Commit Graph

16 Commits

Author SHA1 Message Date
YeonGyu-Kim d5fbada13d test: make unsafe test coercion explicit
Move test coercion out of a hidden global and require each test to import the helper so review tools and runtime scripts can see the unsafe boundary.

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

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-12 15:51:31 +09:00
YeonGyu-Kim fb135d047c test(tools): remove unsafe test assertions
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-05-12 15:48:46 +09:00
YeonGyu-Kim d65bc8730c feat(agents): add gpt-5.5 native deep category prompt
Hephaestus 5.5 was rewritten as an outcome-first delegation contract in c3fabaaf. The deep category (spawned as sisyphus-junior under gpt-5.5) now receives a matching prose-driven category context lifted from drafts/gpt-5-5/deep.md instead of the legacy gpt-5.4-era threat-frame version.

Selection happens via a new model-aware resolvePromptAppend hook on BuiltinCategoryDefinition. When the resolved category model is gpt-5.5 the new DEEP_CATEGORY_PROMPT_APPEND_GPT_5_5 is used; older models keep the legacy DEEP_CATEGORY_PROMPT_APPEND. User prompt_append remains preserved on top of either base.
2026-04-29 15:49:27 +09:00
YeonGyu-Kim def44338ff refactor(models): bump claude-opus-4-6 to claude-opus-4-7 across fallback chains, categories, and hooks
Updates the canonical Anthropic Opus model in every fallback chain
(sisyphus, oracle, prometheus, metis, momus, visual-engineering,
ultrabrain, deep, artistry, unspecified-high), the unspecified-high
category default, the think-mode HIGH_VARIANT_MAP, the Claude Code
alias map, the claude-thinking legacy alias, the context-limit GA
regex, and event.ts fallback strings.

Widens supportsCachedAnthropicLimit to accept both claude-*-4-6 and
claude-*-4-7 so the 1M context cache still applies across the bump.

Regenerates the bundled model-capabilities snapshot from models.dev
and the model-fallback snapshot to match the new source output.
2026-04-17 14:51:52 +09:00
YeonGyu-Kim ee8410ce03 fix: allow variant override even with agent model config (#3163)
model-selection.ts now separates model selection from variant/reasoning
tier, so agent model overrides don't lock the variant.

34 tests pass, 5009 total, tsc clean.

Closes #3163
2026-04-07 15:29:12 +09:00
YeonGyu-Kim 889294a5fd fix(model-fallback): respect user model override for sisyphus-junior category sessions (#2941)
When users configure agents.sisyphus-junior.model, category sessions
should use that model without falling back to hardcoded
AGENT_MODEL_REQUIREMENTS. Two leaks existed:

1. Launch-time: category-resolver.ts did not check overrideModel when
   deciding whether to use the hardcoded fallbackChain. Fixed by adding
   overrideModel to the suppression condition.

2. Runtime retry: model-fallback hook.ts treated undefined fallbackChain
   (from setSessionFallbackChain(id, undefined)) as 'no override' and
   fell through to AGENT_MODEL_REQUIREMENTS on session.error/status
   retry. Fixed by storing explicit empty array and checking .has()
   instead of truthiness.

Tests added:
- hook.test.ts: explicit empty session fallback suppresses agent chain
- event.model-fallback-2941.test.ts: session.error does not arm retry
- category-resolver.test.ts: overrideModel suppresses fallbackChain
- tools.test.ts: sisyphusJuniorModel override assertion
2026-04-07 11:20:42 +09:00
YeonGyu-Kim 8f449e1627 fix: respect user-configured category model over fallbackChain defaults
When a user configures a custom model for a category (e.g. quick.model),
the hardcoded CATEGORY_MODEL_REQUIREMENTS fallbackChain was overriding it.
This caused the user's model to be ignored and replaced with the default
(e.g. openai/gpt-5.4-mini).

Fix:
- Use userModelOverride directly instead of potentially stale actualModel
- Suppress hardcoded fallbackChain when explicitCategoryModel is provided
- Add regression test verifying user category model takes precedence

Closes #3040
2026-04-03 18:27:26 +09:00
YeonGyu-Kim 43023b1eb4 fix(delegate-task): preserve inline variant from category model string
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-01 18:16:37 -07:00
YeonGyu-Kim dc1c410405 fix(delegate-task): update test category references from deep to quick
🤖 Generated with assistance of OhMyOpenCode
2026-03-31 18:11:29 -07:00
Ravi Tharuma e5c5438a44 fix(delegate-task): gate fallback settings to real fallback matches 2026-03-25 11:04:49 +01:00
Ravi Tharuma a77a16c494 feat(config): support object-style fallback_models with per-model settings
Add support for object-style entries in fallback_models arrays, enabling
per-model configuration of variant, reasoningEffort, temperature, top_p,
maxTokens, and thinking settings.

- Zod schema for FallbackModelObject with full validation
- normalizeFallbackModels() and flattenToFallbackModelStrings() utilities
- Provider-agnostic model resolution pipeline with fallback chain
- Session prompt params state management
- Fallback chain construction with prefix-match lookup
- Integration across delegate-task, background-agent, and plugin layers
2026-03-25 11:04:49 +01:00
YeonGyu-Kim e9887dd82f fix(doctor): align auto-update and doctor config paths 2026-03-17 15:56:02 +09:00
Ravi Tharuma 86c6bc7716 Unify dynamic fallback chains for background subagents 2026-03-09 12:43:30 +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 7fe1a653c8 fix(tests): stabilize toast manager and continuation tests 2026-02-10 22:00:54 +09:00
YeonGyu-Kim 19a4324b3e fix(provider-cache): extract models from provider.list().all response
OpenCode SDK does not expose client.model.list API. This caused the
provider-models cache to always be empty (models: {}), which in turn
caused delegate-task categories with requiresModel (e.g., 'deep',
'artistry') to fail with misleading 'Unknown category' errors.

Changes:
- connected-providers-cache.ts: Extract models from provider.list()
  response's .all array instead of calling non-existent client.model.list
- category-resolver.ts: Distinguish between 'unknown category' and
  'model not available' errors with clearer error messages
- Add comprehensive tests for both fixes

Bug chain:
client.model?.list is undefined -> empty cache -> isModelAvailable
returns false for requiresModel categories -> null returned from
resolveCategoryConfig -> 'Unknown category' error (wrong message)
2026-02-10 13:25:49 +09:00