docs: complete v4.1.1 drift sweep in reference and guide docs
Follow-up pass to catch drift my earlier docs commit missed: docs/reference/features.md: - 'Architecture Snapshot': 5-tier hook composition '52 base / 59 with team mode' to '54 base / 61 with team mode' (matches actual ToolGuard +2 from fsync-skip-warning + bash-file-read-guard). docs/reference/cli.md: - Add 'boulder' subcommand to Commands table (inspects boulder work-state). docs/reference/configuration.md: - Code comment example 'Kimi K2.5 work best' to 'Kimi K2.6 work best' to match current primary Sisyphus fallback chain. docs/guide/installation.md: - Add 'Kimi K2.6 (opencode-go, vercel)' row to the provider availability table above the existing K2.5 row. - Selection priority footnote and 'Safe Overrides' chains updated to mention K2.6 alongside K2.5 in Sisyphus and Atlas chains. docs/guide/agent-model-matching.md: - Provider table 'Kimi K2.5' row to 'Kimi K2.6 / K2.5'. - Atlas fallback chain mentions K2.6 instead of K2.5 alone.
This commit is contained in:
YeonGyu-Kim
@@ -255,7 +255,7 @@ Communicative, instruction-following, structured output. Best for agents that ne
|
||||
| **Claude Opus 4.7** | Best overall. Highest compliance with complex prompts. Default for Sisyphus. |
|
||||
| **Claude Sonnet 4.6** | Faster, cheaper. Good balance for everyday tasks. |
|
||||
| **Claude Haiku 4.5** | Fast and cheap. Good for quick tasks and utility work. |
|
||||
| **Kimi K2.5** | Behaves very similarly to Claude. Great all-rounder at lower cost. |
|
||||
| **Kimi K2.6 / K2.5** | Behaves very similarly to Claude. Great all-rounder at lower cost; K2.6 is the current default fallback in the Sisyphus chain. |
|
||||
| **GLM 5** | Claude-like behavior. Solid for orchestration tasks. |
|
||||
|
||||
### GPT Family
|
||||
@@ -459,7 +459,7 @@ If you have OpenRouter and want DeepSeek in the chain when GPT is unavailable:
|
||||
|
||||
- Sisyphus: Opus → Sonnet, Kimi K2.5/2.6, GLM 5 (all communicative models)
|
||||
- Prometheus: Opus → GPT-5.5 (auto-switches to the GPT prompt)
|
||||
- Atlas: Claude Sonnet 4.6 → Kimi K2.5, GPT-5.5 (auto-switches to the GPT prompt)
|
||||
- Atlas: Claude Sonnet 4.6 → Kimi K2.6 → GPT-5.5 (auto-switches to the GPT prompt)
|
||||
|
||||
**Dangerous** — personality mismatch:
|
||||
|
||||
|
||||
@@ -90,7 +90,7 @@ Ask the user these questions to determine CLI options:
|
||||
- If **no** → `--zai-coding-plan=no` (default)
|
||||
|
||||
7. **Do you have an OpenCode Go subscription?**
|
||||
- OpenCode Go is a $10/month subscription providing access to GLM-5, Kimi K2.5, and MiniMax M2.7 models
|
||||
- OpenCode Go is a $10/month subscription providing access to GLM-5/5.1, Kimi K2.5/K2.6, and MiniMax M2.7 models
|
||||
- If **yes** → `--opencode-go=yes`
|
||||
- If **no** → `--opencode-go=no` (default)
|
||||
|
||||
@@ -308,8 +308,8 @@ Not all models behave the same way. Understanding which models are "similar" hel
|
||||
| **Claude Opus 4.7** | anthropic, github-copilot, opencode | Best overall. Default for Sisyphus. |
|
||||
| **Claude Sonnet 4.6** | anthropic, github-copilot, opencode | Faster, cheaper. Good balance. |
|
||||
| **Claude Haiku 4.5** | anthropic, opencode | Fast and cheap. Good for quick tasks. |
|
||||
| **Kimi K2.6** | opencode-go, vercel | Behaves very similarly to Claude. Great all-rounder that appears in several orchestration fallback chains. |
|
||||
| **Kimi K2.5** | kimi-for-coding, opencode, moonshotai, moonshotai-cn, firmware, ollama-cloud, aihubmix | Claude-like behavior. Available on multiple providers. |
|
||||
| **Kimi K2.6** | opencode-go, vercel | Current default fallback after Claude Opus in primary Sisyphus chain. Claude-like behavior. |
|
||||
| **Kimi K2.5** | kimi-for-coding, opencode, moonshotai, moonshotai-cn, firmware, ollama-cloud, aihubmix | Claude-like behavior. Available on multiple providers. Still in active fallback chains. |
|
||||
| **Kimi K2.5 Free** | opencode | Free-tier Kimi. Rate-limited but functional. |
|
||||
| **GLM 5.1** | opencode-go, vercel | Claude-like behavior. Upgraded from GLM-5 on opencode-go. |
|
||||
| **GLM 5** | zai-coding-plan, opencode | Claude-like behavior. Good for broad tasks. |
|
||||
@@ -416,7 +416,7 @@ If the user wants to override which model an agent uses, you can customize in yo
|
||||
When choosing models for Claude-optimized agents:
|
||||
|
||||
```
|
||||
Claude (Opus/Sonnet) > GPT (if agent has dual prompt) > Claude-like (Kimi K2.5, GLM 5)
|
||||
Claude (Opus/Sonnet) > GPT (if agent has dual prompt) > Claude-like (Kimi K2.6, K2.5, GLM 5/5.1)
|
||||
```
|
||||
|
||||
When choosing models for GPT-native agents:
|
||||
@@ -429,9 +429,9 @@ GPT (5.3-codex, 5.2) > Claude Opus (decent fallback) > Gemini (acceptable)
|
||||
|
||||
**Safe** (same family):
|
||||
|
||||
- Sisyphus: Opus → Sonnet, Kimi K2.5, GLM 5
|
||||
- Sisyphus: Opus → Sonnet, Kimi K2.6 (then K2.5), GLM 5/5.1
|
||||
- Prometheus: Opus → GPT-5.5 (auto-switches prompt)
|
||||
- Atlas: Kimi K2.5 → Sonnet, GPT-5.5 (auto-switches)
|
||||
- Atlas: Kimi K2.6 → Sonnet, GPT-5.5 (auto-switches)
|
||||
|
||||
**Dangerous** (no prompt support):
|
||||
|
||||
|
||||
@@ -26,6 +26,7 @@ bunx oh-my-opencode
|
||||
| `run <message>` | Non-interactive OpenCode session runner with completion enforcement |
|
||||
| `get-local-version` | Show current installed version and check for updates |
|
||||
| `refresh-model-capabilities` | Refresh cached model capabilities snapshot from models.dev |
|
||||
| `boulder` | Inspect Sisyphus boulder work-state (active plan, per-task timers, session lineage) |
|
||||
| `version` | Show CLI version |
|
||||
| `mcp oauth` | OAuth token management for MCP servers |
|
||||
|
||||
|
||||
@@ -77,7 +77,7 @@ Here's a practical starting configuration:
|
||||
"$schema": "https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/dev/assets/oh-my-opencode.schema.json",
|
||||
|
||||
"agents": {
|
||||
// Main orchestrator: Claude Opus or Kimi K2.5 work best
|
||||
// Main orchestrator: Claude Opus or Kimi K2.6 work best
|
||||
"sisyphus": {
|
||||
"model": "kimi-for-coding/k2p5",
|
||||
"ultrawork": { "model": "anthropic/claude-opus-4-7", "variant": "max" },
|
||||
|
||||
@@ -106,7 +106,7 @@ See the **[Team Mode Guide](../guide/team-mode.md)** for configuration, team spe
|
||||
|
||||
- **Feature modules**: `src/features/` has 20 modules.
|
||||
- **Tool system**: `src/tools/` has 16 tool directories that produce **20 to 39 tools** depending on config gates.
|
||||
- **Hook system**: 5-tier composition is **52 base hooks**. With team mode it becomes **59** (extra tool guard + transforms + direct team session event handlers).
|
||||
- **Hook system**: 5-tier composition is **54 base hooks**. With team mode it becomes **61** (extra tool guard + transforms + direct team session event handlers).
|
||||
- **MCP system**: 3 tiers: built-in remote MCPs (`websearch`, `context7`, `grep_app`), `.mcp.json` loader, and skill-embedded MCP from `SKILL.md` frontmatter.
|
||||
- **Managers**: plugin startup creates 4 managers: TmuxSessionManager, BackgroundManager, SkillMcpManager, ConfigHandler.
|
||||
- **Config pipeline**: 6 phases in order: provider, plugin-components, agents, tools, MCPs, commands.
|
||||
|
||||
Reference in New Issue
Block a user