luna/oh-my-opencode
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

docs(agent-models): refresh current model guidance

Browse Source 
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-opencode)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
This commit is contained in:
YeonGyu-Kim
2026-03-06 20:50:11 +09:00
parent 1a33eab97c
commit 4e1077cc7a
1 changed files with 80 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/guide/agent-model-matching.md
+80 -62
View File
@@ -8,25 +8,27 @@ Think of AI models as developers on a team. Each has a different brain, differen
This isn't a bug. It's the foundation of the entire system. This isn't a bug. It's the foundation of the entire system.
Oh My OpenCode assigns each agent a model that matches its *working style* — like building a team where each person is in the role that fits their personality. Oh My OpenCode assigns each agent a model that matches its _working style_ — like building a team where each person is in the role that fits their personality.
### Sisyphus: The Sociable Lead ### Sisyphus: The Sociable Lead
Sisyphus is the developer who knows everyone, goes everywhere, and gets things done through communication and coordination. Talks to other agents, understands context across the whole codebase, delegates work intelligently, and codes well too. But deep, purely technical problems? He'll struggle a bit. Sisyphus is the developer who knows everyone, goes everywhere, and gets things done through communication and coordination. Talks to other agents, understands context across the whole codebase, delegates work intelligently, and codes well too. But deep, purely technical problems? He'll struggle a bit.
**This is why Sisyphus uses Claude / Kimi / GLM.** These models excel at: **This is why Sisyphus uses Claude / Kimi / GLM.** These models excel at:
- Following complex, multi-step instructions (Sisyphus's prompt is ~1,100 lines) - Following complex, multi-step instructions (Sisyphus's prompt is ~1,100 lines)
- Maintaining conversation flow across many tool calls - Maintaining conversation flow across many tool calls
- Understanding nuanced delegation and orchestration patterns - Understanding nuanced delegation and orchestration patterns
- Producing well-structured, communicative output - Producing well-structured, communicative output
Using Sisyphus with GPT would be like taking your best project manager — the one who coordinates everyone, runs standups, and keeps the whole team aligned — and sticking them in a room alone to debug a race condition. Wrong fit. No GPT prompt exists for Sisyphus, and for good reason. Using Sisyphus with older GPT models would be like taking your best project manager — the one who coordinates everyone, runs standups, and keeps the whole team aligned — and sticking them in a room alone to debug a race condition. Wrong fit. GPT-5.4 now has a dedicated Sisyphus prompt path, but GPT is still not the default recommendation for the orchestrator.
### Hephaestus: The Deep Specialist ### Hephaestus: The Deep Specialist
Hephaestus is the developer who stays in their room coding all day. Doesn't talk much. Might seem socially awkward. But give them a hard technical problem and they'll emerge three hours later with a solution nobody else could have found. Hephaestus is the developer who stays in their room coding all day. Doesn't talk much. Might seem socially awkward. But give them a hard technical problem and they'll emerge three hours later with a solution nobody else could have found.
**This is why Hephaestus uses GPT-5.3 Codex.** Codex is built for exactly this: **This is why Hephaestus uses GPT-5.3 Codex.** Codex is built for exactly this:
- Deep, autonomous exploration without hand-holding - Deep, autonomous exploration without hand-holding
- Multi-file reasoning across complex codebases - Multi-file reasoning across complex codebases
- Principle-driven execution (give a goal, not a recipe) - Principle-driven execution (give a goal, not a recipe)
@@ -60,39 +62,39 @@ Agents that support both families (Prometheus, Atlas) auto-detect your model at
These agents have Claude-optimized prompts — long, detailed, mechanics-driven. They need models that reliably follow complex, multi-layered instructions. These agents have Claude-optimized prompts — long, detailed, mechanics-driven. They need models that reliably follow complex, multi-layered instructions.
| Agent | Role | Fallback Chain | Notes | | Agent | Role | Fallback Chain | Notes |
|-------|------|----------------|-------| | ------------ | ----------------- | -------------------------------------- | ------------------------------------------------------------------------------------------------- |
| **Sisyphus** | Main orchestrator | Claude Opus → Kimi K2.5 → GLM 5 | **No GPT prompt.** Claude-family only. | | **Sisyphus** | Main orchestrator | Claude Opus → GLM 5 → Big Pickle | Claude-family first. GPT-5.4 has dedicated support, but Claude/Kimi/GLM remain the preferred fit. |
| **Metis** | Plan gap analyzer | Claude Opus → Kimi K2.5 → GPT-5.2 → Gemini 3 Pro | Claude preferred, GPT acceptable fallback. | | **Metis** | Plan gap analyzer | Claude Opus → GPT-5.2 → Gemini 3.1 Pro | Claude preferred, GPT acceptable fallback. |
### Dual-Prompt Agents → Claude preferred, GPT supported ### Dual-Prompt Agents → Claude preferred, GPT supported
These agents ship separate prompts for Claude and GPT families. They auto-detect your model and switch at runtime. These agents ship separate prompts for Claude and GPT families. They auto-detect your model and switch at runtime.
| Agent | Role | Fallback Chain | Notes | | Agent | Role | Fallback Chain | Notes |
|-------|------|----------------|-------| | -------------- | ----------------- | -------------------------------------- | -------------------------------------------------------------------- |
| **Prometheus** | Strategic planner | Claude Opus → GPT-5.2 → Kimi K2.5 → Gemini 3 Pro | Interview-mode planning. GPT prompt is compact and principle-driven. | | **Prometheus** | Strategic planner | Claude Opus → GPT-5.4 → Gemini 3.1 Pro | Interview-mode planning. GPT prompt is compact and principle-driven. |
| **Atlas** | Todo orchestrator | Kimi K2.5 → Claude Sonnet → GPT-5.2 | Kimi is the sweet spot — Claude-like but cheaper. | | **Atlas** | Todo orchestrator | Claude Sonnet 4.6 → GPT-5.4 | Claude first, GPT-5.4 as the current fallback path. |
### Deep Specialists → GPT ### Deep Specialists → GPT
These agents are built for GPT's principle-driven style. Their prompts assume autonomous, goal-oriented execution. Don't override to Claude. These agents are built for GPT's principle-driven style. Their prompts assume autonomous, goal-oriented execution. Don't override to Claude.
| Agent | Role | Fallback Chain | Notes | | Agent | Role | Fallback Chain | Notes |
|-------|------|----------------|-------| | -------------- | ----------------------- | -------------------------------------- | ------------------------------------------------ |
| **Hephaestus** | Autonomous deep worker | GPT-5.3 Codex only | No fallback. Requires GPT access. The craftsman. | | **Hephaestus** | Autonomous deep worker | GPT-5.3 Codex only | No fallback. Requires GPT access. The craftsman. |
| **Oracle** | Architecture consultant | GPT-5.2 → Gemini 3 Pro → Claude Opus | Read-only high-IQ consultation. | | **Oracle** | Architecture consultant | GPT-5.2 → Gemini 3.1 Pro → Claude Opus | Read-only high-IQ consultation. |
| **Momus** | Ruthless reviewer | GPT-5.2 → Claude Opus → Gemini 3 Pro | Verification and plan review. | | **Momus** | Ruthless reviewer | GPT-5.4 → Claude Opus → Gemini 3.1 Pro | Verification and plan review. |
### Utility Runners → Speed over Intelligence ### Utility Runners → Speed over Intelligence
These agents do grep, search, and retrieval. They intentionally use the fastest, cheapest models available. **Don't "upgrade" them to Opus** — that's hiring a senior engineer to file paperwork. These agents do grep, search, and retrieval. They intentionally use the fastest, cheapest models available. **Don't "upgrade" them to Opus** — that's hiring a senior engineer to file paperwork.
| Agent | Role | Fallback Chain | Notes | | Agent | Role | Fallback Chain | Notes |
|-------|------|----------------|-------| | --------------------- | ------------------ | ---------------------------------------------- | ----------------------------------------------------- |
| **Explore** | Fast codebase grep | Grok Code Fast → MiniMax → Haiku → GPT-5-Nano | Speed is everything. Fire 10 in parallel. | | **Explore** | Fast codebase grep | Grok Code Fast → MiniMax → Haiku → GPT-5-Nano | Speed is everything. Fire 10 in parallel. |
| **Librarian** | Docs/code search | Gemini Flash → MiniMax → GLM | Doc retrieval doesn't need deep reasoning. | | **Librarian** | Docs/code search | Gemini Flash → MiniMax → Big Pickle | Doc retrieval doesn't need deep reasoning. |
| **Multimodal Looker** | Vision/screenshots | Kimi K2.5 → Gemini Flash → GPT-5.2 → GLM-4.6v | Kimi excels at multimodal understanding. | | **Multimodal Looker** | Vision/screenshots | GPT-5.3 Codex → K2P5 → Gemini Flash → GLM-4.6v | Uses the first available multimodal-capable fallback. |
--- ---
@@ -102,32 +104,33 @@ These agents do grep, search, and retrieval. They intentionally use the fastest,
Communicative, instruction-following, structured output. Best for agents that need to follow complex multi-step prompts. Communicative, instruction-following, structured output. Best for agents that need to follow complex multi-step prompts.
| Model | Strengths | | Model | Strengths |
|-------|-----------| | --------------------- | ---------------------------------------------------------------------------- |
| **Claude Opus 4.6** | Best overall. Highest compliance with complex prompts. Default for Sisyphus. | | **Claude Opus 4.6** | Best overall. Highest compliance with complex prompts. Default for Sisyphus. |
| **Claude Sonnet 4.6** | Faster, cheaper. Good balance for everyday tasks. | | **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. | | **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. Default for Atlas. | | **Kimi K2.5** | Behaves very similarly to Claude. Great all-rounder at lower cost. |
| **GLM 5** | Claude-like behavior. Solid for orchestration tasks. | | **GLM 5** | Claude-like behavior. Solid for orchestration tasks. |
### GPT Family ### GPT Family
Principle-driven, explicit reasoning, deep technical capability. Best for agents that work autonomously on complex problems. Principle-driven, explicit reasoning, deep technical capability. Best for agents that work autonomously on complex problems.
| Model | Strengths | | Model | Strengths |
|-------|-----------| | ----------------- | ----------------------------------------------------------------------------------------------- |
| **GPT-5.3 Codex** | Deep coding powerhouse. Autonomous exploration. Required for Hephaestus. | | **GPT-5.3 Codex** | Deep coding powerhouse. Autonomous exploration. Required for Hephaestus. |
| **GPT-5.2** | High intelligence, strategic reasoning. Default for Oracle and Momus. | | **GPT-5.2** | High intelligence, strategic reasoning. Default for Oracle. |
| **GPT-5-Nano** | Ultra-cheap, fast. Good for simple utility tasks. | | **GPT-5.4** | Strong principle-driven reasoning. Default for Momus and a key fallback for Prometheus / Atlas. |
| **GPT-5-Nano** | Ultra-cheap, fast. Good for simple utility tasks. |
### Other Models ### Other Models
| Model | Strengths | | Model | Strengths |
|-------|-----------| | -------------------- | ------------------------------------------------------------------------------------------------------------ |
| **Gemini 3 Pro** | Excels at visual/frontend tasks. Different reasoning style. Default for `visual-engineering` and `artistry`. | | **Gemini 3.1 Pro** | Excels at visual/frontend tasks. Different reasoning style. Default for `visual-engineering` and `artistry`. |
| **Gemini 3 Flash** | Fast. Good for doc search and light tasks. | | **Gemini 3 Flash** | Fast. Good for doc search and light tasks. |
| **Grok Code Fast 1** | Blazing fast code grep. Default for Explore agent. | | **Grok Code Fast 1** | Blazing fast code grep. Default for Explore agent. |
| **MiniMax M2.5** | Fast and smart. Good for utility tasks and search/retrieval. | | **MiniMax M2.5** | Fast and smart. Good for utility tasks and search/retrieval. |
### About Free-Tier Fallbacks ### About Free-Tier Fallbacks
@@ -141,16 +144,16 @@ You don't need to configure them. The system includes them so it degrades gracef
When agents delegate work, they don't pick a model name — they pick a **category**. The category maps to the right model automatically. When agents delegate work, they don't pick a model name — they pick a **category**. The category maps to the right model automatically.
| Category | When Used | Fallback Chain | | Category | When Used | Fallback Chain |
|----------|-----------|----------------| | -------------------- | -------------------------- | -------------------------------------------- |
| `visual-engineering` | Frontend, UI, CSS, design | Gemini 3 Pro → GLM 5 → Claude Opus | | `visual-engineering` | Frontend, UI, CSS, design | Gemini 3.1 Pro → GLM 5 → Claude Opus |
| `ultrabrain` | Maximum reasoning needed | GPT-5.3 Codex → Gemini 3 Pro → Claude Opus | | `ultrabrain` | Maximum reasoning needed | GPT-5.3 Codex → Gemini 3.1 Pro → Claude Opus |
| `deep` | Deep coding, complex logic | GPT-5.3 Codex → Claude Opus → Gemini 3 Pro | | `deep` | Deep coding, complex logic | GPT-5.3 Codex → Claude Opus → Gemini 3.1 Pro |
| `artistry` | Creative, novel approaches | Gemini 3 Pro → Claude Opus → GPT-5.2 | | `artistry` | Creative, novel approaches | Gemini 3.1 Pro → Claude Opus → GPT-5.2 |
| `quick` | Simple, fast tasks | Claude Haiku → Gemini Flash → GPT-5-Nano | | `quick` | Simple, fast tasks | Claude Haiku → Gemini Flash → GPT-5-Nano |
| `unspecified-high` | General complex work | Claude Opus → GPT-5.2 → Gemini 3 Pro | | `unspecified-high` | General complex work | GPT-5.4 → Claude Opus → GLM 5 → K2P5 |
| `unspecified-low` | General standard work | Claude Sonnet → GPT-5.3 Codex → Gemini Flash | | `unspecified-low` | General standard work | Claude Sonnet → GPT-5.3 Codex → Gemini Flash |
| `writing` | Text, docs, prose | Gemini Flash → Claude Sonnet | | `writing` | Text, docs, prose | Gemini Flash → Claude Sonnet |
See the [Orchestration System Guide](./orchestration.md) for how agents dispatch tasks to categories. See the [Orchestration System Guide](./orchestration.md) for how agents dispatch tasks to categories.
@@ -168,33 +171,46 @@ See the [Orchestration System Guide](./orchestration.md) for how agents dispatch
// Main orchestrator: Claude Opus or Kimi K2.5 work best // Main orchestrator: Claude Opus or Kimi K2.5 work best
"sisyphus": { "sisyphus": {
"model": "kimi-for-coding/k2p5", "model": "kimi-for-coding/k2p5",
"ultrawork": { "model": "anthropic/claude-opus-4-6", "variant": "max" } "ultrawork": { "model": "anthropic/claude-opus-4-6", "variant": "max" },
}, },
// Research agents: cheaper models are fine // Research agents: cheaper models are fine
"librarian": { "model": "zai-coding-plan/glm-4.7" }, "librarian": { "model": "google/gemini-3-flash" },
"explore": { "model": "github-copilot/grok-code-fast-1" }, "explore": { "model": "github-copilot/grok-code-fast-1" },
// Architecture consultation: GPT or Claude Opus // Architecture consultation: GPT or Claude Opus
"oracle": { "model": "openai/gpt-5.2", "variant": "high" }, "oracle": { "model": "openai/gpt-5.2", "variant": "high" },
// Prometheus inherits sisyphus model; just add prompt guidance // Prometheus inherits sisyphus model; just add prompt guidance
"prometheus": { "prompt_append": "Leverage deep & quick agents heavily, always in parallel." } "prometheus": {
"prompt_append": "Leverage deep & quick agents heavily, always in parallel.",
},
}, },
"categories": { "categories": {
"quick": { "model": "opencode/gpt-5-nano" }, "quick": { "model": "opencode/gpt-5-nano" },
"unspecified-low": { "model": "kimi-for-coding/k2p5" }, "unspecified-low": { "model": "anthropic/claude-sonnet-4-6" },
"unspecified-high": { "model": "anthropic/claude-sonnet-4-6", "variant": "max" }, "unspecified-high": { "model": "openai/gpt-5.4", "variant": "high" },
"visual-engineering": { "model": "google/gemini-3-pro", "variant": "high" }, "visual-engineering": {
"writing": { "model": "kimi-for-coding/k2p5" } "model": "google/gemini-3.1-pro",
"variant": "high",
},
"writing": { "model": "google/gemini-3-flash" },
}, },
// Limit expensive providers; let cheap ones run freely // Limit expensive providers; let cheap ones run freely
"background_task": { "background_task": {
"providerConcurrency": { "anthropic": 3, "openai": 3, "opencode": 10, "zai-coding-plan": 10 }, "providerConcurrency": {
"modelConcurrency": { "anthropic/claude-opus-4-6": 2, "opencode/gpt-5-nano": 20 } "anthropic": 3,
} "openai": 3,
"opencode": 10,
"zai-coding-plan": 10,
},
"modelConcurrency": {
"anthropic/claude-opus-4-6": 2,
"opencode/gpt-5-nano": 20,
},
},
} }
``` ```
@@ -203,12 +219,14 @@ Run `opencode models` to see available models, `opencode auth login` to authenti
### Safe vs Dangerous Overrides ### Safe vs Dangerous Overrides
**Safe** — same personality type: **Safe** — same personality type:
- Sisyphus: Opus → Sonnet, Kimi K2.5, GLM 5 (all communicative models) - Sisyphus: Opus → Sonnet, Kimi K2.5, GLM 5 (all communicative models)
- Prometheus: Opus → GPT-5.2 (auto-switches to GPT prompt) - Prometheus: Opus → GPT-5.4 (auto-switches to the GPT prompt)
- Atlas: Kimi K2.5 → Sonnet, GPT-5.2 (auto-switches to GPT prompt) - Atlas: Claude Sonnet 4.6 → GPT-5.4 (auto-switches to the GPT prompt)
**Dangerous** — personality mismatch: **Dangerous** — personality mismatch:
- Sisyphus → GPT: **No GPT prompt exists. Will degrade significantly.**
- Sisyphus → older GPT models: **Still a bad fit. GPT-5.4 is the only dedicated GPT prompt path.**
- Hephaestus → Claude: **Built for Codex's autonomous style. Claude can't replicate this.** - Hephaestus → Claude: **Built for Codex's autonomous style. Claude can't replicate this.**
- Explore → Opus: **Massive cost waste. Explore needs speed, not intelligence.** - Explore → Opus: **Massive cost waste. Explore needs speed, not intelligence.**
- Librarian → Opus: **Same. Doc search doesn't need Opus-level reasoning.** - Librarian → Opus: **Same. Doc search doesn't need Opus-level reasoning.**