feat(codex): advance Codex/OpenAI model defaults to GPT-5.6 (Sol/Terra/Luna)
Update runtimeTierDefaults.codex and providerPresets.openai in model-catalog.json to the GPT-5.6 family (gpt-5.6-sol/terra/luna), advancing from the superseded GPT-5.4/5.5 generation. Model IDs verified against OpenAI developer API docs: - gpt-5.6-sol: flagship, /, reasoning xhigh - gpt-5.6-terra: balanced, .50/, reasoning medium - gpt-5.6-luna: fast/cheap, /, reasoning medium Tier mapping is 1:1 (Sol↔flagship, Terra↔balanced, Luna↔fast), so profile semantics are unchanged — only the underlying IDs advance. Updates: catalog JSON, test assertions (catalog defaults), docs (CONFIGURATION.md + zh-CN/pt-BR translations, workflow settings), and changeset. Closes #2122
This commit is contained in:
Tom Boucher
@@ -1419,7 +1419,7 @@ When `runtime` is set, profile tiers (`opus`/`sonnet`/`haiku`) resolve to runtim
|
||||
| Runtime | `opus` | `sonnet` | `haiku` | reasoning_effort |
|
||||
|---------|--------|----------|---------|------------------|
|
||||
| `claude` | `claude-opus-4-8` | `claude-sonnet-5` | `claude-haiku-4-5` | (not used) |
|
||||
| `codex` | `gpt-5.5` | `gpt-5.4` | `gpt-5.4-mini` | `xhigh` / `medium` / `medium` |
|
||||
| `codex` | `gpt-5.6-sol` | `gpt-5.6-terra` | `gpt-5.6-luna` | `xhigh` / `medium` / `medium` |
|
||||
| `qwen` | `qwen3-max-2026-01-23` | `qwen3-coder-plus` | `qwen3-coder-next` | (not used) |
|
||||
| `opencode` | `anthropic/claude-opus-4-8` | `anthropic/claude-sonnet-5` | `anthropic/claude-haiku-4-5` | (not used) |
|
||||
| `copilot` | `claude-opus-4-8` | `claude-sonnet-5` | `claude-haiku-4-5` | (not used) |
|
||||
@@ -1437,7 +1437,7 @@ When `runtime` is set, profile tiers (`opus`/`sonnet`/`haiku`) resolve to runtim
|
||||
}
|
||||
```
|
||||
|
||||
This resolves `gsd-planner` → `gpt-5.5` (xhigh), `gsd-executor` → `gpt-5.4` (medium), `gsd-codebase-mapper` → `gpt-5.4-mini` (medium). The Codex installer embeds `model = "..."` and `model_reasoning_effort = "..."` in each generated agent TOML.
|
||||
This resolves `gsd-planner` → `gpt-5.6-sol` (xhigh), `gsd-executor` → `gpt-5.6-terra` (medium), `gsd-codebase-mapper` → `gpt-5.6-luna` (medium). The Codex installer embeds `model = "..."` and `model_reasoning_effort = "..."` in each generated agent TOML.
|
||||
|
||||
**Claude example** — explicit opt-in resolves to full Claude IDs (no `resolve_model_ids: true` needed):
|
||||
|
||||
@@ -1502,9 +1502,9 @@ Choose a provider and budget level via the settings workflow; GSD writes the can
|
||||
"model_policy": {
|
||||
"provider": "openai",
|
||||
"budget": "medium",
|
||||
"high": "gpt-5.5",
|
||||
"medium": "gpt-5.4",
|
||||
"low": "gpt-5.4-mini"
|
||||
"high": "gpt-5.6-sol",
|
||||
"medium": "gpt-5.6-terra",
|
||||
"low": "gpt-5.6-luna"
|
||||
}
|
||||
}
|
||||
```
|
||||
@@ -1520,9 +1520,9 @@ For advanced per-runtime control, `runtime_tiers` accepts explicit entries using
|
||||
"provider": "openai",
|
||||
"runtime_tiers": {
|
||||
"codex": {
|
||||
"opus": { "model": "gpt-5.5", "reasoning_effort": "high" },
|
||||
"sonnet": { "model": "gpt-5.4", "reasoning_effort": "medium" },
|
||||
"haiku": { "model": "gpt-5.4-mini", "reasoning_effort": "low" }
|
||||
"opus": { "model": "gpt-5.6-sol", "reasoning_effort": "high" },
|
||||
"sonnet": { "model": "gpt-5.6-terra", "reasoning_effort": "medium" },
|
||||
"haiku": { "model": "gpt-5.6-luna", "reasoning_effort": "low" }
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1140,7 +1140,7 @@ A saída JSON de `resolve-model` inclui `reasoning_effort` quando o nível de ru
|
||||
| Runtime | `opus` | `sonnet` | `haiku` | reasoning_effort |
|
||||
|---------|--------|----------|---------|------------------|
|
||||
| `claude` | `claude-opus-4-8` | `claude-sonnet-5` | `claude-haiku-4-5` | (não usado) |
|
||||
| `codex` | `gpt-5.5` | `gpt-5.3-codex` | `gpt-5.4-mini` | `xhigh` / `medium` / `medium` |
|
||||
| `codex` | `gpt-5.6-sol` | `gpt-5.6-terra` | `gpt-5.6-luna` | `xhigh` / `medium` / `medium` |
|
||||
| `gemini` | `gemini-3-pro` | `gemini-3-flash` | `gemini-2.5-flash-lite` | (não usado) |
|
||||
| `qwen` | `qwen3-max-2026-01-23` | `qwen3-coder-plus` | `qwen3-coder-next` | (não usado) |
|
||||
| `opencode` | `anthropic/claude-opus-4-8` | `anthropic/claude-sonnet-5` | `anthropic/claude-haiku-4-5` | (não usado) |
|
||||
@@ -1157,7 +1157,7 @@ A saída JSON de `resolve-model` inclui `reasoning_effort` quando o nível de ru
|
||||
}
|
||||
```
|
||||
|
||||
Isso resolve `gsd-planner` → `gpt-5.5` (xhigh), `gsd-executor` → `gpt-5.3-codex` (medium), `gsd-codebase-mapper` → `gpt-5.4-mini` (medium). O instalador do Codex incorpora `model = "..."` e `model_reasoning_effort = "..."` em cada TOML de agente gerado.
|
||||
Isso resolve `gsd-planner` → `gpt-5.6-sol` (xhigh), `gsd-executor` → `gpt-5.6-terra` (medium), `gsd-codebase-mapper` → `gpt-5.6-luna` (medium). O instalador do Codex incorpora `model = "..."` e `model_reasoning_effort = "..."` em cada TOML de agente gerado.
|
||||
|
||||
**Exemplo Claude** — opt-in explícito resolve para IDs Claude completos (sem necessidade de `resolve_model_ids: true`):
|
||||
|
||||
@@ -1222,9 +1222,9 @@ Escolha um provedor e nível de orçamento via o fluxo de configurações; o GSD
|
||||
"model_policy": {
|
||||
"provider": "openai",
|
||||
"budget": "medium",
|
||||
"high": "gpt-5.5",
|
||||
"medium": "gpt-5.3-codex",
|
||||
"low": "gpt-5.4-mini"
|
||||
"high": "gpt-5.6-sol",
|
||||
"medium": "gpt-5.6-terra",
|
||||
"low": "gpt-5.6-luna"
|
||||
}
|
||||
}
|
||||
```
|
||||
@@ -1240,9 +1240,9 @@ Para controle avançado por runtime, `runtime_tiers` aceita entradas explícitas
|
||||
"provider": "openai",
|
||||
"runtime_tiers": {
|
||||
"codex": {
|
||||
"opus": { "model": "gpt-5.5", "reasoning_effort": "high" },
|
||||
"sonnet": { "model": "gpt-5.3-codex", "reasoning_effort": "medium" },
|
||||
"haiku": { "model": "gpt-5.4-mini", "reasoning_effort": "low" }
|
||||
"opus": { "model": "gpt-5.6-sol", "reasoning_effort": "high" },
|
||||
"sonnet": { "model": "gpt-5.6-terra", "reasoning_effort": "medium" },
|
||||
"haiku": { "model": "gpt-5.6-luna", "reasoning_effort": "low" }
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1109,7 +1109,7 @@ minimal < low < medium < high < xhigh < max
|
||||
| 运行时 | `opus` | `sonnet` | `haiku` | reasoning_effort |
|
||||
|---------|--------|----------|---------|------------------|
|
||||
| `claude` | `claude-opus-4-8` | `claude-sonnet-5` | `claude-haiku-4-5` | （不使用） |
|
||||
| `codex` | `gpt-5.5` | `gpt-5.3-codex` | `gpt-5.4-mini` | `xhigh` / `medium` / `medium` |
|
||||
| `codex` | `gpt-5.6-sol` | `gpt-5.6-terra` | `gpt-5.6-luna` | `xhigh` / `medium` / `medium` |
|
||||
| `gemini` | `gemini-3-pro` | `gemini-3-flash` | `gemini-2.5-flash-lite` | （不使用） |
|
||||
| `qwen` | `qwen3-max-2026-01-23` | `qwen3-coder-plus` | `qwen3-coder-next` | （不使用） |
|
||||
| `opencode` | `anthropic/claude-opus-4-8` | `anthropic/claude-sonnet-5` | `anthropic/claude-haiku-4-5` | （不使用） |
|
||||
@@ -1126,7 +1126,7 @@ minimal < low < medium < high < xhigh < max
|
||||
}
|
||||
```
|
||||
|
||||
这将 `gsd-planner` 解析为 `gpt-5.5`（xhigh），`gsd-executor` 解析为 `gpt-5.3-codex`（medium），`gsd-codebase-mapper` 解析为 `gpt-5.4-mini`（medium）。Codex 安装器将 `model = "..."` 和 `model_reasoning_effort = "..."` 嵌入每个生成的 agent TOML。
|
||||
这将 `gsd-planner` 解析为 `gpt-5.6-sol`（xhigh），`gsd-executor` 解析为 `gpt-5.6-terra`（medium），`gsd-codebase-mapper` 解析为 `gpt-5.6-luna`（medium）。Codex 安装器将 `model = "..."` 和 `model_reasoning_effort = "..."` 嵌入每个生成的 agent TOML。
|
||||
|
||||
**Claude 示例** — 显式选择解析到完整 Claude ID（无需 `resolve_model_ids: true`）：
|
||||
|
||||
@@ -1191,9 +1191,9 @@ minimal < low < medium < high < xhigh < max
|
||||
"model_policy": {
|
||||
"provider": "openai",
|
||||
"budget": "medium",
|
||||
"high": "gpt-5.5",
|
||||
"medium": "gpt-5.3-codex",
|
||||
"low": "gpt-5.4-mini"
|
||||
"high": "gpt-5.6-sol",
|
||||
"medium": "gpt-5.6-terra",
|
||||
"low": "gpt-5.6-luna"
|
||||
}
|
||||
}
|
||||
```
|
||||
@@ -1209,9 +1209,9 @@ minimal < low < medium < high < xhigh < max
|
||||
"provider": "openai",
|
||||
"runtime_tiers": {
|
||||
"codex": {
|
||||
"opus": { "model": "gpt-5.5", "reasoning_effort": "high" },
|
||||
"sonnet": { "model": "gpt-5.3-codex", "reasoning_effort": "medium" },
|
||||
"haiku": { "model": "gpt-5.4-mini", "reasoning_effort": "low" }
|
||||
"opus": { "model": "gpt-5.6-sol", "reasoning_effort": "high" },
|
||||
"sonnet": { "model": "gpt-5.6-terra", "reasoning_effort": "medium" },
|
||||
"haiku": { "model": "gpt-5.6-luna", "reasoning_effort": "low" }
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user