From d16d47a0b4b0ba6b6262d863c7175076a6e23f09 Mon Sep 17 00:00:00 2001 From: YeonGyu-Kim Date: Thu, 14 May 2026 13:05:15 +0900 Subject: [PATCH] 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. --- docs/guide/agent-model-matching.md | 4 ++-- docs/guide/installation.md | 12 ++++++------ docs/reference/cli.md | 1 + docs/reference/configuration.md | 2 +- docs/reference/features.md | 2 +- 5 files changed, 11 insertions(+), 10 deletions(-) diff --git a/docs/guide/agent-model-matching.md b/docs/guide/agent-model-matching.md index 891441d31..94a2a4d17 100644 --- a/docs/guide/agent-model-matching.md +++ b/docs/guide/agent-model-matching.md @@ -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: diff --git a/docs/guide/installation.md b/docs/guide/installation.md index 97e88f4ff..973c3dd7b 100644 --- a/docs/guide/installation.md +++ b/docs/guide/installation.md @@ -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): diff --git a/docs/reference/cli.md b/docs/reference/cli.md index ca33f7614..481d28fad 100644 --- a/docs/reference/cli.md +++ b/docs/reference/cli.md @@ -26,6 +26,7 @@ bunx oh-my-opencode | `run ` | 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 | diff --git a/docs/reference/configuration.md b/docs/reference/configuration.md index d67f4f1fc..53fe9e100 100644 --- a/docs/reference/configuration.md +++ b/docs/reference/configuration.md @@ -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" }, diff --git a/docs/reference/features.md b/docs/reference/features.md index d3bf03776..1d89ff545 100644 --- a/docs/reference/features.md +++ b/docs/reference/features.md @@ -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.