What's Changed
-
docs(providers): document Wally under OpenAI-compatible providers by @sanchitmonga22 in https://github.com/QwenLM/qwen-code/pull/16529
-
fix(core): share one gh runner and name an unusable view directory by @wenshao in https://github.com/QwenLM/qwen-code/pull/16545
-
fix(telemetry): report OpenAI cache_write_tokens as cache creation by @2SinceJuly in https://github.com/QwenLM/qwen-code/pull/16454
-
feat(core): name the active shell in the startup context by @2SinceJuly in https://github.com/QwenLM/qwen-code/pull/16491
-
docs(daemon): document session-scoped permission vote for channel auto-approve by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/16541
-
test(cli): stop a flaky A2A approval poll from failing the whole shard by @wenshao in https://github.com/QwenLM/qwen-code/pull/16555
-
fix(ci): route external PR CI directly to disposable runners by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/16551
-
feat(qqbot): add opt-in forwardBotMessages for bot-authored messages by @Eric-GoodBoy-Tech in https://github.com/QwenLM/qwen-code/pull/15904
-
fix(channels): skip memory extraction and follow-up suggestions on channel turns by @wenshao in https://github.com/QwenLM/qwen-code/pull/16565
-
fix(ci): report timed-out main CI runs instead of letting cancelled hide them by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/16280
-
fix(web-shell): refresh standalone sessions after allocation by @ZedingZhang in https://github.com/QwenLM/qwen-code/pull/15311
-
fix(batch): report provider-specific output budgets in readiness checks by @Jun516 in https://github.com/QwenLM/qwen-code/pull/15181
-
fix(core): share compression cache for equivalent model selectors by @xxwtiancai in https://github.com/QwenLM/qwen-code/pull/15318
-
fix(desktop): restore saved web previews by @zonemeen in https://github.com/QwenLM/qwen-code/pull/14597
-
fix(managed-agent): create a never-attached Session for its first automation verb (#14548) by @xxwtiancai in https://github.com/QwenLM/qwen-code/pull/14561
-
fix(memory): report why a background memory agent stopped by @everyoneexe in https://github.com/QwenLM/qwen-code/pull/13466
-
fix(web-shell): do not persist rejected daemon URL credentials by @lorenzozanee in https://github.com/QwenLM/qwen-code/pull/12285
-
fix(core): base web terminal backpressure on pending input by @dakjdakd in https://github.com/QwenLM/qwen-code/pull/14313
-
fix(cli): emit headless results before draining memory by @xxwtiancai in https://github.com/QwenLM/qwen-code/pull/13885
-
fix(lsp): Attribute diagnostics to explicit extension owners by @loglapa in https://github.com/QwenLM/qwen-code/pull/14117
-
fix(cli): settle Live call stops after failure by @GoldArowana in https://github.com/QwenLM/qwen-code/pull/13835
-
fix(cli): remove dead REPLACE mergeStrategy declarations for modelProviders and providerProtocol by @liwenjie200543 in https://github.com/QwenLM/qwen-code/pull/12613
-
fix(ci): run the failure patrol on ECS and time its sandbox image pull separately by @wenshao in https://github.com/QwenLM/qwen-code/pull/16462
-
refactor(serve): share the prompt admission with in-process callers by @wenshao in https://github.com/QwenLM/qwen-code/pull/16543
-
fix(managed-agent): let --check read the configuration the server reads by @wenshao in https://github.com/QwenLM/qwen-code/pull/16364
-
fix(ci): keep sdk-java resolver bookkeeping and in-house jars out of the host cache (#15281) by @qwen-code-dev-bot in https://github.com/QwenLM/qwen-code/pull/15286
-
fix(web-shell): narrow sidebarless live-state polling to displayed workspaces by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/16550
-
fix(cli): warn about Node 24/25 Wasm memory spikes without disabling AST checks by @Willam2004 in https://github.com/QwenLM/qwen-code/pull/15321
-
feat(agents): make default background execution configurable by @ZedingZhang in https://github.com/QwenLM/qwen-code/pull/15178
-
fix(extension): persist CDP reconnect backoff across service worker restarts by @he-yufeng in https://github.com/QwenLM/qwen-code/pull/14022
-
feat(cli): enable LSP through a user-scoped setting and env pair by @BigDaddy1337 in https://github.com/QwenLM/qwen-code/pull/14613
-
fix(web-shell): isolate mixed-direction Markdown text by @hahahahahayesyeseys in https://github.com/QwenLM/qwen-code/pull/14035
-
docs(tools): add You.com free MCP to the web search MCP services by @brainsparker in https://github.com/QwenLM/qwen-code/pull/14000
-
fix(review): refuse the findings artifact by name and print the expected schema by @ZedingZhang in https://github.com/QwenLM/qwen-code/pull/14824
-
fix(sdk-typescript): clamp an overflowing session-spawn deadline to the timer ceiling by @Bug-killer-prog in https://github.com/QwenLM/qwen-code/pull/14676
-
fix(web-shell): route standalone reloads by session source type by @cactuser-Lu in https://github.com/QwenLM/qwen-code/pull/12384
-
fix(ci): harden the already-published desktop probe by @lorenzozanee in https://github.com/QwenLM/qwen-code/pull/12184
-
fix(web-shell): remove productScope gating on managed provider capabilities by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/16554
-
docs(channels): document self-pushed head echoes and scope their suppression by @wenshao in https://github.com/QwenLM/qwen-code/pull/16577
-
docs(design): propose idle parking for resident Hosted Sessions by @wenshao in https://github.com/QwenLM/qwen-code/pull/16564
-
fix(managed-agent): prove A3 rewritten command recovery without Hook rerun by @wenshao in https://github.com/QwenLM/qwen-code/pull/16116
-
feat(channels): give bound sessions role guidance without operator templates by @wenshao in https://github.com/QwenLM/qwen-code/pull/16576
-
ci: raise the ephemeral runner slot cap to 64 per host by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/16591