The caller-facing description told orchestrators WHAT `deep` is but
never specified goal cardinality, so they bundled multiple goals into
one call (e.g. "fix X + merge Y + deploy Z"). The deep agent's own
prompt was already configured to refuse such bundles, but only after
they arrived. The rule now lives on the caller side: ONE goal + ONE
deliverable per call; multiple goals must fan out as parallel `deep`
calls.
Update the README quick-overview bullet and the dedicated File Locations
section in docs/reference/configuration.md to describe the walk-up
behaviour added in #417: configs under `.opencode/` are discovered by
walking from the working directory up to $HOME, with closer configs
winning.
Includes a hierarchical example (`~/.config/opencode/` global,
`~/work/.opencode/` work overrides, repo-specific overrides under that)
and a security note explaining why `mcp_env_allowlist` remains
extensible only from the canonical user config.
Document the new primary chain and install-time fallback behavior for explorer and librarian.\nKeep the user-facing guidance aligned with the runtime and CLI model selection.
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
Syncs the README translations, CONTRIBUTING, docs/reference,
docs/guide, docs/examples JSONC configs, and the hierarchical
src/**/AGENTS.md files with the model version bump already landed
in the source and migration commits.
- Split two separate JSON objects into separate code blocks
- Remove 'stream' field from agent config (not in schema)
- Add note about streaming configuration location
The Sisyphus Tasks section documented a nonexistent 'enabled' field
with a default of 'false', which contradicts the actual behavior:
- The SisyphusTasksConfigSchema has no 'enabled' field; it only has
storage_path, task_list_id, and claude_code_compat
- The task system toggle lives at experimental.task_system and
defaults to true (since v3.14)
Updated the docs to:
- Remove the phantom 'enabled' field from example and options table
- Add the missing 'task_list_id' option that exists in the schema
- Clarify that sisyphus.tasks configures storage only
- Point to experimental.task_system as the actual on/off toggle
- Explain what the task system does (replaces TodoWrite/TodoRead)
Updated across README (all locales), docs/guide/, docs/reference/,
docs/examples/, AGENTS.md files, and test expectations/snapshots.
The deep category and multimodal-looker still use gpt-5.3-codex as
those are separate from the hephaestus agent.
- Upgrade minimax-m2.5 → minimax-m2.7 (latest model) across all agents and categories
- Replace minimax-m2.5-free with minimax-m2.7-highspeed (optimized speed variant)
- Expand MiniMax fallback coverage to atlas, sisyphus-junior, writing, and unspecified-low
- Add isMiniMaxModel() detection function in types.ts for model family detection
- Update all tests (58 passing) and documentation
The GitHub repository was renamed from oh-my-opencode to oh-my-openagent,
but all documentation, scripts, and source code references still pointed
to the old repository name. This caused confusion for users who saw
'oh-my-opencode' in docs but a different repo name on GitHub.
Updated all references across:
- README files (en, ko, ja, zh-cn, ru)
- CONTRIBUTING.md
- docs/ (installation, overview, configuration, etc.)
- Source code (schema URLs, GitHub API calls, issue links)
- Test snapshots
The npm package name remains 'oh-my-opencode' (unchanged).
Fixes: https://x.com/Dhruv14588676/status/2031216617762468348
- Update DEFAULT_CATEGORIES to use 'openai/gpt-5.4-high' directly instead of separate model + variant
- Add helper functions (isExplicitHighModel, getExplicitHighBaseModel) to preserve explicit high models during fuzzy matching
- Update category resolver to avoid collapsing explicit high models to base model + variant pair
- Update tests to verify explicit high model handling in both background and sync modes
- Update documentation examples to reflect new configuration
🤖 Generated with OhMyOpenCode assistance
Align runtime defaults, tests, docs, and generated artifacts with the newer GPT-5.4 baseline. Keep think-mode and prompt-routing expectations consistent after the model version bump.
Hashline edit tool and companion hooks now require explicit opt-in
via `"hashline_edit": true` in config. Previously enabled by default.
- tool-registry: hashline edit tool not registered unless opted in
- create-tool-guard-hooks: hashline-read-enhancer disabled by default
- Updated config schema comment and documentation
- Added TDD tests for default behavior
YeonGyu-Kim