api_retry heartbeats already reach the desktop status bar, but the
streaming-to-non-streaming fallback had no signal at all: the CLI only
flipped an internal flag, and the one-shot fallback response can take
minutes with zero incremental output, so the UI showed a bare spinner
the whole time.
- CLI: yield a {type:'system', subtype:'streaming_fallback', cause}
message at both fallback sites (stream error/watchdog and 404 stream
creation), mirroring the existing api_error -> api_retry path through
query.ts passthrough, QueryEngine SDK output, and the SDK schema.
- Server: translate it to a streaming_fallback ServerMessage;
unrecognized causes normalize to 'unknown' instead of dropping the
event.
- Desktop: track it as active-turn state (cleared at the same 12 sites
as apiRetry; a fallback notice supersedes the stale retry banner) and
render a neutral pill with the turn timer - expected state, not an
error, so no amber styling and nothing in the diagnostics panel.
- Retry banner now shows "retrying now" once the countdown elapses
instead of sticking at "waiting 0s".
With 62241a31 disabling the non-streaming fallback for desktop CLI
sessions, this notice mainly covers the 404 gateway path (which skips
the disable check), callers that re-enable fallback via env, and
non-desktop SDK consumers.
Constraint: Retries and fallbacks are expected states per the
diagnostics severity standard - lightweight active-turn UI only, no
error-panel entries, no transcript persistence.
Tested: bun test src/server/__tests__/ws-memory-events.test.ts
Tested: bun run check:server
Tested: cd desktop && bun run test -- --run
Tested: cd desktop && bun run lint
Not-tested: live provider outage reproduction; verified via unit
coverage of the translation, store lifecycle, and indicator rendering.
Strip the rotating billing attribution line before converting system
prompts to OpenAI Chat/Responses requests, forward a stable
prompt_cache_key derived from the client session, request stream usage
explicitly on Chat streams, and map cached_tokens back to Anthropic
cache_read_input_tokens with exclusive input accounting.
Add historical tool and skill aggregation to activity stats, compact the token summary, and show Codex-style activity insights with plugin/skill ranking.
Tested: bun test src/utils/__tests__/stats.test.ts
Tested: bun run check:persistence-upgrade
Tested: bun run check:desktop
Not-tested: bun run check:server (previous full run exposed unrelated conversations WebSocket timeouts; focused stats and persistence checks passed)
Confidence: medium
Scope-risk: moderate
Mapped Windows drives can resolve to UNC paths before the CLI starts. Treat the UNC prefix as safe only after the target has already been proven to be inside the allowed working directory, while keeping sensitive paths and out-of-workspace UNC writes behind safety checks.
Tested: bun test src\\utils\\permissions\\filesystem.test.ts
Tested: real local app server/WebSocket session with deepseek-v4-pro and --dangerously-skip-permissions wrote through X:\\project without a permission_request.
Not-tested: full check:server is still red on this Windows checkout due pre-existing unrelated failures in shell env, H5/local-file, MCP, FileRead CJK, and a darwin-only expectation.
Confidence: high
Scope-risk: narrow
Git writes upstream branch config when a worktree starts from origin/main. Use the already-resolved base SHA as the worktree start point so parallel agent worktrees do not race on shared .git/config.
Tested: bun test src/utils/__tests__/worktree.test.ts
Tested: real gpt-5.5 Sub2API run with four worktree-isolated agents
Not-tested: bun run check:server currently fails unrelated WebSocket restart/timeouts
Confidence: high
Scope-risk: narrow
/agent should behave like a normal session prompt that tells the main model to use the selected Agent tool. The previous forked command path buffered the subagent run behind local command output and forced desktop clients to wait for command completion instead of seeing the normal Agent interaction stream.
Constraint: Desktop /agent must preserve ordinary chat/session semantics and still require /agent <agent> <prompt>.
Rejected: Keep slash_agent SDK event bridging | it preserves the separate forked execution path instead of fixing the product flow.
Confidence: high
Scope-risk: moderate
Directive: Do not move /agent back to context: fork without proving the desktop normal Agent tool stream still works.
Tested: bun test src/commands/agent.test.ts src/utils/processUserInput/processSlashCommand.test.ts src/server/__tests__/ws-memory-events.test.ts
Tested: cd desktop && bun run test -- --run src/stores/chatStore.test.ts src/components/chat/MessageList.test.tsx
Tested: git diff --check
Not-tested: bun run check:server is blocked before source checks by expired quarantine entries: server:cron-scheduler, server:providers-real, server:tasks, server:e2e:business-flow, server:e2e:full-flow
The desktop /agent slash path runs before the normal query loop, so the old implementation waited for the forked command to finish and only surfaced the final local-command stdout. Emit foreground slash-agent task events from /agent, drain SDK events while QueryEngine waits for pre-query slash processing, and allow those current-turn events through the WebSocket pre-send mute gate.
Constraint: /agent is a forked slash command that does not produce ordinary assistant deltas until its final stdout is synthesized.
Rejected: Frontend-only loading state | would not expose real forked-agent progress or tool/tool-result updates.
Confidence: high
Scope-risk: moderate
Directive: Keep slash_agent task events scoped to /agent; ordinary slash command stdout and /goal event handling should remain on the existing local-command paths.
Tested: bun test src/QueryEngine.test.ts src/utils/processUserInput/processSlashCommand.test.ts src/server/__tests__/ws-memory-events.test.ts
Tested: cd desktop && bun run test -- --run src/stores/chatStore.test.ts src/components/chat/MessageList.test.tsx
Not-tested: bun run check:server is blocked by expired quarantine review entries: server:cron-scheduler, server:providers-real, server:tasks, server:e2e:business-flow, server:e2e:full-flow
Desktop title generation previously upgraded the first sidebar title from the raw user prompt before assistant output existed. That made image-plus-text sessions vulnerable to keeping a title based only on the user's initial wording. This moves polished title generation to completed turns, reuses the CLI title prompt and transcript extractor, and routes title calls through the configured haiku model with a retry when disabled thinking is rejected.
Constraint: The first user message still needs an immediate placeholder title so the sidebar is responsive.
Rejected: Generate the AI title before assistant output | image-derived context is only available after the assistant turn completes.
Confidence: high
Scope-risk: moderate
Directive: Keep polished automatic titles tied to completed transcript turns, not pre-response user prompts.
Tested: bun test src/server/__tests__/title-service.test.ts
Tested: bun test src/server/__tests__/conversations.test.ts -t "refreshes the first-turn AI title"
Tested: git diff --check
Tested: Real MiniMax-M3 /tmp session f89073ed-3467-492a-b63c-e1886c146a3a with image attachment wrote ai-title "Validate session title generation"
Not-tested: bun run check:server is blocked by existing expired quarantine manifest entries
MiniMax's official M3 model page and release notes describe M3 as supporting up to a 1M-token context window with a guaranteed minimum of 512K. Keep the built-in MiniMax preset aligned with that official default instead of inheriting the older 204.8K MiniMax generation limit.
Constraint: Official MiniMax M3 docs state the M3 API supports up to 1M tokens context window.
Rejected: Keep 204800 and rely on manual provider overrides | that makes the built-in MiniMax preset wrong for new users.
Confidence: high
Scope-risk: narrow
Directive: Do not copy MiniMax-M2.7's 204.8K window onto MiniMax-M3 without re-checking official M3 docs.
Related: https://www.minimax.io/models/text/m3
Related: https://www.minimax.io/blog/minimax-m3
Tested: git diff --check
Tested: bun test src/server/__tests__/provider-presets.test.ts src/server/__tests__/providers-real.test.ts src/server/__tests__/provider-runtime-env.test.ts src/server/__tests__/providers.test.ts src/utils/__tests__/context.test.ts
Not-tested: bun run check:server blocked before execution by expired quarantine entries: server:cron-scheduler, server:providers-real, server:tasks, server:e2e:business-flow, server:e2e:full-flow
Desktop chat can fall back to persisted transcript estimates when live inspection context is unavailable. That path previously only used built-in model windows, so custom provider settings such as MiniMax-M3 with a 1,000,000-token window still displayed the default 200,000-token estimate. Resolve transcript context windows from the session or active provider runtime env first, then fall back to built-ins.
Constraint: Provider model context windows are stored in provider runtime env, not always in the server process env.
Rejected: Change the built-in MiniMax-M3 window to 1,000,000 | upstream preset correctly keeps MiniMax-M3 at 204,800 by default, while user overrides must remain provider-specific.
Confidence: high
Scope-risk: moderate
Directive: Keep transcript estimates aligned with session/provider runtime env before consulting built-in model defaults.
Tested: git diff --check
Tested: bun test src/server/__tests__/conversations.test.ts --test-name-pattern "active provider model context windows|Sonnet 4.6 transcript usage|low-trust media"
Tested: bun test src/server/__tests__/provider-presets.test.ts src/server/__tests__/provider-runtime-env.test.ts src/server/__tests__/providers.test.ts src/utils/__tests__/context.test.ts src/utils/__tests__/contextBudget.test.ts
Tested: bun test src/server/__tests__/conversations.test.ts src/server/__tests__/conversation-service.test.ts src/server/__tests__/providers.test.ts src/server/__tests__/provider-presets.test.ts src/server/__tests__/provider-runtime-env.test.ts src/utils/__tests__/context.test.ts src/utils/__tests__/contextBudget.test.ts
Not-tested: bun run check:server blocked before execution by expired quarantine entries: server:cron-scheduler, server:providers-real, server:tasks, server:e2e:business-flow, server:e2e:full-flow
Remote main includes PR #694, which updates the MiniMax preset to MiniMax-M3 and removes deprecated built-in MiniMax context-window entries. Merge that provider baseline before applying the transcript context-window estimate fix so the local line keeps upstream provider defaults.
Constraint: Remote main advanced independently with PR #694 while local main carried unreleased commits.
Rejected: Reset local main to origin/main | would discard local-only main commits.
Confidence: high
Scope-risk: moderate
Directive: Preserve MiniMax-M3 provider preset changes when touching provider context-window logic.
Tested: bun test src/server/__tests__/conversations.test.ts src/server/__tests__/conversation-service.test.ts src/server/__tests__/providers.test.ts src/server/__tests__/provider-presets.test.ts src/server/__tests__/provider-runtime-env.test.ts src/utils/__tests__/context.test.ts src/utils/__tests__/contextBudget.test.ts
Not-tested: bun run check:server blocked by expired quarantine entries: server:cron-scheduler, server:providers-real, server:tasks, server:e2e:business-flow, server:e2e:full-flow
Add MiniMax-M3 as the new default for the minimax provider preset and
remove deprecated M2.5/M2.1/M2 entries. MiniMax-M2.7 and the highspeed
variant are kept for users who pinned the previous generation.
Updated places:
- providerPresets.json: default models -> M3, modelContextWindows trimmed
- modelContextWindows.ts: built-in window list mirrors the new set
- provider-presets / providers-real / thinking tests updated to assert
the new default
- .env.example and third-party docs (zh + en) recommend M3
- scripts/repro-issue-247-real.ts default model bumped to M3
Co-Authored-By: Octopus <liyuan851277048@icloud.com>
Desktop users need a direct way to pick an installed Agent from slash completion while preserving the existing command and skill namespace. Add /agent <agent> <prompt> as the single execution surface and render active agents as namespaced completion rows.
Constraint: Existing slash command names and ordering must remain authoritative.
Rejected: Register each Agent as a top-level /<agent> command | would collide with built-in commands, skills, and future custom commands.
Confidence: high
Scope-risk: moderate
Tested: bun run verify
Large screenshots were being treated like oversized text payloads,
which pushed readable images through an aggressive resize/compression
path before the model saw them. The image path now preserves images
that already fit API byte and dimension limits, prefers lossless or
high-quality compression when only bytes are too large, and only
downscales by vision pixel budget when the image would exceed the
Read token budget.
Constraint: Fixes pasted/read image failures reported in #615 and #677 while preserving screenshot readability requested in #663
Rejected: Always resize to 2048px | would unnecessarily degrade screenshots that already fit provider limits
Rejected: Continue estimating image budget from base64 text length | image blocks are billed/read as vision pixels, not text payload
Confidence: high
Scope-risk: moderate
Directive: Do not lower fallback JPEG quality or long-edge limits without revalidating real screenshot OCR/vision tasks
Tested: bun test src/utils/__tests__/imageResizer.test.ts src/server/__tests__/conversation-attachments.test.ts
Tested: bun run check:server
Tested: bun run check:coverage (changed-line coverage 95.25%; adapters/desktop coverage lanes failed from existing non-target issues)
Tested: GPT-5.5 Read smoke on 1394x4404, 4096x2304, and 7900x900 images
Not-tested: Real resize/re-encode branch in this source worktree because optional sharp/native image processor is not installed locally
Related: #615
Related: #677
Related: #663
Desktop terminal settings previously only controlled the UI terminal, so Windows sessions could show pwsh while agent PowerShell detection still fell back to Windows PowerShell 5.1. The sidecar now receives a narrow PowerShell-only override and the runtime resolves pwsh through PSHOME and standard Windows paths before falling back.
Fixes#665.
Constraint: Windows terminal shell selection must not make cmd, Git Bash, or arbitrary custom shells drive PowerShellTool execution
Rejected: Reuse the full terminal shell path for agent tools | would couple UI terminal behavior to tool execution and could route non-PowerShell shells into PowerShell detection
Confidence: medium
Scope-risk: moderate
Directive: Keep agent command shell selection narrower than terminal UI shell selection unless the permission/parser model is updated with it
Tested: bun test src/utils/shell/powershellDetection.test.ts; cd desktop/src-tauri && cargo test agent_powershell_override --lib; bun run check:native; bun run check:server; git diff --check
Not-tested: Live Windows desktop smoke with installed pwsh
Related: #665
(cherry picked from commit ecd813b9d2aebfb8d8b6d196170177eec969a6de)
The desktop app can quit while a preview-driven Bash task is still running npm/vite. Bash commands are spawned as detached process groups, so killing only the CLI or shell process can leave descendant dev servers alive and make later app launches look stuck.
This gives the CLI enough shutdown budget to run cleanup, lets the native sidecar wait long enough for that server cleanup, kills detached Bash process groups before the existing tree-kill fallback, and closes the native preview WebView instead of hiding it on workbench unmount.
Constraint: CLI gracefulShutdown has a 5s failsafe, so outer desktop shutdown windows must not SIGKILL it after 2-3s
Rejected: Treat the browser preview as the dev-server owner | it only opens URLs and does not spawn npm/vite
Confidence: high
Scope-risk: moderate
Directive: Do not shorten desktop/server shutdown windows below the CLI cleanup budget without reproducing BashTool background-task teardown
Tested: bun test src/utils/ShellCommand.test.ts src/server/__tests__/conversation-service.test.ts
Tested: cd desktop && bun run test -- --run src/components/browser/BrowserSurface.test.tsx src/components/workbench/WorkbenchPanel.webview.test.tsx
Tested: cd desktop && bun run lint
Tested: bun run check:server
Tested: SKIP_INSTALL=1 ./desktop/scripts/build-macos-arm64.sh
Tested: Opened canonical app and generated DMG app; both showed visible/frontmost window and left no app/sidecar/vite processes after quit
Not-tested: Notarized release install path
Synthetic API errors were carrying only English display text, so desktop chat could not distinguish our compatibility guidance from raw upstream failures and recovery logic depended on those English strings.
Add stable business error codes for media, PDF, request-size, prompt-length, and auto-mode errors. Desktop chat now resolves those codes through locale keys and suppresses the stale English fallback for known business errors, while normalizeMessagesForAPI still supports legacy text matching for old transcripts.
Constraint: Raw upstream provider details must remain available for diagnostics but should not drive localized business UX.
Rejected: Localize src/services/api/errors.ts strings directly | that would make persisted transcript text and media recovery depend on the active UI language.
Confidence: high
Scope-risk: moderate
Directive: Add new user-facing synthetic API errors with businessErrorCode values before localizing their display text.
Tested: bun test src/services/api/errors.test.ts tests/mediaRecoveryAndEstimation.test.ts src/server/__tests__/ws-memory-events.test.ts
Tested: cd desktop && bun run test -- run src/stores/chatStore.test.ts src/components/chat/MessageList.test.tsx
Tested: bun run check:server
Tested: bun run check:desktop
Not-tested: Manual desktop screenshot smoke for the rendered Chinese error card
Unsupported image rejections from text-only compatible providers should not
poison the session, and low-trust multimodal usage spikes should not make
context indicators report a full window.
Constraint: Third-party Anthropic-compatible providers may report encoded media bytes as usage tokens.
Rejected: Trust all provider usage uniformly | third-party media responses can pin context to 100% incorrectly.
Confidence: high
Scope-risk: moderate
Directive: Do not remove the media-aware fallback without checking text-only provider recovery and desktop context indicators.
Tested: bun run check:server
Tested: focused media/context regression suite
Desktop reasoning effort now follows the selected session runtime instead of the General settings surface. Session metadata records provider, model, and effort so reconnects and prewarm restarts preserve the per-session runtime, while the default effort is max for new sessions.
Constraint: Existing transcript and localStorage runtime data must remain readable without a required migration.
Rejected: Keep effort as a General setting | it made one session change leak into every other session.
Confidence: high
Scope-risk: moderate
Directive: Do not reintroduce global desktop effort controls without proving multi-session isolation.
Tested: bun run check:server
Tested: bun run check:desktop
Tested: bun run check:native
Tested: bun run check:policy
Tested: bun run check:coverage
Tested: cd desktop && bun run test -- src/components/controls/ModelSelector.test.tsx src/stores/chatStore.test.ts
Tested: bun test src/server/__tests__/settings.test.ts --test-name-pattern "effort"
Tested: bun test src/server/__tests__/conversations.test.ts --test-name-pattern "runtime"
Not-tested: Live provider smoke for domestic providers without local credentials.
Portable desktop installs can mutate CLAUDE_CONFIG_DIR from an embedded or external CLI while the desktop server is already running. The server skill surface now rereads plugin-related state before listing skills, and /reload-plugins refreshes plugin skills alongside plugin commands so terminal sessions see the same enabled skills without a restart.
Constraint: Portable mode expects CLI, desktop API, and terminal sessions to share the selected CLAUDE_CONFIG_DIR even when writes happen from separate processes
Rejected: Require a desktop restart after plugin install | leaves the portable install workflow stale and contradicts the existing /reload-plugins handoff
Confidence: high
Scope-risk: moderate
Directive: Keep skill discovery and reload summaries counting plugin skills separately from plugin slash commands
Tested: bun test src/server/__tests__/skills.test.ts
Tested: bun test src/server/__tests__/plugins.test.ts
Tested: bun test src/server/__tests__/sessions.test.ts
Tested: bun run check:server
Tested: CLAUDE_CONFIG_DIR=/tmp portable smoke with anthropics/skills, two cwd /api/skills checks, and DeepSeek skill slash-command calls
Tested: bun run quality:gate --mode baseline --allow-live --provider-model deepseek:main:deepseek-main --only provider-smoke:*
Not-tested: Packaged desktop UI visual smoke
Desktop MCP settings were using the process startup directory for local
project config and treated new custom servers as user-global. The desktop
API now carries the active cwd into local MCP reads, writes, and enablement
state, and the settings page exposes the same local/project/user scopes that
the CLI supports.
Constraint: Claude Code MCP scope semantics are local, project, and user.
Constraint: Desktop sessions can switch projects inside one long-lived server process.
Rejected: Only clear getProjectPathForConfig cache | still leaves request-scoped desktop API calls tied to getOriginalCwd
Confidence: high
Scope-risk: moderate
Directive: Do not route MCP local config or disabledMcpServers through ambient original cwd in desktop APIs.
Tested: bun test src/server/__tests__/mcp.test.ts
Tested: cd desktop && bun run test -- mcpSettings.test.tsx
Tested: bun run check:server
Tested: bun run check:desktop
Not-tested: Live provider smoke; the change is config/control-channel scoped.
Desktop portable mode depends on CLI-driven installs using the same filesystem root as the app. The installed terminal launcher now carries CLAUDE_CONFIG_DIR into macOS/Linux shell invocations and uses a Windows cmd wrapper so plugin, skill, and MCP operations do not fall back to the native home config. Moved portable bundles also rebase cached plugin install paths when the cache exists under the current config root.
Constraint: Desktop portable bundles are file-system based and must survive zip/unzip relocation.
Rejected: Copy the sidecar binary directly into user bin | it cannot inject the selected portable config directory for future CLI installs.
Rejected: Rewrite plugin install paths unconditionally | missing cache directories should remain visible as broken state instead of being silently retargeted.
Confidence: high
Scope-risk: moderate
Directive: Keep desktop launcher wrappers as env-carrying sh/cmd files; do not revert to raw sidecar copies without portable install verification.
Tested: bun test src/server/__tests__/desktop-cli-launcher.test.ts src/utils/plugins/installedPluginsManager.test.ts
Tested: cargo test portable --manifest-path desktop/src-tauri/Cargo.toml
Tested: bun run check:server
Tested: bun run check:native
Tested: macOS launcher fixture plus Computer Use Finder verification of portable marker output.
Not-tested: Windows physical desktop execution; Windows wrapper behavior is covered by unit test only.
File browsing and workspace trees were treating every dot-prefixed entry as hidden, which made project files such as .env.example impossible to select through the desktop file surfaces. The fix keeps normal dotfiles and project folders visible while still hiding VCS metadata directories such as .git.
Constraint: VCS internals should stay out of user-facing file trees even when dotfiles are visible
Rejected: Add a UI toggle for hidden files | issue asks for file lists to include dot-prefixed project entries by default
Confidence: high
Scope-risk: narrow
Directive: Do not reintroduce blanket dotfile filtering on filesystem browse, workspace tree, or path completion paths
Tested: bun test src/server/__tests__/filesystem.test.ts src/server/__tests__/workspace-service.test.ts src/utils/suggestions/directoryCompletion.test.ts
Tested: bun run check:server
Not-tested: desktop browser visual smoke
When the model streams `tool_use ... text ... tool_use` interleaved blocks
within one turn (e.g. parallel TaskCreate calls plus a mid-stream
explanation), the previous merge logic preserved the literal stream order
and persisted it to history. On the next request, Bedrock's stricter
history validator inspects the trailing run of `tool_use` blocks: text
between tool_uses makes the earlier tool_uses no longer count as
"trailing", so they are reported as missing tool_result and the API 400s
even though all tool_results were actually returned. See
CLIENT_TOOL_USE_BUG_REPORT.md from the worldRouter proxy team for the
captured request body and Bedrock error.
This fix:
- Adds `reorderAssistantToolUseBlocks` that moves non-tool_use blocks out
of the tool_use cluster (preserving tool_use id order, thinking/
redacted_thinking positions, and dropping no blocks). No-op when zero
or one tool_use, or when tool_uses are already contiguous.
- Applies it in `mergeAssistantMessages` so live stream-merge produces
clean history.
- Applies it as a pass in `normalizeMessagesForAPI` so sessions resumed
from disk that were persisted before this fix also get cleaned up.
- Adds 9 bun:test cases covering the no-op, hoist, head/tail
preservation, idempotence, and merge cases (including the exact
pattern from the upstream bug report).
Computer Use now rejects Python runtimes below 3.9 before running pip,
keeps Pillow on the Python 3.9-compatible 11.x line, and falls back from
the configured mirror to the default PyPI index when dependency installs
fail.
Constraint: Pillow 11.3 requires Python 3.9+, while user machines may resolve a different Python than expected
Rejected: Downgrade Pillow to the Python 3.8-compatible 10.x line | current product direction assumes modern Python installs
Confidence: high
Scope-risk: narrow
Directive: Keep runtime package ranges aligned with the setup Python minimum before changing either side
Tested: bun test src/server/__tests__/computer-use-api.test.ts src/server/__tests__/computer-use-requirements.test.ts src/server/__tests__/computer-use-python.test.ts src/utils/computerUse/pipInstall.test.ts
Tested: bun run check:server
Tested: bun run check:coverage
Tested: bun run check:policy
Not-tested: Real Windows 10 machine dependency install against the reported user environment
ChatGPT Official runs through Codex OAuth, so context accounting should follow
the Codex model catalog and its effective context window instead of public API
limits. This keeps GPT-5.5 at the same usable window shown by Codex while
preserving GPT-5.4's larger Codex window.
Constraint: Codex OAuth model metadata applies effective_context_window_percent to raw catalog windows
Rejected: Use public API GPT-5.5 1.05M context | Codex app and OAuth runtime clamp this model to the smaller effective window
Confidence: high
Scope-risk: narrow
Directive: Keep ChatGPT Official context values aligned to Codex model catalog behavior, not generic OpenAI API docs
Tested: bun test src/services/openaiAuth/models.test.ts src/services/compact/autoCompact.test.ts src/server/__tests__/providers.test.ts
Tested: bun run check:server
Tested: git diff --check
Not-tested: Manual desktop screenshot after rebuilding the app
The worktree implementation adds one General settings surface for AI request timeout and proxy configuration. This merge keeps main's newer attribution-signing and ChatGPT Official provider paths while preserving the unified network override across CLI sessions, provider checks, and OpenAI-compatible proxy forwarding.
Constraint: Main had newer attribution and official-provider changes touching the same server integration points
Rejected: Prefer the worktree proxy body verbatim | it would drop main's signed CCH attribution wrapper
Rejected: Keep provider preset timeouts above General | it would violate the single timeout control requirement
Confidence: high
Scope-risk: moderate
Directive: General network settings must remain the final AI request timeout and proxy override for every provider protocol
Tested: bun test src/server/__tests__/conversation-service.test.ts src/server/__tests__/network-settings.test.ts src/server/__tests__/providers.test.ts src/server/__tests__/proxy-network-settings.test.ts
Tested: cd desktop && bun run test -- --run src/stores/settingsStore.test.ts src/__tests__/generalSettings.test.tsx
Not-tested: Full bun run verify after resolving main merge conflicts
Direct TUI launches read cc-haha managed settings without the desktop host's session-env injection, so a stale proxy URL could survive after switching to an Anthropic-compatible provider. The provider runtime env calculation now has one shared source of truth and CLI config loading recomputes managed provider env from the active provider index before applying it.
Constraint: Direct source-based TUI usage must keep working with .env when no desktop provider is configured
Rejected: Inject desktop runtime only from the embedded terminal shell | native terminals and source TUI launches would still read stale managed settings
Confidence: high
Scope-risk: moderate
Directive: Keep provider env derivation shared between ProviderService and CLI managedEnv loading
Tested: bun test src/server/__tests__/provider-runtime-env.test.ts src/server/__tests__/providers.test.ts src/server/__tests__/conversation-service.test.ts
Tested: bun run check:server
Not-tested: Live provider request from embedded terminal TUI
Direct native CLI launches already inherit their user's shell environment, so recapturing a login interactive shell from the same TTY is unnecessary and can interfere with prompt input on macOS terminals.
The desktop and non-interactive subprocess paths still keep the shell-env bridge because they do not own the user's interactive terminal.
Constraint: Windows was already excluded from terminal shell env capture, which explains why v0.2.8 remained healthy there.
Rejected: Disable terminal shell env capture globally | desktop subprocesses still need the captured login-shell environment.
Confidence: high
Scope-risk: narrow
Directive: Do not re-enable interactive shell env capture for direct TTY launches without a native PTY input regression test.
Tested: bun test src/utils/terminalShellEnvironment.test.ts src/utils/mcpStdioEnvironment.test.ts
Tested: Native PTY smoke confirmed typed characters appear in claude-haha prompt
Tested: SKIP_INSTALL=1 ./desktop/scripts/build-macos-arm64.sh
Not-tested: Full bun run verify was intentionally not completed after user requested only a local macOS build
Local main added desktop branch-from-chat, attribution headers, sidecar packaging changes, and provider model normalization. The merge keeps those mainline changes while preserving ChatGPT Official provider metadata, OpenAI OAuth runtime env, provider-load guards, and model catalog behavior.
Constraint: Current worktree was detached; created feat/chatgpt-official-oauth-provider before merging to preserve the OAuth commit line.
Rejected: Rebase the OAuth line over main | the branch already contains many reviewed commits and a merge makes the integration point explicit.
Confidence: high
Scope-risk: moderate
Tested: bun test src/server/__tests__/providers.test.ts src/server/__tests__/settings.test.ts src/server/__tests__/conversation-service.test.ts src/server/__tests__/proxy-transform.test.ts src/utils/__tests__/providerManagedEnvCompat.test.ts src/services/api/client.test.ts src/services/openaiAuth/fetch.test.ts src/server/__tests__/haha-openai-oauth-service.test.ts src/server/__tests__/haha-openai-oauth-api.test.ts
Tested: cd desktop && bun run test -- src/__tests__/generalSettings.test.tsx src/components/settings/ChatGPTOfficialLogin.test.tsx src/stores/providerStore.test.ts src/components/controls/ModelSelector.test.tsx --testNamePattern "ChatGPT|OpenAI OAuth|Providers tab|ChatGPTOfficialLogin|ModelSelector|providerStore"
Tested: git diff --cached --check
Bring the verified worktree implementation into local main while preserving the existing local main commits and unrelated dirty working tree changes.
Constraint: Local main already had unrelated uncommitted provider/runtime edits, so the merge only touches the desktop branch feature paths.
Confidence: high
Scope-risk: moderate
Tested: bun run verify before merge; merge completed without conflicts
Not-tested: Post-merge full quality gate on dirty local main
Desktop users need the same branch-from-here workflow that the CLI already exposed, so the branch creation logic now lives in a shared transcript utility and the desktop app routes completed message actions through the server API. The UI hydrates transcript ids after live completions so newly generated turns can be branched immediately without a refresh.
Constraint: Source sessions must remain unmodified while branch sessions inherit the active transcript chain and persistence metadata.
Rejected: Keep a desktop-only branch implementation | it would drift from CLI /branch semantics and duplicate transcript filtering rules
Confidence: high
Scope-risk: moderate
Directive: Do not remove the post-completion transcript hydration without a real-model desktop E2E for just-finished messages
Tested: bun run verify; Chrome Web UI E2E with real gpt-5.5 provider on ports 45678/45679
Not-tested: Provider-specific behavior beyond the configured Sub2API-ChatGPT route
Provider-managed environments should preserve Claude attribution only when the selected model is actually Claude-prefixed. Non-Claude provider models now disable the attribution header so third-party providers do not inherit Claude-specific prompt metadata.
Constraint: Claude model detection is intentionally model-name based to match the requested provider policy.
Rejected: Remove attribution headers globally | official Claude-prefixed models should keep existing behavior.
Confidence: high
Scope-risk: moderate
Directive: Do not broaden this policy without live provider request-shape verification.
Tested: Targeted server, provider, settings, cron, and managed-env tests in prior verification pass.
Not-tested: Full verify gate after this commit.
Settings General now owns AI request timeout and proxy policy so Anthropic-native and OpenAI-compatible provider paths share one user-visible control. The desktop UI persists the network settings, the server proxy and provider checks read them directly, and CLI sessions receive the same timeout/proxy environment.
Constraint: Provider request behavior must be consistent across Anthropic, OpenAI Chat, and OpenAI Responses formats
Rejected: Keep preset API_TIMEOUT_MS precedence | it would make the General timeout control unreliable for some providers
Confidence: high
Scope-risk: moderate
Directive: Do not add protocol-specific AI request timeout controls without preserving General as the final override
Tested: bun test src/server/__tests__/conversation-service.test.ts src/server/__tests__/network-settings.test.ts src/server/__tests__/providers.test.ts src/server/__tests__/proxy-network-settings.test.ts
Tested: cd desktop && bun run test -- --run src/stores/settingsStore.test.ts src/__tests__/generalSettings.test.tsx
Tested: bun run check:desktop
Tested: bun run check:server
Not-tested: socks5 manual proxy support; manual proxy validation currently accepts HTTP/HTTPS URLs only
Desktop sessions can receive task tools, background-agent lifecycle events, and child tool stream events in the same turn. The UI now keeps root Agent cards separate from task-management tools, preserves parent links when later stream events omit them, and surfaces completed background-agent result text from task notifications.
Constraint: Existing desktop session history can contain task-notification XML and live WS events with incomplete parent metadata.
Rejected: Render local_agent lifecycle messages as standalone cards | duplicates the Agent tool card and makes ownership unclear.
Confidence: high
Scope-risk: moderate
Directive: Do not collapse Agent and TaskCreate/TaskUpdate root tools into one generic group without checking multi-agent screenshots.
Tested: SKIP_INSTALL=1 PRESERVE_TAURI_TARGET=1 ./desktop/scripts/build-macos-arm64.sh
Tested: Real gpt-5.5 desktop E2E sessions under /tmp/cc-haha-subagent-e2e-20260519-025454 for 3 subagents, child tools, result dialog, and background Bash completion.
Not-tested: Full bun run verify gate.
Activating the built-in ChatGPT provider now writes a dedicated OpenAI OAuth runtime environment instead of clearing provider state. The runtime points the CLI at the desktop-managed OpenAI token file, avoids Anthropic auth/base-url variables, reports auth from the OpenAI token file, and prevents Claude OAuth injection when ChatGPT Official is active.
Constraint: Default provider sessions read cc-haha managed settings, while session-scoped provider selections inject env directly from the desktop host.
Rejected: Treat ChatGPT Official as a generic OpenAI proxy provider | proxy routing would require API-key shaped auth and would leak it into the wrong runtime path.
Confidence: high
Scope-risk: moderate
Tested: bun test src/server/__tests__/providers.test.ts
Tested: bun test src/server/__tests__/conversation-service.test.ts
Tested: bun test src/services/openaiAuth/storage.test.ts src/server/__tests__/haha-openai-oauth-service.test.ts src/server/__tests__/haha-openai-oauth-api.test.ts
Tested: git diff --check
Remote main carries portable-mode, legacy Windows workdir recovery, and Feishu path-safety fixes while local main carries terminal shell, update proxy, slash-command, prompt-draft, AskUserQuestion, background-work, and shell-env changes. This merge keeps both lines by layering portable Bash-path defaults underneath the desktop terminal shell preference and preserving both update-proxy and app-mode settings state.
Constraint: Local main and origin/main diverged after v0.2.7 and both lines contain release-relevant desktop/runtime fixes
Rejected: Prefer either side's terminal settings wholesale | would drop either Windows portable Bash support or explicit desktop startup-shell support
Confidence: medium
Scope-risk: moderate
Directive: Keep portable Bash path as the system-default terminal fallback; explicit desktop startup-shell settings should continue to override it
Tested: cd desktop && bun run test -- --run src/pages/TerminalSettings.test.tsx src/stores/settingsStore.test.ts
Tested: cd desktop/src-tauri && cargo test terminal -- --nocapture
Tested: bun test src/server/__tests__/sessions.test.ts -t stale worktree
Tested: bun run check:desktop
Tested: bun run check:server
Tested: bun run check:native
Not-tested: Manual Windows packaged-app terminal/portable smoke
Desktop launches can inherit a sparse GUI environment, while user runtimes such as nvm and Homebrew are often initialized from shell startup files. Capture a bounded login+interactive shell environment once and reuse it for desktop CLI sessions, scheduled tasks, and MCP stdio startup while keeping explicit MCP PATH and provider-managed env overrides authoritative.
Constraint: macOS app launches may omit user shell PATH and exported runtime variables
Rejected: Patch only MCP stdio | leaves normal desktop sessions and scheduled tasks inconsistent
Confidence: high
Scope-risk: moderate
Directive: Keep provider/OAuth scrubbing after shell env merging when changing child env builders
Tested: bun test src/utils/terminalShellEnvironment.test.ts src/utils/mcpStdioEnvironment.test.ts src/server/services/mcpHostPreflight.test.ts src/server/__tests__/conversation-service.test.ts src/server/__tests__/cron-scheduler-launcher.test.ts src/server/__tests__/mcp.test.ts
Tested: bun run check:server
Tested: bun run check:coverage
Tested: bun run verify
Not-tested: Real desktop UI live-model smoke on an installed .app
The contributor PR adds useful Windows terminal and portable mode support, but it also reintroduced an older General settings zoom block and left the new native settings paths without enough regression coverage. This commit keeps the feature direction intact while removing the duplicate UI, making invalid bash paths fail at save time, and covering the portable cache and app-mode paths with focused tests.
Constraint: This commit lands directly on the contributor PR branch to avoid a long review-comment loop.
Rejected: Ask the contributor to rework the PR from scratch | the remaining issues are narrow and maintainable by us.
Confidence: high
Scope-risk: moderate
Directive: Keep future portable-mode changes covered at the native boundary and the desktop store boundary.
Tested: cd desktop && bun run test src/pages/TerminalSettings.test.tsx src/__tests__/generalSettings.test.tsx src/stores/settingsStore.test.ts
Tested: bun test src/utils/__tests__/cachePaths.test.ts
Tested: cd desktop/src-tauri && cargo test
Tested: cd desktop && bun run lint
Tested: cd desktop/src-tauri && cargo check
Tested: bun run check:server
Tested: bun run check:desktop
Not-tested: Manual Windows packaged-app portable-mode smoke; to be covered before a future release.
Desktop plugin enable and disable actions are written by the server process, while an already-running CLI owns its own settings cache. Reloading only the plugin caches left enabledPlugins stale after a disable-then-enable cycle, so the slash command list stayed empty until a new conversation spawned a fresh CLI.
Reset the settings cache at the active plugin refresh boundary before resolving enabled plugins. The regression test simulates an external desktop enable toggle after a cached disabled read and verifies the plugin slash command is restored in the same refresh.
Constraint: Desktop server and active CLI are separate processes with independent in-memory settings caches
Rejected: Restart the CLI on every plugin toggle | heavier user-visible lifecycle change and unnecessary once the reload handoff invalidates settings
Confidence: high
Scope-risk: narrow
Directive: Keep reload_plugins as the handoff that rereads settings before plugin command discovery
Tested: bun test src/server/__tests__/plugins.test.ts
Tested: bun run check:server
Desktop sessions must treat the global Thinking toggle as the source of truth across active CLI sessions, title generation, and provider-compatible request bodies. DeepSeek-style streams can start with reasoning blocks before text, so the WebSocket bridge now keeps the UI in thinking state until text content actually starts.
Constraint: DeepSeek and MiniMax use Anthropic-compatible surfaces but expose thinking behavior through provider-specific request and stream shapes
Rejected: Keep provider-specific disabled-thinking env defaults | stale defaults kept overriding the user's global Thinking setting
Rejected: Treat every non-tool stream block as text | reasoning-only startup blocks created a blank streaming gap before the visible thinking bubble
Confidence: high
Scope-risk: moderate
Directive: Do not change thinking stream state transitions without replaying reasoning-before-text provider events
Tested: bun test src/server/__tests__/ws-memory-events.test.ts
Tested: bun run check:server
Tested: bun run verify
Not-tested: Live DeepSeek provider smoke with real quota
This merge carries the worktree fix into the local main branch so long multi-session desktop usage keeps rendering cost bounded while DeepSeek follows the shared General Settings Thinking toggle. It preserves running-session behavior and keeps legacy DeepSeek managed env from pinning thinking off after upgrade.
Constraint: User requested the worktree result merged into local main without pushing.
Confidence: high
Scope-risk: moderate
Directive: Keep DeepSeek controlled by the global Thinking setting; do not restore provider-specific disabled-thinking defaults without both toggle-state tests.
Tested: bun test src/server/__tests__/conversations.test.ts -t "global Thinking setting control DeepSeek"
Tested: bun test src/server/__tests__/persistence-upgrade.test.ts src/server/__tests__/provider-presets.test.ts src/server/__tests__/providers.test.ts src/server/__tests__/title-service.test.ts src/utils/__tests__/thinking.test.ts src/utils/__tests__/providerManagedEnvCompat.test.ts
Tested: cd desktop && bun run test -- MessageList.test.tsx ContextUsageIndicator.test.tsx
Tested: bun run check:server
Virtualized chat rendering keeps inactive long-running sessions cheap without disconnecting their CLI process, while DeepSeek now relies on the shared Thinking setting instead of a provider-specific disabled-thinking override. Existing legacy DeepSeek managed env is normalized so old local settings do not keep suppressing reasoning output after upgrade.
Constraint: Multiple desktop tabs must keep live sessions running and remain quick to switch without reconnecting.
Rejected: Pause or disconnect hidden sessions | would delay tab switching and interrupt streaming/tool state visibility.
Rejected: Keep DeepSeek disabled-thinking preset | conflicts with the General Settings Thinking control.
Confidence: high
Scope-risk: moderate
Directive: Do not reintroduce provider-specific disabled-thinking defaults for DeepSeek without testing both General Settings toggle states.
Tested: bun test src/server/__tests__/conversations.test.ts -t "global Thinking setting control DeepSeek"
Tested: bun test src/server/__tests__/persistence-upgrade.test.ts src/server/__tests__/provider-presets.test.ts src/server/__tests__/providers.test.ts src/server/__tests__/title-service.test.ts src/utils/__tests__/thinking.test.ts src/utils/__tests__/providerManagedEnvCompat.test.ts
Tested: cd desktop && bun run test -- MessageList.test.tsx ContextUsageIndicator.test.tsx
Tested: bun run check:server
Desktop startup can fail before React mounts on older WebViews, so an HTML-level watchdog now renders startup diagnostics even when the module bundle never reaches the app code. Persistent provider migration now imports legacy root provider config into cc-haha-owned storage without deleting the old source file, and plugin marketplace cleanup refuses obvious corrupted cache roots or outside paths.
Constraint: User explicitly accepted the current reviewed state for landing despite remaining review concerns.
Constraint: Global ~/.claude state is user-owned and protected; automatic repair must avoid deleting shared config, transcripts, skills, MCP, plugins, OAuth, adapters, and teams.
Rejected: Tell users to delete ~/.claude or ~/.claude/cc-haha | unsafe because it can destroy user-owned Claude state and still may not fix WebView compatibility failures.
Confidence: medium
Scope-risk: moderate
Directive: Do not weaken protected-path checks; future deletion paths should validate real paths and symlink behavior before recursive rm.
Tested: bun test src/utils/plugins/installedPluginsManager.test.ts src/utils/plugins/marketplaceManager.test.ts
Tested: bun run check:server
Tested: cd desktop && bun run test -- --run src/main.test.tsx index-html.test.ts vite-config.test.ts src/theme/globals.test.ts
Tested: cd desktop && bun run build
Tested: bun run check:coverage
Not-tested: live macOS 12/Safari 15 WKWebView startup on an affected machine.
Not-tested: H5 diagnostic URL redaction and symlink-escape hardening are known follow-up risks from review.
Settings reported false negatives for resources the runtime could load, because the API paths used narrower discovery rules than the execution path. This keeps the Settings surfaces read-only where appropriate while matching runtime visibility for linked skills, version-constrained plugins, and merged MCP sources.
Constraint: Settings MCP list must not actively connect to servers while loading.
Rejected: Add UI-specific fallbacks | would preserve drift between Settings and runtime loaders
Confidence: high
Scope-risk: moderate
Directive: Keep Settings resource listing backed by the same shared loader semantics as runtime discovery.
Tested: bun test src/server/__tests__/skills.test.ts
Tested: bun test src/server/__tests__/plugins.test.ts
Tested: bun test src/server/__tests__/mcp.test.ts
Tested: bun run check:server
Tested: bun run check:coverage
Tested: bun run verify
Not-tested: Live external MCP connector account state
Providers like DeepSeek with 1M context windows can report
input_tokens that, when combined with output_tokens, exceed the
declared context window — causing the UI to show >100% usage.
Add an optional contextWindow parameter to calculateCurrentContextTokenTotal
that clamps the result to the window size. Pass it from analyzeContext
and sessionService where the window size is already available.
Backward compatible: callers that omit the parameter keep existing behavior.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
