Commit Graph

26 Commits

Author SHA1 Message Date
Jason Kölker
a562e3aa4b 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 remapped `config.agent` keys
to display names without canonicalizing configured defaults.

Normalize configured `default_agent` through display-name mapping before
fallback logic and extend tests to cover canonical and display-name
inputs.
2026-02-17 01:45:47 +00:00
Jason Kölker
90ede4487b fix(config): preserve configured default_agent
oh-my-opencode overwrote OpenCode's default_agent with sisyphus whenever
Sisyphus orchestration was enabled. This made explicit defaults like
Hephaestus ineffective and forced manual agent switching in new sessions.

Only assign sisyphus as default when default_agent is missing or blank,
and preserve existing configured values. Add tests for both preservation
and fallback behavior to prevent regressions.
2026-02-17 01:41:52 +09:00
YeonGyu-Kim
be2e45b4cb test: update assertions for display name agent keys
- config-handler.test: look up agents by display name keys
- agent-key-remapper.test: new tests for key remapping function
- Rebuild schema asset
2026-02-16 20:43:18 +09:00
YeonGyu-Kim
e257bff31c fix(plugin-handlers): remove as any type assertions in config-handler tests
Replace unsafe `as any` casts on `createBuiltinAgents` spy with properly
typed `as unknown as { mockResolvedValue: ... }` pattern. Adds bun-types
reference directive.

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-02-08 18:00:12 +09:00
YeonGyu-Kim
e7f4f6dd13 fix: deny todowrite/todoread per-agent when task_system is enabled
When experimental.task_system is enabled, add todowrite: deny and
todoread: deny to per-agent permissions for all primary agents
(sisyphus, hephaestus, atlas, prometheus, sisyphus-junior).

This ensures the model never sees these tools in its tool list,
complementing the existing global tools config and runtime hook.
2026-02-08 14:05:53 +09:00
YeonGyu-Kim
b88a868173 fix(config): plan agent inherits model settings from prometheus when not explicitly configured
Previously, demoted plan agent only received { mode: 'subagent' } with no
model settings, causing fallback to step-3.5-flash. Now inherits all
model-related settings (model, variant, temperature, top_p, maxTokens,
thinking, reasoningEffort, textVerbosity, providerOptions) from the
resolved prometheus config. User overrides via agents.plan.* take priority.

Prompt, permission, description, and color are intentionally NOT inherited.
2026-02-08 13:22:56 +09:00
YeonGyu-Kim
7ede8e04f0 fix(config-handler): add timeout + error boundary around loadAllPluginComponents (#1559) 2026-02-07 13:32:57 +09:00
YeonGyu-Kim
a691a3ac0a refactor: migrate delegate_task to task tool with metadata fixes
- Rename delegate_task tool to task across codebase (100 files)
- Update model references: claude-opus-4-6 → 4-5, gpt-5.3-codex → 5.2-codex
- Add tool-metadata-store to restore metadata overwritten by fromPlugin()
- Add session ID polling for BackgroundManager task sessions
- Await async ctx.metadata() calls in tool executors
- Add ses_ prefix guard to getMessageDir for performance
- Harden BackgroundManager with idle deferral and error handling
- Fix duplicate task key in sisyphus-junior test object literals
- Fix unawaited showOutputToUser in ast_grep_replace
- Fix background=true → run_in_background=true in ultrawork prompt
- Fix duplicate task/task references in docs and comments
2026-02-06 21:35:30 +09:00
YeonGyu-Kim
3a0d7e8dc3 fix(config): stop sisyphus-junior from inheriting UI-selected model 2026-02-06 17:44:47 +09:00
YeonGyu-Kim
1f64920453 chore: update claude-opus-4-5 references to claude-opus-4-6 (excludes antigravity models) 2026-02-06 15:09:07 +09:00
YeonGyu-Kim
4c7215404e chore: update gpt-5.2-codex references to gpt-5.3-codex 2026-02-06 15:08:33 +09:00
YeonGyu-Kim
f030992755 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
9d217b05b8 fix(config-handler): preserve plan prompt when demoted (#1416) 2026-02-03 13:37:57 +09:00
YeonGyu-Kim
7ebafe2267 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
64825158a7 feat(agents): add Hephaestus - autonomous deep worker agent (#1287)
* refactor(keyword-detector): split constants into domain-specific modules

* feat(shared): add requiresAnyModel and isAnyFallbackModelAvailable

* feat(config): add hephaestus to agent schemas

* feat(agents): add Hephaestus autonomous deep worker

* feat(cli): update model-fallback for hephaestus support

* feat(plugin): add hephaestus to config handler with ordering

* test(delegate-task): update tests for hephaestus agent

* docs: update AGENTS.md files for hephaestus

* docs: add hephaestus to READMEs

* chore: regenerate config schema

* fix(delegate-task): bypass requiresModel check when user provides explicit config

* docs(hephaestus): add 4-part context structure for explore/librarian prompts

* docs: fix review comments from cubic (non-breaking changes)

- Move Hephaestus from Primary Agents to Subagents (uses own fallback chain)
- Fix Hephaestus fallback chain documentation (claude-opus-4-5 → gemini-3-pro)
- Add settings.local.json to claude-code-hooks config sources
- Fix delegate_task parameters in ultrawork prompt (agent→subagent_type, background→run_in_background, add load_skills)
- Update line counts in AGENTS.md (index.ts: 788, manager.ts: 1440)

* docs: fix additional documentation inconsistencies from oracle review

- Fix delegate_task parameters in Background Agents example (docs/features.md)
- Fix Hephaestus fallback chain in root AGENTS.md to match model-requirements.ts

* docs: clarify Hephaestus has no fallback (requires gpt-5.2-codex only)

Hephaestus uses requiresModel constraint - it only activates when gpt-5.2-codex
is available. The fallback chain in code is unreachable, so documentation
should not mention fallbacks.

* fix(hephaestus): remove unreachable fallback chain entries

Hephaestus has requiresModel: gpt-5.2-codex which means the agent only
activates when that specific model is available. The fallback entries
(claude-opus-4-5, gemini-3-pro) were unreachable and misleading.

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-02-01 19:26:57 +09:00
gabriel-ecegi
ffbca5e48e fix(config): properly handle prompt_append for Prometheus agent (#1271)
- Extract prompt_append from override and append to prompt instead of shallow spread
- Add test verifying prompt_append is appended, not overwriting base prompt
- Fixes #723

Co-authored-by: Gabriel Ečegi <gabriel-ecegi@users.noreply.github.com>
2026-02-01 19:11:49 +09:00
YeonGyu-Kim
f146aeff0f refactor: major codebase cleanup - BDD comments, file splitting, bug fixes (#1350)
* style(tests): normalize BDD comments from '// #given' to '// given'

- Replace 4,668 Python-style BDD comments across 107 test files
- Patterns changed: // #given -> // given, // #when -> // when, // #then -> // then
- Also handles no-space variants: //#given -> // given

* fix(rules-injector): prefer output.metadata.filePath over output.title

- Extract file path resolution to dedicated output-path.ts module
- Prefer metadata.filePath which contains actual file path
- Fall back to output.title only when metadata unavailable
- Fixes issue where rules weren't injected when tool output title was a label

* feat(slashcommand): add optional user_message parameter

- Add user_message optional parameter for command arguments
- Model can now call: command='publish' user_message='patch'
- Improves error messages with clearer format guidance
- Helps LLMs understand correct parameter usage

* feat(hooks): restore compaction-context-injector hook

- Restore hook deleted in cbbc7bd0 for session compaction context
- Injects 7 mandatory sections: User Requests, Final Goal, Work Completed,
  Remaining Tasks, Active Working Context, MUST NOT Do, Agent Verification State
- Re-register in hooks/index.ts and main plugin entry

* refactor(background-agent): split manager.ts into focused modules

- Extract constants.ts for TTL values and internal types (52 lines)
- Extract state.ts for TaskStateManager class (204 lines)
- Extract spawner.ts for task creation logic (244 lines)
- Extract result-handler.ts for completion handling (265 lines)
- Reduce manager.ts from 1377 to 755 lines (45% reduction)
- Maintain backward compatible exports

* refactor(agents): split prometheus-prompt.ts into subdirectory

- Move 1196-line prometheus-prompt.ts to prometheus/ subdirectory
- Organize prompt sections into separate files for maintainability
- Update agents/index.ts exports

* refactor(delegate-task): split tools.ts into focused modules

- Extract categories.ts for category definitions and routing
- Extract executor.ts for task execution logic
- Extract helpers.ts for utility functions
- Extract prompt-builder.ts for prompt construction
- Reduce tools.ts complexity with cleaner separation of concerns

* refactor(builtin-skills): split skills.ts into individual skill files

- Move each skill to dedicated file in skills/ subdirectory
- Create barrel export for backward compatibility
- Improve maintainability with focused skill modules

* chore: update import paths and lockfile

- Update prometheus import path after refactor
- Update bun.lock

* fix(tests): complete BDD comment normalization

- Fix remaining #when/#then patterns missed by initial sed
- Affected: state.test.ts, events.test.ts

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-02-01 16:47:50 +09:00
Kwanghyun Moon
b405494808 fix: resolve deadlock in config handler during plugin initialization (#1304)
* fix: resolve deadlock in config handler during plugin initialization

The config handler and createBuiltinAgents were calling fetchAvailableModels
with client, which triggers client.provider.list() API call to OpenCode server.
This caused a deadlock because:
- Plugin initialization waits for server response
- Server waits for plugin init to complete before handling requests

Now using cache-only mode by passing undefined instead of client.
If cache is unavailable, the fallback chain will use the first model.

Fixes #1301

* test: add regression tests for deadlock prevention in fetchAvailableModels

Add tests to ensure fetchAvailableModels is called with undefined client
during plugin initialization. This prevents regression on issue #1301.

- config-handler.test.ts: verify config handler does not pass client
- utils.test.ts: verify createBuiltinAgents does not pass client

* test: restore spies in utils.test.ts to prevent test pollution

Add mockRestore() calls for all spies created in test cases to ensure proper cleanup between tests and prevent state leakage.

* test: restore fetchAvailableModels spy

---------

Co-authored-by: robin <robin@watcha.com>
Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-31 12:46:05 +09:00
justsisyphus
cd4da93bf2 fix(test): migrate config-handler tests from mock.module to spyOn to prevent cross-file cache pollution 2026-01-29 21:35:14 +09:00
YeonGyu-Kim
23b49c4a5c fix: expand override.category and explicit reasoningEffort priority (#1219) (#1235)
* fix: expand override.category and explicit reasoningEffort priority (#1219)

Two bugs fixed:

1. createBuiltinAgents(): override.category was never expanded into concrete
   config properties (model, variant, reasoningEffort, etc.). Added
   applyCategoryOverride() helper and applied it in the standard agent loop,
   Sisyphus path, and Atlas path.

2. Prometheus config-handler: reasoningEffort/textVerbosity/thinking from
   direct override now use explicit priority chains (direct > category)
   matching the existing variant pattern, instead of relying on spread
   ordering.

Priority order (highest to lowest):
  1. Direct override properties
  2. Override category properties
  3. Resolved variant from model fallback chain
  4. Factory base defaults

Closes #1219

* fix: use undefined check for thinking to allow explicit false
2026-01-29 19:46:34 +09:00
justsisyphus
9b59ef66e4 test: fix flaky tests caused by mock.module pollution across parallel test files 2026-01-28 00:54:20 +09:00
justsisyphus
488c89156b test(config-handler): add tests for plan demote and prometheus mode 2026-01-27 16:06:03 +09:00
YeonGyu-Kim
04633ba208 fix(models): update model names to match OpenCode Zen catalog (#1048)
* fix(models): update model names to match OpenCode Zen catalog

OpenCode Zen recently updated their official model catalog, deprecating
several preview and free model variants:

DEPRECATED → NEW (Official Zen Names):
- gemini-3-pro-preview → gemini-3-pro
- gemini-3-flash-preview → gemini-3-flash
- grok-code → gpt-5-nano (FREE tier maintained)
- glm-4.7-free → big-pickle (FREE tier maintained)
- glm-4.6v → glm-4.6

Changes:
- Updated 6 source files (model-requirements, delegate-task, think-mode, etc.)
- Updated 9 documentation files (installation, configurations, features, etc.)
- Updated 14 test files with new model references
- Regenerated snapshots to reflect catalog changes
- Removed duplicate think-mode entries for preview variants

Impact:
- FREE tier access preserved via gpt-5-nano and big-pickle
- All 55 model-related tests passing
- Zero breaking changes - pure string replacement
- Aligns codebase with official OpenCode Zen model catalog

Verified:
- Zero deprecated model names in codebase
- All model-related tests pass (55/55)
- Snapshots regenerated and validated

Affects: 30 files (6 source, 9 docs, 14 tests, 1 snapshot)

* fix(multimodal-looker): update fallback chain with glm-4.6v and gpt-5-nano

- Change glm-4.6 to glm-4.6v for zai-coding-plan provider
- Add opencode/gpt-5-nano as 4th fallback (FREE tier)
- Push gpt-5.2 to 5th position

Fallback chain now:
1. gemini-3-flash (google, github-copilot, opencode)
2. claude-haiku-4-5 (anthropic, github-copilot, opencode)
3. glm-4.6v (zai-coding-plan)
4. gpt-5-nano (opencode) - FREE
5. gpt-5.2 (openai, github-copilot, opencode)

* chore: update bun.lock

---------

Co-authored-by: justsisyphus <justsisyphus@users.noreply.github.com>
2026-01-24 15:30:35 +09:00
justsisyphus
3d3d3e493b fix(delegate-task): category built-in model takes precedence over inherited model
Previously, when using categories like 'quick', the parent session's model
(e.g., Opus 4.5) would override the category's built-in model (e.g., Haiku).

Fixed priority: userConfig.model → category built-in → systemDefault

The inherited model from parent session no longer affects category-based
delegation - categories have their own explicit models.
2026-01-20 17:05:17 +09:00
Kenny
c698a5b888 fix: remove hardcoded model defaults from categories and agents
BREAKING CHANGE: Model resolution overhauled

- Created centralized model-resolver.ts with priority chain:
  userModel → inheritedModel → systemDefaultModel
- Removed model field from all 7 DEFAULT_CATEGORIES entries
- Removed DEFAULT_MODEL constants from 10 agents
- Removed singleton agent exports (use factories instead)
- Made CategoryConfigSchema.model optional
- CLI no longer generates model overrides
- Empty strings treated as unset (uses fallback)

Users must now:
1. Use factory functions (createOracleAgent, etc.) instead of singletons
2. Provide model explicitly or use systemDefaultModel
3. Configure category models explicitly if needed

Fixes model fallback bug where hardcoded defaults overrode
user's OpenCode configured model.
2026-01-17 12:51:03 -05:00
Ivan Marshall Widjaja
f9dca8d877 fix(config): resolve category to model for Prometheus (Planner) agent (#652)
* fix(config): resolve category to model for Prometheus (Planner) agent

When Prometheus (Planner) was configured with only a category (e.g.,
"ultrabrain") and no explicit model, the category was ignored and the
agent fell back to the hardcoded default "anthropic/claude-opus-4-5".
Add resolveModelFromCategoryWithUserOverride() helper that checks user
categories first, then DEFAULT_CATEGORIES, to resolve category names
to their corresponding models. Apply this resolution when building
the Prometheus agent configuration.

Co-Authored-By: Sisyphus <sisyphus@mengmota.com>

* fix(test): use actual implementation instead of local duplicate

Co-Authored-By: Sisyphus <sisyphus@mengmota.com>

* fix(config): apply all category properties, not just model for Prometheus (Planner)

The resolveModelFromCategoryWithUserOverride() helper only extracted
the model field from CategoryConfig, ignoring critical properties like
temperature, top_p, tools, maxTokens, thinking, reasoningEffort, and
textVerbosity. This caused categories like "ultrabrain" (temperature:
0.1) to run with incorrect default temperatures.

Refactor resolveModelFromCategoryWithUserOverride() to
resolveCategoryConfig() that returns the full CategoryConfig. Update
Prometheus (Planner) configuration to apply all category properties
(temperature, top_p, tools, etc.) when a category is specified, matching
the pattern established in Sisyphus-Junior. Explicit overrides still
take precedence during merge.

Co-Authored-By: Sisyphus <sisyphus@mengmota.com>

---------

Co-authored-by: Sisyphus <sisyphus@mengmota.com>
2026-01-12 12:04:55 +09:00