ton/pi_harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ai): add max thinking level

Browse Source
This commit is contained in:
Mario Zechner
2026-07-09 22:30:53 +02:00
parent 8973ae28ab
commit fbdd46389c
61 changed files with 441 additions and 168 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/README.md
+4 -2
View File
@@ -730,7 +730,7 @@ if (model.reasoning) {
const response = await models.completeSimple(model, {
messages: [{ role: 'user', content: 'Solve: 2x + 5 = 13', timestamp: Date.now() }]
}, {
reasoning: 'medium' // 'minimal' | 'low' | 'medium' | 'high' | 'xhigh'
reasoning: 'medium' // 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max'
});
// Access thinking and text blocks
@@ -743,6 +743,8 @@ for (const block of response.content) {
}
```
`xhigh` and `max` are model-specific, opt-in levels. Use `getSupportedThinkingLevels(model)` to determine whether a concrete model exposes either level; models such as GPT-5.6 can expose both.
### Provider-Specific Options (stream/complete)
`models.stream()`/`complete()` accept the owning API's full option set. Use `hasApi()` to narrow a dynamically looked-up model to its API for full option typing:
@@ -999,7 +1001,7 @@ Custom models can carry `headers` (e.g. proxies behind bot detection) and `compa
Some OpenAI-compatible servers do not understand the `developer` role used for reasoning-capable models. For those providers, set `compat.supportsDeveloperRole` to `false` so the system prompt is sent as a `system` message instead. If the server also does not support `reasoning_effort`, set `compat.supportsReasoningEffort` to `false` too. This commonly applies to Ollama, vLLM, SGLang, and similar OpenAI-compatible servers.
Use model-level `thinkingLevelMap` to describe model-specific thinking controls. Keys are pi thinking levels (`off`, `minimal`, `low`, `medium`, `high`, `xhigh`). Missing keys use provider defaults, string values are sent to the provider, and `null` marks a level unsupported.
Use model-level `thinkingLevelMap` to describe model-specific thinking controls. Keys are pi thinking levels (`off`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max`). Missing standard levels through `high` use provider defaults; `xhigh` and `max` are opt-in and require a non-null map entry. String values are sent to the provider, `null` marks a level unsupported, and maps may skip levels.
```typescript
const ollamaReasoningModel: Model<'openai-completions'> = {