827b5b913 fix(config): prevent plan agent from inheriting prometheus prompt on demote 
Plan agent demote now only sets mode to 'subagent' without spreading
prometheus config. This ensures plan agent uses OpenCode's default
prompt instead of inheriting prometheus prompt.
 2026-02-03 14:28:57 +09:00
YeonGyu-Kim f787e15dc9 feat(agents): add GPT-5.2 optimized prompt for sisyphus-junior 
Restructure sisyphus-junior agent to use model-specific prompts:
- GPT models: GPT-5.2 prompting guide principles (verbosity constraints,
  scope discipline, tool usage rules, explicit decision criteria)
- Claude models: Original prompt with extended reasoning context

Directory structure now mirrors atlas/ pattern for consistency.
 2026-02-03 14:12:22 +09:00
YeonGyu-Kim 172efc4d04 feat(tasks-todowrite-disabler): improve error message with actionable workflow guidance 2026-02-03 14:11:27 +09:00
YeonGyu-Kim 013fc5f57c feat(agents): add useTaskSystem flag for conditional todo/task discipline prompts 
- Sisyphus: buildTaskManagementSection() with todo/task variants
- Sisyphus-Junior: buildTodoDisciplineSection() with todo/task variants
- Hephaestus: buildTodoDisciplineSection() with todo/task variants
- All factory functions accept useTaskSystem parameter (default: false)
 2026-02-03 13:58:56 +09:00
YeonGyu-Kim 9519f2e4f9 feat(agents): add Todo Discipline section to Hephaestus prompt 2026-02-03 13:52:03 +09:00
YeonGyu-Kim e4988a83b2 fix(config-handler): preserve plan prompt when demoted (#1416) 2026-02-03 13:37:57 +09:00
YeonGyu-Kim c7c8c9f01f refactor(ultrawork): simplify workflow and apply parallel context gathering (#1412) 
* refactor(ultrawork): simplify workflow to natural tool-like agent usage

Restore beta.16 style where explore/librarian agents feel like tools:
- Simplify delegate_task examples (agent=, background=true)
- Remove verbose DATA DEPENDENCIES explanation
- Condense EXECUTION RULES to action-oriented bullets
- Simplify WORKFLOW to 4 clear steps
- Remove procedural constraints that discouraged parallel exploration

The goal: agents fire background tasks AND continue direct exploration,
rather than waiting passively for background results.

* refactor(ultrawork/gpt5.2): apply two-track parallel context gathering

Based on GPT-5.2 Prompting Guide recommendations:
- 'Parallelize independent reads to reduce latency'
- Fire background agents (explore, librarian) for deep search
- Use direct tools (Grep, Read, LSP) simultaneously for quick wins
- Collect and merge ALL findings for comprehensive context

Pattern: background fire → direct exploration in parallel → collect → proceed

* fix: address Cubic review feedback

- Fix delegate_task parameter names in default.ts (agent → subagent_type, background → run_in_background)
- Add missing load_skills and run_in_background parameters to delegate_task examples
- Restore new_task_system_enabled property to schema and TypeScript config
- Fix tool names in gpt5.2.ts (Grep → grep, Read → read_file)

Identified by cubic (https://cubic.dev)
 2026-02-03 12:13:22 +09:00
YeonGyu-Kim 1de6b52307 fix(prometheus): enforce path constraints and atomic write protocol (#1414) 
* fix(prometheus): enforce path constraints and atomic write protocol

- Add FORBIDDEN PATHS section blocking docs/, plan/, plans/ directories
- Add SINGLE ATOMIC WRITE protocol to prevent content loss from multiple writes
- Simplify PROMETHEUS_AGENTS array to single PROMETHEUS_AGENT string

* fix: reconcile Edit tool signature in interview-mode.ts with identity-constraints.ts

Identified by cubic: Edit tool usage was inconsistent between files.

- interview-mode.ts showed: Edit(path, content)
- identity-constraints.ts showed: Edit(path, oldString="...", newString="...")

Updated interview-mode.ts to use the correct Edit signature with oldString and newString parameters to match the actual tool API and prevent agent hallucination.
 2026-02-03 12:11:52 +09:00
YeonGyu-Kim c05ee6f75f refactor(config-handler): separate plan prompt into dedicated configuration (#1413) 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-02-03 12:11:49 +09:00
YeonGyu-Kim 7930d87812 refactor(background-agent): optimize lifecycle and simplify tools (#1411) 
* refactor(background-agent): optimize cache timer lifecycle and result handling

Ultraworked with Sisyphus

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

* refactor(background-task): simplify tool implementation and expand test coverage

Ultraworked with Sisyphus

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

* fix(background-task): fix BackgroundCancel tool parameter handling

Correct parameter names and types in BackgroundCancel tool to match actual usage patterns. Add comprehensive test coverage for parameter validation.

---------

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-02-03 12:11:45 +09:00
YeonGyu-Kim 28e149e5d7 feat(agents): respect uiSelectedModel in Atlas model resolution (#1410) 
Atlas now respects uiSelectedModel when resolving model in createBuiltinAgents. Added test coverage for this behavior.
 2026-02-03 12:11:42 +09:00
YeonGyu-Kim 9ccca7a97f feat(task-system): add experimental task system with Claude Code spec alignment (#1415) 
* feat(hooks): add tasks-todowrite-disabler hook to block TodoRead/TodoWrite

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

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

* feat(task-tools): add parallel execution guidance to descriptions

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

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

* refactor(index): migrate task system to experimental.task_system flag

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

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

* docs: update AGENTS.md for experimental task system

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

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

* fix(task-tests): align test field names with Claude Code spec (subject, blockedBy, addBlockedBy)

* fix: address Cubic review feedback

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

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

* fix: add optional chaining for tasksTodowriteDisabler null check

---------

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-02-03 12:11:23 +09:00
YeonGyu-Kim 6b8294b7e5 docs(AGENTS): add critical sections for PR workflow and OpenCode source reference 
- Emphasize PR target branch rule with NEVER DELETE warning
- Add git workflow diagram (master <- dev <- feature branches)
- Add OpenCode source code reference section for plugin development
- Emphasize librarian agent usage for plugin-related tasks
 2026-02-03 11:05:45 +09:00
YeonGyu-Kim 7b63c46739 refactor(oracle): optimize prompt for GPT-5.2 with XML structure and verbosity constraints 
- Restructure prompt with XML tags for better instruction adherence
- Add output_verbosity_spec with concrete limits (≤7 steps, ≤3 sentences)
- Add uncertainty_and_ambiguity section with decision tree
- Add scope_discipline to prevent scope drift
- Add tool_usage_rules for efficient tool calling
- Add high_risk_self_check for architecture/security answers
- Add long_context_handling for large code inputs
- Update context to support session continuation follow-ups
 2026-02-03 11:03:41 +09:00
YeonGyu-Kim 817fc208b8 fix(prompts): add missing run_in_background and load_skills params to examples 
All delegate_task examples now include required parameters to prevent
model confusion about parameter omission.

Fixes #1403
 2026-02-03 10:50:26 +09:00
YeonGyu-Kim 713df6b0a5 fix(delegate-task): honor sisyphus-junior model override precedence (#1404) 2026-02-03 10:41:26 +09:00
YeonGyu-Kim 163995d5c8 atlas reminder reinforce 2026-02-03 10:31:34 +09:00
github-actions[bot] 071a31911a @dan-myles has signed the CLA in code-yeongyu/oh-my-opencode#1399 2026-02-02 16:59:02 +00:00
YeonGyu-Kim 39dc2ff303 feat: add agent fallback and preemptive-compaction restoration 
- Add agent visibility fallback for first-run scenarios
- Restore preemptive-compaction hook
- Update migration and schema for preemptive-compaction restoration
 2026-02-02 22:40:59 +09:00
YeonGyu-Kim 1bba54c7f6 docs: update AGENTS.md with explore agent model change (grok-code-fast-1) 2026-02-02 21:19:21 +09:00
YeonGyu-Kim 8fa3da6080 feat(agents): add grok-code-fast-1 as primary model for explore agent 2026-02-02 21:13:45 +09:00
YeonGyu-Kim 9cab46f917 refactor(background-agent): optimize cache timer lifecycle and result handling 
Improve cache timer management in background agent manager and update result handler to properly handle cache state transitions
 2026-02-02 21:07:20 +09:00
YeonGyu-Kim 1520d6b3c6 feat(skills): set triage category ratio to 1:2:1 (unspecified-low:writing:quick) 2026-02-02 21:07:20 +09:00
YeonGyu-Kim bc3a337c30 feat(skills): add streaming mode and todo tracking to triage skills 
- Convert github-pr-triage to streaming architecture (process PRs one-by-one with immediate reporting)
- Convert github-issue-triage to streaming architecture (process issues one-by-one with real-time updates)
- Add mandatory initial todo registration for both triage skills
- Add phase-by-phase todo status updates
- Generate final comprehensive report at the end
- Show live progress every 5 items during processing
 2026-02-02 21:07:20 +09:00
YeonGyu-Kim 31e5673ec8 docs(issue-templates): add AI agent consultation to prerequisite checklist 2026-02-02 21:07:20 +09:00
YeonGyu-Kim 86642c7117 refactor(agents): restructure atlas agent into modular directory with model-based routing 
Split monolithic atlas.ts into modular structure: index.ts (routing), default.ts (Claude-optimized), gpt.ts (GPT-optimized), utils.ts (shared utilities). Atlas now routes to appropriate prompt based on model type instead of overriding model settings.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
 2026-02-02 21:07:20 +09:00
YeonGyu-Kim 1b45576b72 fix: honor agent variant overrides (#1394) 
* fix(shared): honor agent variant overrides

* test(shared): use model in fallback chain to verify override precedence

Address PR review: test now uses claude-opus-4-5 (which has default
variant 'max' in sisyphus chain) to properly verify that agent override
'high' takes precedence over the fallback chain's default variant.
 2026-02-02 21:07:10 +09:00
github-actions[bot] 0d2578efe5 @pierrecorsini has signed the CLA in code-yeongyu/oh-my-opencode#1386 2026-02-02 07:59:23 +00:00
YeonGyu-Kim 4fa854ad08 test(task): improve todo-sync tests with bun-types and inline assertions 
🤖 Generated with assistance of OhMyOpenCode (https://github.com/code-yeongyu/oh-my-opencode)
 2026-02-02 16:50:13 +09:00
YeonGyu-Kim a65e5a7073 feat(task): add real-time single-task todo sync via OpenCode API 
- Add syncTaskTodoUpdate function for immediate todo updates
- Integrate with TaskCreate and TaskUpdate tools
- Preserve existing todos when updating single task
- Add comprehensive tests for new sync function

🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
 2026-02-02 15:05:07 +09:00
YeonGyu-Kim 6c789eac16 format: apply prettier to index.ts 
🤖 Generated with [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
 2026-02-02 15:04:53 +09:00
YeonGyu-Kim 465c0168a5 refactor(prometheus): replace binary verification with layered agent-executed QA 
Restructure verification strategy from binary (TDD xor manual) to layered
(TDD AND/OR agent QA). Elevate zero-human-intervention as universal principle,
require per-scenario ultra-detailed QA format with named scenarios, negative
cases, and evidence capture. Remove ambiguous 'manual QA' terminology.
 2026-02-02 14:18:01 +09:00
YeonGyu-Kim 0541c58cb3 feat(task): refactor to Claude Code style individual tools 
- Split unified Task tool into individual tools (TaskCreate, TaskGet, TaskList, TaskUpdate)
- Update schema to Claude Code field names (subject, blockedBy, blocks, activeForm, owner, metadata)
- Add OpenCode Todo API sync layer (todo-sync.ts)
- Implement Todo sync on task create/update for continuation enforcement
- Add comprehensive tests for all tools (96 tests total)
- Update AGENTS.md documentation

Breaking Changes:
- Field names changed: title→subject, dependsOn→blockedBy, open→pending
- Tool names changed: task→task_create, task_get, task_list, task_update

Closes: todo-continuation-enforcer now sees Task-created items
 2026-02-02 13:13:06 +09:00