puter/paseo
1
0
Fork 0
mirror of https://github.com/getpaseo/paseo.git synced 2026-07-29 12:01:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update MiniMax structured generation fallback (#1955)

Browse Source 
Prefer MiniMax M3 for metadata generation and align the related docs/tests with the newer provider model.

Co-authored-by: octo-patch <266937838+octo-patch@users.noreply.github.com>
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Octopus
2026-07-10 02:26:12 +08:00
committed by GitHub
parent ebaecace2b
commit 15d3091104
4 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/custom-providers.md
View File

@@ -171,7 +171,7 @@ For pay-as-you-go, use `ANTHROPIC_API_KEY` with a standard Model Studio key (`sk
| `qwen3-coder-next` | Optimized for coding |
| `kimi-k2.5` | Vision capable |
| `glm-5` | Zhipu GLM |
| `MiniMax-M2.5` | MiniMax |
| `MiniMax-M3` | MiniMax |
**Additional models (pay-as-you-go):**
`qwen3-max`, `qwen3.5-flash`, `qwen3-coder-plus`, `qwen3-coder-flash`, `qwen3-vl-plus`, `qwen3-vl-flash`

4
packages/server/src/server/agent/structured-generation-providers.test.ts
View File

@@ -68,7 +68,7 @@ describe("resolveStructuredGenerationProviders", () => {
status: READY,
enabled: true,
models: [
{ provider: "router", id: "minimax-m2.5-free", label: "MiniMax M2.5", isDefault: true },
{ provider: "router", id: "minimax-m3-free", label: "MiniMax M3", isDefault: true },
{ provider: "router", id: "nemotron-3-super-free", label: "Nemotron 3 Super" },
],
},
@@ -87,7 +87,7 @@ describe("resolveStructuredGenerationProviders", () => {
expect(providers).toEqual([
{ provider: "work-claude", model: "claude-haiku-2026" },
{ provider: "work-codex", model: "gpt-5.4-mini-2026", thinkingOptionId: "low" },
{ provider: "router", model: "minimax-m2.5-free" },
{ provider: "router", model: "minimax-m3-free" },
{ provider: "router", model: "nemotron-3-super-free" },
{ provider: "focused-provider", model: "focused-model", thinkingOptionId: "high" },
]);

2
packages/server/src/server/agent/structured-generation-providers.ts
View File

@@ -25,7 +25,7 @@ export const DEFAULT_STRUCTURED_GENERATION_PROVIDERS: readonly StructuredGenerat
[
{ modelSubstring: "haiku" },
{ modelSubstring: "gpt-5.4-mini", thinkingOptionId: "low" },
{ modelSubstring: "minimax-m2.5" },
{ modelSubstring: "minimax-m3" },
{ modelSubstring: "nemotron-3-super" },
] as const;

2
public-docs/metadata-generation.md
View File

@@ -29,7 +29,7 @@ The candidate list is assembled in this order:
2. **Built-in defaults**, matched against the models of the providers you have enabled:
1. a `haiku` model
2. `gpt-5.4-mini` (low reasoning)
3. `minimax-m2.5`
3. `minimax-m3`
4. `nemotron-3-super`
3. **The model currently selected** for that agent or draft, as a last resort.