1.5.1: refined office, chat in the app language, current OpenAI models, own connector keys
Build Release Installers / Release for the tag (push) Successful in 16s
Build Release Installers / Windows installer (NSIS x64) (push) Successful in 1m48s
Build Release Installers / Linux packages (AppImage + deb x64) (push) Successful in 2m21s
CI / Typecheck, lint, tests, e2e (push) Successful in 3m52s
Build Release Installers / macOS installers (dmg + zip, x64 + arm64) (push) Successful in 7m15s

- Home: the goal title box is two line boxes tall (2.8em), so a third line no longer peeks out.
- Chat messages, reply fallbacks and assignment DMs follow the app display language; tasks and documents keep the working language.
- OpenAI and GPT-account model lists match OpenAI's current line-up; default gpt-6.1-sol.
- Onboarding connectors step takes the operator's Composio and logo.dev keys, then lists the toolkits the Composio project enables; without a key Connectors leaves the sidebar.
- Google Antigravity removed end to end (migration 111), with the remote-revocation path only it used.
- Office: 2x pixel people with outlines, rim light, walk, typing and blink; dithered real-clock lighting; detailed furniture and floors.
- Per-agent model picker lists the provider's whole model list, live when connected.
- Chat wake context breaks same-millisecond ties by insertion order; the mid-run inbox dedupes by message id.
- The stored "clock" theme reads back instead of falling to "system".

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
ZacharyZhang-NYandClaude Opus 5.5 committed 2026-10-09 21:12:19 -04:00
1 parent 48dfddffef
commit 245ff66336
79 files changed
+1301 -1035

No files matched your search

+2 -4
View File
@@ -5,7 +5,7 @@ import { accumulateResponsesStream, parseResponsesOutput, toResponsesInput } fro
import { accumulateChatStream, parseChatChoice, toChatMessages } from "../../src/main/services/provider-tool-turns/chat-format";
import { parseAnthropicContent, toAnthropicMessages } from "../../src/main/services/provider-tool-turns/anthropic-format";
import { parseBedrockOutput, toBedrockMessages } from "../../src/main/services/provider-tool-turns/bedrock-format";
import { accumulateGeminiStream, parseGeminiResponse, vertexRequestBody } from "../../src/main/services/provider-tool-turns/gemini-format";
import { parseGeminiResponse, vertexRequestBody } from "../../src/main/services/provider-tool-turns/gemini-format";
async function* stream(items: JsonRecord[]): AsyncIterable<ProviderEventStreamMessage> {
for (const data of items) yield { eventName: null, data, rawData: JSON.stringify(data) };
@@ -53,10 +53,8 @@ describe("reasoning survives tool turns", () => {
test("Gemini: thought signatures on parts go back, streamed or not", async () => {
const parts = [{ text: "plan", thought: true }, { functionCall: { name: "f", args: {} }, thoughtSignature: "SIG" }];
const vertex = vertexRequestBody({ model: "gemini-3-pro", instructions: null, messages: after(parseGeminiResponse({ candidates: [{ content: { parts }, finishReason: "STOP" }] })), tools: [] });
const vertex = vertexRequestBody({ instructions: null, messages: after(parseGeminiResponse({ candidates: [{ content: { parts }, finishReason: "STOP" }] })), tools: [] });
expect((vertex.contents as JsonRecord[])[1]).toEqual({ role: "model", parts });
const streamed = await accumulateGeminiStream(stream([...parts.map((part) => ({ response: { candidates: [{ content: { parts: [part] } }] } })), { response: { candidates: [{ finishReason: "STOP" }] } }]));
expect(streamed.replay).toEqual({ format: "gemini", content: parts });
});
test("Chat: streamed reasoning goes back under the field it came in, and OpenRouter details are merged into whole entries", async () => {