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

Merge origin/main into model runtime changes

Browse Source
This commit is contained in:
Mario Zechner
2026-07-15 13:00:45 +02:00
parent bd9e09db44 dcfe36c797
commit 5e336cfa80
26 changed files with 244 additions and 163 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/ai/CHANGELOG.md
+23 -7
View File
@@ -9,7 +9,6 @@
- Renamed the canonical login interaction interface from `AuthLoginCallbacks` to `AuthInteraction`; it exposes the provider-neutral `prompt()`/`notify()` protocol used by API-key and OAuth flows.
- Changed the `Models` request contract: `getAuth(model)` now includes model headers, while `getAuth(providerId)` remains provider-scoped, and Models stream options may include `transformHeaders`. Custom `Models` implementations must execute the transform after merging auth/model and explicit headers, then remove it before provider dispatch.
- Changed dynamic model refresh to `Models.refresh(options)`, which refreshes every configured dynamic provider and returns per-provider errors/cancellation state. `Provider.refreshModels(context)` now receives the effective credential, scoped model storage, network policy, and abort signal.
- Removed the `OpenAIResponsesCompat.sendSessionIdHeader` flag. Session-affinity behavior is now controlled by `compat.sessionAffinityFormat` (`"openai"`, `"openai-nosession"`, or `"openrouter"`). Replace `sendSessionIdHeader: false` with `sessionAffinityFormat: "openai-nosession"` ([#6366](https://github.com/earendil-works/pi/issues/6366)).
### Added
@@ -18,10 +17,6 @@
- Added neutral auth-flow information/link events and provider-owned Amazon Bedrock and Google Vertex AI credential selection flows.
- Added `ModelsStore` with an in-memory default for restoring and persisting dynamic provider catalogs.
- Added the dynamic Radius `pi-messages` gateway provider with OAuth and credential-specific catalog refresh.
- Added cache-friendly dynamic tool loading. `ToolResultMessage.addedToolNames` marks where tools from `Context.tools` became available; Anthropic and OpenAI Responses use native deferred loading so late tools stay out of the cached prefix, while other providers continue using `Context.tools` normally ([#6474](https://github.com/earendil-works/pi-mono/pull/6474)).
- Added native `xhigh` and `max` thinking levels for Claude Fable 5 across all generated provider catalogs ([#6490](https://github.com/earendil-works/pi-mono/pull/6490) by [@davidbrai](https://github.com/davidbrai)).
- Added `toolChoice` support to OpenAI Codex Responses, including `"required"` to force a tool call.
- Added `toolChoice` support to OpenAI Responses, including required and named tool selection.
### Changed
@@ -31,10 +26,31 @@
- Fixed Cloudflare Workers AI and AI Gateway streams to materialize account and gateway endpoint placeholders after auth resolution, including compat streaming with custom model objects.
- Fixed lazy provider streams to preserve their final assistant message when forwarding an inner stream.
## [0.80.7] - 2026-07-14
### Breaking Changes
- Removed the `OpenAIResponsesCompat.sendSessionIdHeader` flag. Session-affinity behavior is now controlled by `compat.sessionAffinityFormat` (`"openai"`, `"openai-nosession"`, or `"openrouter"`). Replace `sendSessionIdHeader: false` with `sessionAffinityFormat: "openai-nosession"` ([#6496](https://github.com/earendil-works/pi-mono/pull/6496) by [@petrroll](https://github.com/petrroll)).
### Added
- Added cache-friendly dynamic tool loading. `ToolResultMessage.addedToolNames` marks where tools from `Context.tools` became available; Anthropic and OpenAI Responses use native deferred loading so late tools stay out of the cached prefix, while other providers continue using `Context.tools` normally ([#6474](https://github.com/earendil-works/pi-mono/pull/6474)).
- Added native `xhigh` and `max` thinking levels for Claude Fable 5 across all generated provider catalogs ([#6490](https://github.com/earendil-works/pi-mono/pull/6490) by [@davidbrai](https://github.com/davidbrai)).
- Added `toolChoice` support to OpenAI and Codex Responses, including required and named tool selection ([#6588](https://github.com/earendil-works/pi-mono/pull/6588) by [@xl0](https://github.com/xl0)).
### Fixed
- Fixed OpenRouter model context windows to use the top provider's actual context length ([#6481](https://github.com/earendil-works/pi-mono/pull/6481) by [@davidbrai](https://github.com/davidbrai)).
- Fixed the GitHub Copilot `mai-code-1-flash-picker` model to route through the `/responses` endpoint.
- Fixed the GitHub Copilot `mai-code-1-flash-picker` model to route through the `/responses` endpoint ([#6544](https://github.com/earendil-works/pi-mono/pull/6544) by [@petrroll](https://github.com/petrroll)).
- Fixed Amazon Bedrock requests to use the generic `apiKey` stream option as a Bedrock bearer token.
- Fixed OpenRouter OpenAI-compatible session IDs to use the `x-session-id` header instead of OpenAI-specific session-affinity fields ([#6366](https://github.com/earendil-works/pi/issues/6366)).
- Fixed OpenRouter OpenAI-compatible session IDs to use the `x-session-id` header instead of OpenAI-specific session-affinity fields ([#6496](https://github.com/earendil-works/pi-mono/pull/6496) by [@petrroll](https://github.com/petrroll)).
- Fixed Amazon Bedrock ambient AWS credentials to keep using SigV4 authentication, including for custom model IDs ([#6532](https://github.com/earendil-works/pi-mono/pull/6532) by [@ribelo](https://github.com/ribelo)).
- Fixed Cloudflare Workers AI and AI Gateway authentication to use ambient account and gateway IDs when stored credentials contain only an API key ([#6292](https://github.com/earendil-works/pi-mono/pull/6292) by [@markphelps](https://github.com/markphelps)).
- Fixed Amazon Bedrock errors to report unhandled provider stop reasons instead of only `An unknown error occurred` ([#6598](https://github.com/earendil-works/pi-mono/pull/6598) by [@davidbrai](https://github.com/davidbrai)).
- Fixed Azure OpenAI Responses reasoning replay when `encrypted_content` appears only in the terminal response event ([#6608](https://github.com/earendil-works/pi-mono/pull/6608) by [@davidbrai](https://github.com/davidbrai)).
- Fixed Anthropic-compatible proxies that omit `usage` from `message_delta` events ([#6611](https://github.com/earendil-works/pi-mono/pull/6611) by [@davidbrai](https://github.com/davidbrai)).
- Fixed OpenCode OpenAI Responses models to omit the unsupported `session-id` header while preserving other cache-affinity data ([#6645](https://github.com/earendil-works/pi-mono/pull/6645) by [@davidbrai](https://github.com/davidbrai)).
## [0.80.6] - 2026-07-09
packages/ai/package.json
+1 -1
View File
@@ -1,6 +1,6 @@
{
"name": "@earendil-works/pi-ai",
"version": "0.80.6",
"version": "0.80.7",
"description": "Unified LLM API with automatic model discovery and provider configuration",
"type": "module",
"main": "./dist/index.js",
packages/ai/src/api/openai-codex-responses.ts
+3 -2
View File
@@ -258,8 +258,9 @@ export const stream: StreamFunction<"openai-codex-responses", OpenAICodexRespons
if (nextBody !== undefined) {
body = nextBody as RequestBody;
}
const websocketRequestId = options?.sessionId || createCodexRequestId();
const sseHeaders = buildSSEHeaders(model.headers, options?.headers, accountId, apiKey, options?.sessionId);
const codexSessionId = clampOpenAIPromptCacheKey(options?.sessionId);
const websocketRequestId = codexSessionId || createCodexRequestId();
const sseHeaders = buildSSEHeaders(model.headers, options?.headers, accountId, apiKey, codexSessionId);
const websocketHeaders = buildWebSocketHeaders(
model.headers,
options?.headers,
packages/ai/src/providers/openrouter.models.ts
+57 -75
View File
@@ -462,24 +462,6 @@ export const OPENROUTER_MODELS = {
contextWindow: 262144,
maxTokens: 80000,
} satisfies Model<"openai-completions">,
"arcee-ai/trinity-mini": {
id: "arcee-ai/trinity-mini",
name: "Arcee AI: Trinity Mini",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
reasoning: true,
input: ["text"],
cost: {
input: 0.045,
output: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"arcee-ai/virtuoso-large": {
id: "arcee-ai/virtuoso-large",
name: "Arcee AI: Virtuoso Large",
@@ -688,8 +670,8 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.21,
output: 0.79,
input: 0.25,
output: 0.95,
cacheRead: 0.13,
cacheWrite: 0,
},
@@ -1122,13 +1104,13 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.12,
input: 0.06,
output: 0.35,
cacheRead: 0.09,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
maxTokens: 8192,
} satisfies Model<"openai-completions">,
"google/gemma-4-31b-it:free": {
id: "google/gemma-4-31b-it:free",
@@ -1146,7 +1128,7 @@ export const OPENROUTER_MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 8192,
maxTokens: 32768,
} satisfies Model<"openai-completions">,
"ibm-granite/granite-4.1-8b": {
id: "ibm-granite/granite-4.1-8b",
@@ -1239,6 +1221,24 @@ export const OPENROUTER_MODELS = {
contextWindow: 262144,
maxTokens: 65536,
} satisfies Model<"openai-completions">,
"kwaipilot/kat-coder-air-v2.5": {
id: "kwaipilot/kat-coder-air-v2.5",
name: "Kwaipilot: KAT-Coder-Air V2.5",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
reasoning: false,
input: ["text"],
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0.03,
cacheWrite: 0,
},
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"openai-completions">,
"kwaipilot/kat-coder-pro-v2": {
id: "kwaipilot/kat-coder-pro-v2",
name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -1257,23 +1257,23 @@ export const OPENROUTER_MODELS = {
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"openai-completions">,
"liquid/lfm-2.5-1.2b-thinking:free": {
id: "liquid/lfm-2.5-1.2b-thinking:free",
name: "LiquidAI: LFM2.5-1.2B-Thinking (free)",
"kwaipilot/kat-coder-pro-v2.5": {
id: "kwaipilot/kat-coder-pro-v2.5",
name: "Kwaipilot: KAT-Coder-Pro V2.5",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
compat: {"supportsDeveloperRole":false,"thinkingFormat":"openrouter"},
reasoning: true,
reasoning: false,
input: ["text"],
cost: {
input: 0,
output: 0,
cacheRead: 0,
input: 0.74,
output: 2.96,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 32768,
maxTokens: 4096,
contextWindow: 256000,
maxTokens: 80000,
} satisfies Model<"openai-completions">,
"meta-llama/llama-3.1-70b-instruct": {
id: "meta-llama/llama-3.1-70b-instruct",
@@ -1357,8 +1357,8 @@ export const OPENROUTER_MODELS = {
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.15,
output: 0.6,
input: 0.2,
output: 0.8,
cacheRead: 0,
cacheWrite: 0,
},
@@ -1866,7 +1866,7 @@ export const OPENROUTER_MODELS = {
cacheRead: 0.07,
cacheWrite: 0,
},
contextWindow: 256000,
contextWindow: 262144,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"moonshotai/kimi-k2.6": {
@@ -1897,9 +1897,9 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.72,
input: 0.719,
output: 3.49,
cacheRead: 0.159,
cacheRead: 0.149,
cacheWrite: 0,
},
contextWindow: 262144,
@@ -2457,11 +2457,11 @@ export const OPENROUTER_MODELS = {
cost: {
input: 0.05,
output: 0.4,
cacheRead: 0.01,
cacheRead: 0.005,
cacheWrite: 0,
},
contextWindow: 400000,
maxTokens: 4096,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"openai/gpt-5-pro": {
id: "openai/gpt-5-pro",
@@ -2493,7 +2493,7 @@ export const OPENROUTER_MODELS = {
cost: {
input: 1.25,
output: 10,
cacheRead: 0.13,
cacheRead: 0.125,
cacheWrite: 0,
},
contextWindow: 400000,
@@ -2977,26 +2977,8 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.036,
output: 0.18,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 131072,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"openai/gpt-oss-120b:free": {
id: "openai/gpt-oss-120b:free",
name: "OpenAI: gpt-oss-120b (free)",
api: "openai-completions",
provider: "openrouter",
baseUrl: "https://openrouter.ai/api/v1",
compat: {"thinkingFormat":"openrouter"},
reasoning: true,
input: ["text"],
cost: {
input: 0,
output: 0,
input: 0.03,
output: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
@@ -3482,7 +3464,7 @@ export const OPENROUTER_MODELS = {
input: ["text"],
cost: {
input: 0.09,
output: 0.1,
output: 0.55,
cacheRead: 0,
cacheWrite: 0,
},
@@ -4075,13 +4057,13 @@ export const OPENROUTER_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.285,
input: 0.289,
output: 2.4,
cacheRead: 0.15,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 262140,
maxTokens: 262140,
contextWindow: 131072,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"qwen/qwen3.6-35b-a3b": {
id: "qwen/qwen3.6-35b-a3b",
@@ -4476,7 +4458,7 @@ export const OPENROUTER_MODELS = {
cacheRead: 0.028,
cacheWrite: 0,
},
contextWindow: 32000,
contextWindow: 262144,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"xiaomi/mimo-v2.5-pro": {
@@ -4562,12 +4544,12 @@ export const OPENROUTER_MODELS = {
input: ["text"],
cost: {
input: 0.43,
output: 1.74,
output: 1.75,
cacheRead: 0.08,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 131072,
contextWindow: 198000,
maxTokens: 16384,
} satisfies Model<"openai-completions">,
"z-ai/glm-4.6v": {
id: "z-ai/glm-4.6v",
@@ -4638,8 +4620,8 @@ export const OPENROUTER_MODELS = {
cacheRead: 0.119,
cacheWrite: 0,
},
contextWindow: 202752,
maxTokens: 4096,
contextWindow: 198000,
maxTokens: 128000,
} satisfies Model<"openai-completions">,
"z-ai/glm-5-turbo": {
id: "z-ai/glm-5-turbo",
@@ -4688,9 +4670,9 @@ export const OPENROUTER_MODELS = {
thinkingLevelMap: {"xhigh":"xhigh"},
input: ["text"],
cost: {
input: 0.84,
output: 2.64,
cacheRead: 0.156,
input: 0.924,
output: 2.904,
cacheRead: 0.1716,
cacheWrite: 0,
},
contextWindow: 1024000,
packages/ai/test/openai-codex-stream.test.ts
+48
View File
@@ -640,6 +640,54 @@ describe("openai-codex streaming", () => {
expect(capturedPayload?.prompt_cache_key).toBe("x".repeat(64));
});
it("clamps Codex session-id header to 64 characters", async () => {
const token = mockToken();
const sessionId = "x".repeat(67);
let capturedHeaders: Headers | undefined;
const encoder = new TextEncoder();
vi.stubGlobal(
"fetch",
vi.fn(async (_input: string | URL, init?: RequestInit) => {
capturedHeaders = init?.headers instanceof Headers ? init.headers : undefined;
return new Response(
new ReadableStream<Uint8Array>({
start(controller) {
controller.enqueue(encoder.encode(buildSSEPayload({ status: "completed" })));
controller.close();
},
}),
{ status: 200, headers: { "content-type": "text/event-stream" } },
);
}),
);
const model: Model<"openai-codex-responses"> = {
id: "gpt-5.1-codex",
name: "GPT-5.1 Codex",
api: "openai-codex-responses",
provider: "openai-codex",
baseUrl: "https://chatgpt.com/backend-api",
reasoning: true,
input: ["text"],
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
contextWindow: 400000,
maxTokens: 128000,
};
const context: Context = {
systemPrompt: "You are a helpful assistant.",
messages: [{ role: "user", content: "Say hello", timestamp: Date.now() }],
};
await streamOpenAICodexResponses(model, context, {
apiKey: token,
transport: "sse",
sessionId,
}).result();
expect(capturedHeaders?.get("session-id")).toBe("x".repeat(64));
expect(capturedHeaders?.get("x-client-request-id")).toBe("x".repeat(64));
});
it("preserves gpt-5.5 xhigh reasoning effort from simple options", async () => {
const tempDir = mkdtempSync(join(tmpdir(), "pi-codex-stream-"));
process.env.PI_CODING_AGENT_DIR = tempDir;