Commit Graph

8 Commits

Author SHA1 Message Date
YeonGyu-Kim ed16dc0608 fix(chat-params): complete maxOutputTokens migration in session prompt params 2026-04-08 17:14:17 +09:00
YeonGyu-Kim 1fae073009 fix(sync): forward delegated model tuning params
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
2026-04-04 15:40:37 +09:00
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 42fb2548d6 fix(agent): always keep agent when model is explicitly configured
Previously, when an explicit model was configured, the agent name was
omitted to prevent opencode's built-in agent fallback chain from
overriding the user-specified model. This removes that conditional logic
and always passes the agent name alongside the model. Tests are updated
to reflect this behavior change.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-25 11:46:07 +09:00
YeonGyu-Kim 931bf6c31b fix: resolve JSON parse error in Oracle after promptAsync refactor (#1681) 2026-02-17 01:29:17 +09:00
YeonGyu-Kim b58f3edf6d refactor: remove redundant subagent-question-blocker hook
Replace PreToolUse hook-based question tool blocking with the existing
tools parameter approach (tools: { question: false }) which physically
removes the tool from the LLM's toolset before inference.

The hook was redundant because every session.prompt() call already passes
question: false via the tools parameter. OpenCode converts this to a
PermissionNext deny rule and deletes the tool from the toolset, preventing
the LLM from even seeing it. The hook only fired after the LLM already
called the tool, wasting tokens.

Changes:
- Remove subagent-question-blocker hook invocation from PreToolUse chain
- Remove hook registration from create-session-hooks.ts
- Delete src/hooks/subagent-question-blocker/ directory (dead code)
- Remove hook from HookNameSchema and barrel export
- Fix sync-executor.ts missing question: false in tools parameter
- Add regression tests for both the removal and the tools parameter
2026-02-13 14:55:46 +09:00
YeonGyu-Kim 162701f56e test(delegate-task): validate sync prompt tool restrictions 2026-02-10 22:54:48 +09:00
YeonGyu-Kim df0b9f7664 fix(delegate-task): Wave 1 - fix polling timeout, resource cleanup, tool restrictions, idle dedup, auth-plugins JSONC, CLI runner hang
- fix(delegate-task): return error on poll timeout instead of silent null
- fix(delegate-task): ensure toast and session cleanup on all error paths with try/finally
- fix(delegate-task): apply agent tool restrictions in sync-prompt-sender
- fix(plugin): add symmetric idle dedup to prevent double hook triggers
- fix(cli): replace regex-based JSONC editing with jsonc-parser in auth-plugins
- fix(cli): abort event stream after completion and restore no-timeout default

All changes verified with tests and typecheck.
2026-02-10 22:00:54 +09:00