Commit Graph

20 Commits

Author SHA1 Message Date
YeonGyu-Kim
d9ee0d9c0d docs: rewrite agent-model matching as technical guide for agents
Rewrite agent-model-matching.md as a technical reference that:
- Documents actual fallback chains from model-requirements.ts
- Explains model-specific prompt routing (Prometheus/Atlas GPT detection)
- Covers safe vs dangerous model substitutions with rationale
- Includes task categories (visual-engineering, deep, quick, etc.)
- Guides agents on how to explain model choices to users
- Adds provider priority chain

Also update installation.md to reference the guide when users
want custom model configuration, with explanation of what is
safe to change and why.
2026-02-19 15:01:34 +09:00
YeonGyu-Kim
6df7f73f81 refactor: remove dead ultrawork model override code
Remove ultrawork-model-override hook and per-agent ultrawork model swap
config that relied on zen opencode.ai free tier (no longer functional).

Removed:
- src/hooks/ultrawork-model-override/ (hook, test, index)
- ultrawork field from AgentOverrideConfigSchema
- ultrawork-model-override from HookNameSchema
- UltraworkConfig type from model-fallback-types
- Non-max20 sonnet+ultrawork-opus codepath from model-fallback
- Claude subscription model table from installation docs
- All references in plugin-interface, create-session-hooks, schema.json
- Related test cases and updated snapshots
2026-02-19 03:17:40 +09:00
YeonGyu-Kim
617e53605a feat(cli): use sonnet-4-6 with ultrawork opus-4-6 for non-max20 Claude subscribers 2026-02-18 17:47:08 +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
fba06868dd docs: fix model references across guide docs (Opus 4.5→4.6, GPT-5.2 Codex→5.3, Atlas model, add deep category, fix dot notation) 2026-02-17 11:31:22 +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
b19bc857e3 fix(docs): instruct curl over WebFetch for installation (#1461) 2026-02-04 11:25:25 +09:00
Junho Yeo
3074434887 fix: use correct gh api command for starring repo (#1274)
`gh repo star` is not a valid GitHub CLI command.
Use `gh api --silent --method PUT /user/starred/OWNER/REPO` instead.
2026-01-30 15:58:56 +09:00
justsisyphus
67aeb9cb8c chore: replace big-pickle model with glm-4.7-free 2026-01-30 13:44:04 +09:00
justsisyphus
d9723e76ab refactor: remove unused background-compaction hook module 2026-01-25 12:58:05 +09:00
justsisyphus
c8cc94cd3c fix: remove github-copilot association from gpt-5-nano model mapping
explore agent uses opencode/gpt-5-nano exclusively — github-copilot
should not be associated with gpt-5-nano in docs, tests, or fallback chains.
2026-01-25 12:46:03 +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
luojiyin
e3cc4c8cef Merge branch 'dev' into fix/typos 2026-01-22 10:51:45 +08:00
justsisyphus
1ab97bd0a7 fix: replace invalid --chatgpt option with --openai in CLI 2026-01-22 10:28:10 +09:00
justsisyphus
ffe82c1dbd feat(cli): redesign model fallback with native cross-fallback and OpenAI separation
- Add OpenAI/ChatGPT as separate subscription option (--openai flag)
- Implement native tier cross-fallback (Claude → OpenAI → Gemini)
- Change fallback order: Native → OpenCode Zen → GitHub Copilot → Z.ai
- Add explore agent special logic: max20 → haiku, else → grok-code
- Add critical warning when Claude is not configured
- Add tests for ChatGPT-only and explore agent cases
2026-01-21 11:19:00 +09:00
justsisyphus
c00f210922 feat(cli): add model fallback system with provider priority
Implements intelligent model selection based on available providers.
Priority order: Native > Copilot > OpenCode Zen > Z.ai > Ultimate Fallback.

- Add model-fallback.ts with MODEL_CATALOG and capability-based resolution
- Extend InstallConfig with hasOpencodeZen and hasZaiCodingPlan
- Add TUI prompts and CLI args for new provider options
- Z.ai gets Librarian priority (zai-coding-plan/glm-4.7)

🤖 Generated with assistance of [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)
2026-01-21 11:19:00 +09:00
justsisyphus
f1887327ee refactor(agents): remove document-writer agent in favor of writing category
- Delete document-writer.ts agent file
- Remove from types, schema, utils, index exports
- Remove tool restrictions entry
- Remove migration mappings
- Update atlas.ts to use category="writing" instead of agent="document-writer"
- Update init-deep command template
- Update all documentation (AGENTS.md, README.*, docs/)
- Regenerate schema.json

document-writer functionality is now handled via delegate_task with
category="writing" which uses the writing category's model config.
2026-01-20 16:52:31 +09:00
luojiyin
d61817bc76 fix: correct spelling errors (IDEALY→IDEALLY, EXPLICITELY→EXPLICITLY) 2026-01-20 13:31:37 +08:00
justsisyphus
380b946681 docs 2026-01-19 14:58:13 +09:00
justsisyphus
b0bb4048c9 docs update 2026-01-19 14:58:13 +09:00