mirror of
https://github.com/NanmiCoder/cc-haha
synced 2026-07-27 15:13:37 +08:00
1172 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
你的姓名
|
a5ed9a2f22 |
ci(native): install adapter deps before sidecar build
desktop-native-checks runs un run check:native, which builds the sidecar binaries. Sidecar entry points import IM adapter deps (@whiskeysockets/baileys for whatsapp, dingtalk-stream, grammy for telegram, @larksuiteoapi/node-sdk for feishu). These live in the adapters/ workspace and are not installed by cd desktop && bun install. Without an adapter install step the sidecar build fails with 'Could not resolve' for each upstream IM dependency. This was masked on previous merged PRs (#2-#6) because their change-policy job failed first and skipped this lane. Now that change-policy is unblocked, the lane runs and surfaces this pre-existing CI gap. Other lanes that touch adapter code already do this (coverage-checks at line 197 has an 'Install adapter dependencies' step). This commit just brings desktop-native-checks in line. Confidence: high Scope-risk: narrow (CI workflow only, no product code). |
||
|
你的姓名
|
d59819c5c3 |
ci: unblock change-policy on the merge PR
Two fork-vs-upstream gaps surfaced when PR Quality ran against
8d914596 (the upstream v0.4.1 merge):
1. `bun run check:policy` failed with `Cannot find package 'yaml'`
because the change-policy job in pr-quality.yml had no
`bun install` step. Other lanes (server-checks, desktop-checks,
adapter-checks, coverage-checks) all install root deps before
running their checks; change-policy was the outlier. Upstream's
release-update-metadata.test.ts started importing `yaml` from
the root package.json, so the missing install step finally bit.
Fix: add the missing `bun install` step. Lockfile already pins
yaml@2.8.3, so this is a no-op everywhere else.
2. Two assertions in scripts/pr/release-workflow.test.ts were
written against the upstream identity (NanmiCoder/cc-haha) but
commit 3cbed50c on this fork repointed desktop/package.json
`homepage` and `build.publish.owner` to 706412584/cc-haha
without updating the tests. The merge brought the upstream
tests forward and the fork-only desktop config conflict was
immediately. Both assertions are now fork-friendly:
- homepage: regex `https://github.com/<owner>/cc-haha`
- publish: explicit github provider + repo cc-haha, owner
can be any non-empty identifier.
Author name/email and Linux maintainer assertions are kept
strict because commit 3cbed50c intentionally preserved them.
Tested:
- `bun run check:policy` locally: 81/83 pass. The single
remaining failure (`release workflow records macOS signing
state and warns for unsigned builds`) is a Windows-only CRLF
mismatch in a regex that uses `fi\n` against a workflow file
with CRLF line endings. CI runs on Ubuntu and the test passes
upstream, so this does not block the PR.
Confidence: high
Scope-risk: narrow (CI workflow + test, no product code touched).
|
||
|
你的姓名
|
8d91459610 |
Merge upstream NanmiCoder/cc-haha v0.4.1 into fork main
Pulls 21 upstream commits (147 files, +17234 / -317) since merge-base
4bea9ee6. Major upstream additions:
- feat(trace): session trace monitoring + LangSmith-style two-pane UI
(large new subtree under src/server/services/traceCaptureService.ts,
src/server/api/traces.ts, desktop/src/components/trace/, lib/trace/)
- feat(adapters): WhatsApp linked-device adapter (new sub-tree)
- feat(adapter): Telegram command menu
- feat(desktop): plugin list bulk toggles
- feat(desktop): output style desktop config
- fix(agent): defer permission/runtime restarts during active turns
- fix(agent): avoid concurrent worktree config writes
- fix(desktop): native preview screenshots, memory file preview-first
Conflict resolution (8 files, all handled by hand):
- desktop/package.json: kept fork version 0.5.8 (vs upstream 0.4.1)
and the fork's homepage URL.
- src/server/router.ts: kept BOTH /api/projects (fork) and
/api/traces (upstream) handlers + imports.
- desktop/src/components/chat/chatBlocks.test.tsx: kept fork's
"expanded by default" thinking-block tests; upstream had the old
"collapsed by default" assertions which contradict the live
ThinkingBlock.tsx default (`useState(true)`).
- desktop/src/pages/Settings.tsx: merged imports — added
`type TranslationKey` (upstream, used by trace tab) plus kept
fork's providerCompat store imports.
- desktop/src/components/plugins/PluginList.tsx: integrated
upstream's bulk-toggle (selectedPluginIds, ConfirmDialog,
bulkEnable/Disable) on top of fork's catalog/marketplace/inline
actions. Row layout now has checkbox + details button + inline
toggle/uninstall + chevron all coexisting. Both ConfirmDialog
instances (uninstall + bulk-batch) kept.
- src/server/api/sessions.ts: kept BOTH session-summary (handoff,
fork) and trace-call (upstream) handler functions and imports.
Routing dispatch was auto-merged correctly.
- src/server/services/conversationService.ts: unified
SessionStartOptions to carry fork's coordinatorMode +
handoffSystemPrompt AND upstream's resumeInterruptedTurn.
- src/server/ws/handler.ts: unified RuntimeOverride type to keep
fork's `thinkingEnabled` field (used 30+ times elsewhere) AND
upstream's new ActiveUserTurnState plus the deferred-restart Maps
(activeUserTurns, deferredRuntimeRestarts, deferredPermissionModes).
cleanupSessionRuntimeState now drains both fork's session sets
(coordinatorModeSessions, handoffSummarySessions) and upstream's
new Maps.
Verification:
- bun run lint (desktop): clean.
- bun test src/server/__tests__/mcp.test.ts -t marketplace: 2/2 pass.
- bun test src/server/__tests__/sessions.test.ts: 76/77 pass. The
single failure (slash-commands legacy custom commands) reproduces
on un-merged origin/main and is pre-existing — not introduced by
this merge.
Not-tested:
- Full bun run verify gate. Recommended before push/PR.
- Live trace UI smoke (no provider creds in this environment).
- Plugin list bulk-toggle smoke (no headed Electron available).
- WhatsApp adapter (separate sub-tree, not exercised by typecheck).
Confidence: medium-high (typecheck clean, no markers, conflicts all
semantically reasonable). Recommend a maintainer eye on
ws/handler.ts and conversationService.ts before merging upward,
since the deferred-restart vs handoff-injection paths touch the
same Map-of-pending-state surface.
Scope-risk: broad (147 files brought in via merge). Risk surface is
contained because trace + WhatsApp are independent subtrees and the
hand-resolved conflicts kept both sides additive rather than
rewriting either's logic.
|
||
|
程序员阿江(Relakkes)
|
3e52c58a33 |
release: v0.4.1
Tested: bun run scripts/release.ts 0.4.1 --dry Confidence: medium Scope-risk: narrowv0.4.1 |
||
|
你的姓名
|
062978ec97 | release: v0.5.8 | ||
|
cc-haha
|
64691f7672 |
fix(plugin): reverse-engineering 0.4.0 -> 0.4.2 review fixes
Self-review of v0.4.0 surfaced three real bugs (would have produced
incorrect output to the user / LLM) plus a handful of consistency
gaps. None of these block enabling the plugin or break the smoke,
but together they erode trust in what the plugin tells the user.
Real bugs fixed
---------------
1. commands/triage.md and commands/report.md used a bash-style
`${user_config.ARTIFACT_DIR:-artifacts/re-runs}` default-fallback.
The substitute regex in src/utils/plugins/pluginOptionsStorage.ts
is a plain `\$\{user_config\.([^}]+)\}` capture -- it would have
keyed off the literal string `ARTIFACT_DIR:-artifacts/re-runs`,
missed it, and returned the unsubstituted match, leaking the
`:-default` syntax into the LLM prompt. Worse, manifest defaults
(plugin.json `userConfig.ARTIFACT_DIR.default`) are NOT auto-merged
into runtime options -- `loadPluginOptions` only reads
settings.json + secureStorage. So the only way `${user_config.X}`
resolves at all is if the user explicitly set it in the UI; for
plugin authors who want a sensible fallback, the variable form
isn't actually useful here. Switched both commands to a prose
directive ("use ARTIFACT_DIR setting if present; otherwise default
to artifacts/re-runs") that the LLM can resolve from context. This
matches how the SKILL.md files already wrote the same idea.
2. agents/reverse-engineer.md "When you do NOT have the right MCP
server available" still told the agent to point users at the
`userConfig` toggle for each MCP. Those toggles
(ENABLE_GHIDRA / ENABLE_RADARE2 / ENABLE_JADX / ENABLE_APKTOOL /
ENABLE_FRIDA) were removed in the v0.4.0 cleanup -- they never
actually controlled MCP loading, only made the userConfig dialog
look more important than it was. The fix points users at
Settings -> MCP for runtime enable/disable and at the README's
prerequisites table for install instructions, both of which are
the actual sources of truth post-cleanup.
3. agents/reverse-engineer.md description listed binwalk as a
first-class tool in the toolchain bullet. binwalk is not bundled
as an MCP -- skills/firmware-blob shells out to the binwalk CLI
directly through Bash. Dropped from the description so the LLM
doesn't hallucinate a binwalk MCP server when none exists.
Consistency gaps fixed
----------------------
4. README.md opening summary still claimed "five MCP servers ...
six skills"; reality is seven MCP servers and eleven skills since
v0.3.0/v0.4.0. The capability tables further down were correct,
only the lead paragraph was stale. Replaced with a less number-
coupled summary.
5. README install snippet hard-coded `C:\Users\70641\cc-haha\plugins`
in three places. Replaced with `(Resolve-Path .\plugins).Path` so
any contributor's checkout works without editing -- and noted
`<repo-root>` semantics in prose for non-Windows readers.
6. README References section didn't list the new GDB and LLDB MCPs
added in v0.4.0. Added entries for signal-slot/mcp-gdb and
stass/lldb-mcp.
7. Added a README section "LLDB MCP -- fallback if uvx fetch fails"
covering the upstream-packaging gap in stass/lldb-mcp (it ships
as a single .py without an installable entry point, so
`uvx --from git+...` may report `python: can't open file
'lldb_mcp.py'` on first start). The fallback recipe (clone +
absolute python3 path) is now in the README rather than something
each user has to rediscover.
8. plugin.json keywords were narrower than marketplace.json tags:
keywords had 7 entries, tags had 16. Brought keywords up to the
12 most useful for plugin discovery (firmware, embedded, debugger,
single-step, ghidra, radare2, frida, gdb, lldb).
9. skills/triage Step 3 routing table mapped "Live process /
instrumented session" directly to frida-dynamic. The agent's
Stage 3 says to read dynamic-debug-overview FIRST and let it pick
between Frida / GDB / LLDB. Updated triage to match -- now any
runtime question routes to dynamic-debug-overview, which then
picks the right lane.
10. agent description had "iOS -> r2 + optionally class-dump", but
skills/ios-analysis actually keeps Ghidra (with the iOS loader)
in scope as well. Updated agent to "r2 (preferred, via the
radare2 MCP) or Ghidra with the iOS loader" so the LLM knows
Ghidra is also a path on iOS.
Manifest version bump 0.4.0 -> 0.4.2 (two patch bumps because the
first fix pass missed the loadPluginOptions semantics; bumping again
re-materialised the cache after the corrected commands content was
written).
Verification
------------
bun run plugins/reverse-engineering/scripts/validate.ts
-> 0 fail / 0 warn (marketplace + plugin schema both clean)
bun run plugins/reverse-engineering/scripts/smoke.ts
-> 13 passed / 0 failed
version=0.4.2, commands=2, agents=1, skills=11, mcpServers=7,
skill ids match the on-disk glob
Cache materialised at
~/.claude/plugins/cache/cc-haha-builtin/reverse-engineering/0.4.2/
carries the corrected commands without the bash-style
default-fallback.
Confidence: high
Scope-risk: narrow (plugin-only patch; no source code touched, no
breaking change to existing skill names or component counts).
Tested: validate (pass), smoke (13/13 pass), cache content spot-check
of commands/report.md.
Not-tested: live `/reverse-engineering:triage` against a real sample
end-to-end; the substitution change is text-only and the runtime
loader was unaffected.
|
||
|
小橙子
|
fe4bf78448
|
fix(provider): auto-detect & fall back from thinking-incompatible providers (#6)
When a third-party Anthropic-compatible gateway (typical: Bedrock-backed proxies like the user's mimo setup) can't relay Anthropic's `thinking` field, it returns 400s like "该模型不支持 'additionalModelRequestFields' 字段" — the gateway has wrapped the unknown Anthropic param into AWS Bedrock's `additionalModelRequestFields`, and Bedrock rejects on the target model. The user reported a 4.5 model on mimo failing this way while the same model on kiro-account-manager 1.7.5 (which doesn't go through Bedrock) was fine. End-to-end fix: detect the failure pattern, sticky-mark the provider, auto-restart the sidecar with `CLAUDE_CODE_DISABLE_THINKING=1`, and surface a Settings badge so the user knows what happened. Mirrors the desktop providerCompatStore pattern from PR #4 (fake tool_use detection) — two compat dimensions, same re-arm-on-edit semantics, same UX shape. Server side ----------- - `SavedProvider` schema gains `thinkingIncompatible?: boolean` and `thinkingIncompatibleReason?: string` (max 500 chars). Fully back-compat: missing field reads as undefined. - `ProviderService.markThinkingIncompatible(id, reason)` writes the flag, idempotent for identical reasons (no thrash on a burst of the same error). Returns null for unknown ids and openai-official. - `ProviderService.updateProvider` auto-clears the flag on any edit — user changing config = "I'm fixing it" → fresh chance. - `buildProviderManagedEnv` injects `CLAUDE_CODE_DISABLE_THINKING=1` when the flag is true, so the next sidecar launch goes out without thinking entirely. - WS handler runs `detectThinkingIncompatMessage` on every error ServerMessage forwarded to the desktop. On match, fires: 1. `markThinkingIncompatible` (persists) 2. `provider_compat_event` WS message to the desktop 3. `enqueueRuntimeTransition` → `scheduleRestartSessionWithRuntimeConfig` (same graceful path used by set_runtime_config — never tears down a streaming response mid-flight) Process-local dedup so a burst of identical errors doesn't restart the sidecar repeatedly. - Detection regex deliberately narrow: /additionalModelRequestFields/i /\bthinking\b[^.]*\b(not supported|unsupported|invalid| disabled|rejected)\b/i /unknown.{0,40}\bthinking\b/i False positives would permanently disable thinking on the wrong provider until the user edited its config. Desktop side ------------ - New ServerMessage variant `provider_compat_event` plumbed through both server and desktop chat type unions. - `providerCompatStore` gains `thinkingIncompatibleProviderIds: Set<string>`, `recordThinkingIncompatible(id, reason)` action, `hasProviderThinkingIncompatible(id)` helper. Persisted to the same localStorage key as the fake-tool_use counter, alongside it. Dedup: re-firing for an already-flagged provider doesn't re-toast. - `clearProvider(id)` now clears BOTH dimensions, matching the server-side updateProvider behavior. - `chatStore` switch dispatches the new event to the store. - `Settings → Provider` row renders a separate "思考不兼容" badge (psychology_alt icon) next to the existing "工具调用异常" badge. Both badges can show simultaneously when a provider has both problems; both are cleared by the same edit-and-save action. - 5 locales (en/zh/zh-TW/jp/kr) get 3 new keys each: badge label, badge tooltip, and toast message. Tests ----- - `src/server/ws/thinkingIncompat.test.ts` (NEW, 6 cases): regex pinning — Bedrock additionalModelRequestFields rejections / thinking-rejection phrases / unrelated 4xx / passing mentions of thinking / null-empty defensive / case-insensitive. - `src/server/__tests__/providers.test.ts` (5 added): markThinkingIncompatible persists / truncates 500-char reason / idempotent / null-for-unknown-id / null-for-openai-official / updateProvider auto-clears. - `src/server/__tests__/provider-runtime-env.test.ts` (2 added): `CLAUDE_CODE_DISABLE_THINKING=1` injected when flag true / absent when flag false (back-compat with v0.5.7 providers.json). - `desktop/src/stores/providerCompatStore.test.ts` (6 added): records flag + one-time toast / persists set / hydrates from localStorage / clearProvider clears both dimensions / null-empty defensive / hasProviderThinkingIncompatible reflects current state. Folded into the unreleased v0.5.8 release notes — fold both this fix and the PR #5 (handoff fixes) into the same 0.5.8 release. Tested: - bun run lint (desktop) clean - bun test src/server/{ws/thinkingIncompat,__tests__/providers, __tests__/provider-runtime-env}.test.ts → 87 + 6 = 93 pass - bunx vitest run src/stores/providerCompatStore.test.ts → 14 pass - bunx vitest run src/components/chat/AssistantMessage.faketooluse.test.tsx → 6 pass (regression check, no breakage from the new chatStore dispatcher case) Confidence: high Scope-risk: narrow — additive types throughout (back-compat with v0.5.7 providers.json), narrow detection regex, dedup guard prevents restart loops, edit-to-clear gives users an easy escape hatch. Co-authored-by: 你的姓名 <you@example.com> |
||
|
程序员阿江(Relakkes)
|
d9ce2f09e1 |
refactor(desktop): move trace entry into Settings
Trace is a low-frequency diagnostic feature, so its entry points no longer sit in primary chrome: - Remove the Trace nav item above the session list in the sidebar - Remove the trace open/open-window buttons from the session header - Add a Trace tab in Settings between Token usage and Diagnostics, embedding the existing TraceList page full-bleed - Add settings.tab.trace and drop unused sidebar.traces across locales |
||
|
程序员阿江(Relakkes)
|
d3d7566f0c |
refactor(trace): redesign trace UI with LangSmith-style two-pane layout
UI rebuild (desktop): - TraceSession: replace 3-column layout with two panes — turn-grouped timeline tree (draggable splitter, search/filter, keyboard nav) and a section-flow detail panel (Response / Messages / System Prompt / Tools / Parameters / Raw), collapse state persists across spans - Render LLM requests/responses semantically: messages as role-colored conversation with tool_use/tool_result pairing instead of raw JSON dumps; Raw fallback via CodeViewer for legacy truncated records - TraceList: row-style list with model chips, mono metrics, hover actions; content-visibility rows (no virtualization, WebKit-safe) - i18n synced across zh/en/jp/kr/zh-TW (+25/-55 keys) Data & capture (server): - Capture full bodies: preview cap 2048 -> 240k chars, stream cap 256KB -> 1MB; list API trims previews to keep polling light; new GET /api/sessions/:id/trace/calls/:callId returns the full record - Extract per-call token usage at read time (SSE + JSON + proxy wrapped); mtime-keyed read cache for the polling path - Fix sensitive-key regex redacting *_tokens count fields, which made token stats always report 0 Frontend data layer: - SSE stream reassembly (Anthropic + OpenAI chat) adapted from claude-tap (MIT, attribution in THIRD_PARTY_LICENSES.md), request/ response body parsers, shared formatters, on-demand call detail cache; traceViewModel gains tokenUsage/isLifecycleNoise, drops fullRaw Tested: - bun run check:server (1201 pass) - bun run check:desktop (lint + 1358 tests + build) - Chromium walkthrough against real local traces: list, session tree, LLM semantic detail (new format), legacy fallback, tool detail |
||
|
程序员阿江(Relakkes)
|
cf7e48e540 |
fix(desktop): restore visual selection history cards
Restore visual-selection prompts from persisted transcript history as annotated screenshot attachments instead of exposing the model-facing selector prompt after reopening a session. Tested: cd desktop && bun run test -- --run src/stores/chatStore.test.ts -t "restores visual selection history" --reporter verbose Tested: bun run check:desktop Confidence: high Scope-risk: narrow |
||
|
程序员阿江(Relakkes)
|
5dfddd1132 |
fix(adapters): reconnect WhatsApp login socket after post-pairing restart
WhatsApp always closes the pairing socket with DisconnectReason.restartRequired (515) right after a successful QR scan, so the login flow treated every successful scan as "connection closed". Recreate the socket with the saved credentials and keep waiting for the open event instead, matching the openclaw reference behavior. Also restart on QR rotation timeout (408) to serve a fresh QR, bounded by a restart limit. Tested: - cd adapters && bun test (397 pass) - cd adapters && bunx tsc --noEmit -p tsconfig.json - bun test src/server/__tests__/adapters.test.ts |
||
|
程序员阿江(Relakkes)
|
ae09a39e55 |
fix(desktop): update IM adapter setup guidance
Put Telegram first in the IM adapter settings, add a single documentation link in the setup copy, and keep per-platform settings focused on configuration. Tested: cd desktop && bun run test AdapterSettings.test.tsx Tested: bun run check:desktop Scope-risk: narrow Confidence: high |
||
|
程序员阿江(Relakkes)
|
e8fcccebf0 |
fix: defer permission restarts during active turns (#626)
Persist permission mode changes immediately, but defer restart-only permission transitions until the active desktop turn emits its terminal result. Tested: - bun test src/server/__tests__/conversations.test.ts -t "should defer bypass permission restarts until the active turn completes" - bun test src/server/__tests__/conversations.test.ts -t "permission" - bun run check:server Scope-risk: narrow |
||
|
程序员阿江(Relakkes)
|
d7a1306790 |
fix(desktop): let memory markdown editor fill pane
Tested: cd desktop && bun run test -- src/__tests__/memorySettings.test.tsx --run --reporter=verbose --pool=forks --maxWorkers=1 --minWorkers=1 Tested: bun run check:desktop Tested: bun run check:coverage Tested: Chrome CDP smoke confirmed the memory editor textarea expands to 592px tall Confidence: high Scope-risk: narrow |
||
|
程序员阿江(Relakkes)
|
66306a54bf |
fix(desktop): capture preview screenshots natively
Use Electron WebContentsView capturePage for browser preview screenshots and selection annotations so captured images match the rendered preview. Tested: - cd desktop && bun run test -- electron/services/preview.test.ts src/lib/previewEvents.test.ts src/components/browser/BrowserSurface.test.tsx src/preview-agent/screenshot.test.ts src/preview-agent/picker.test.ts src/preview-agent/editBubble.test.ts - cd desktop && bun run lint - cd desktop && bun run build - bun run check:desktop - bun run check:electron - bun run check:native Not-tested: - Real GUI click-through for Screenshot / Select Element; Electron runtime launch was blocked in this shell and packaged build did not enter the smoke path. Constraint: GUI click-through smoke was blocked by local Electron launch behavior; package smoke passed but does not launch the app. Confidence: medium Scope-risk: narrow |
||
|
小橙子
|
2b6202d381
|
fix(handoff): reuse empty session + ship raw tail for v0.5.8 (#5)
Two bugs in the v0.5.7 "Continue from here" hand-off path landed in the wild and the user caught them while exercising 0.5.8 prep: 1. **Stray empty session.** When the user previously opened a "New session in X" tab from the sidebar, then closed the tab to declutter, the freshly-created empty session was already on disk and visible in the sidebar. Coming back to the welcome screen (activeTabId = null → EmptySession route) and clicking "Continue from here" called `createSession` unconditionally, minting yet another empty session next to the now-stale one. The user ended up with `Untitled Session 27 minutes ago` lingering in the sidebar while the hand-off ran in a completely separate fresh session. Extract the picker into `desktop/src/lib/sessionReuse.ts` — `pickReusableEmptySession(sessions, workDir, excludeSessionId?)` filters by exact-workDir match, `messageCount === 0`, excludes the previous session being handed off FROM, and sorts by `modifiedAt` desc. Caller in `EmptySession.onAutoHandoff` runs this before `createSession`; on hit, openTab on the existing sessionId and let ContentRouter switch to ActiveSession naturally; on miss, create fresh as before. 7 unit tests cover the boundaries: workDir mismatch, non-zero messageCount, excludeSessionId honored, null workDir treated as "no candidates" (so we never silently merge home-dir sessions into a project hand-off), empty workDir argument, empty session list, freshness sort order. 2. **Summary too abstract; AI doesn't know specific recent state.** The previous implementation only injected the LLM-summarized `main` + `recent` paragraphs into the next session's system prompt. That summarization tends to wash out exact wording, file paths, error messages, and the user's literal last question — the user reported "AI doesn't know what we just hit a wall on." Add `recentRaw?: string` to `SessionSummary`. New helper `buildRecentRawSlice` keeps the LAST ~12 turns (env-tunable via `CLAUDE_CODE_HANDOFF_RAW_TURNS`, range 0–50, default 12), each truncated to 400 chars preserving the `USER:` / `ASSISTANT:` role prefix, total capped at ~8000 chars (env-tunable via `CLAUDE_CODE_HANDOFF_RAW_CHARS`, range 500–30000, default 8000). Older turns drop first when the total cap is busted by dense recent turns. `formatHandoffSystemPrompt` renders the raw slice inside a fenced code block AFTER the abstracted recent summary, so the next session sees both the digest and the literal text. Section is omitted entirely when `recentRaw` is absent — v0.5.7 caches still load and produce the exact same prompt bytes (back-compat). 8 unit tests cover the formatter's back-compat path, the raw block placement, fence rendering, tail-N selection, all-fits case, per-turn truncation with role prefix preservation, total cap busting (older drops first), and the `RAW_TURNS=0` opt-out. Both fixes fold into the unreleased v0.5.8 — release-notes/v0.5.8.md gets two new fix bullets and the 范围 / 验证 sections call out the new files and 15 added tests. desktop/package.json bump to 0.5.8 stays as-is (preset earlier in the same worktree before this commit). Tested: - bun run lint (desktop) clean - bunx vitest run sessionReuse.test.ts → 7/7 pass - bun test sessionSummaryService.test.ts → 8/8 pass - bunx vitest run EmptySession.test.tsx → 22/22 pass (regression check after the helper extraction — the existing tests don't go through the hand-off branch but exercise the rest of the file) Confidence: high Scope-risk: narrow (no shape changes to any persistence — recentRaw is an additive field, old caches deserialize cleanly because `tryParseSummaryResponse` already only required main+recent) Co-authored-by: 你的姓名 <you@example.com> |
||
|
小橙子
|
65a042bd08
|
fix: detect & isolate fake tool_use leaks from non-Anthropic providers (#4)
* feat(plugin): add reverse-engineering plugin v0.4.0 + project-level codegraph
Bundles a multi-platform RE toolkit as a local marketplace plugin that
clone-and-enable installs in cc-haha desktop. Covers static (Ghidra,
radare2, JADX, apktool, binwalk via Bash) and the gap a previous review
called out: dynamic debugging is the lane that matters most for
AI-driven RE, but Frida alone cannot single-step or set real
breakpoints. This commit fills that gap with three non-overlapping
dynamic lanes -- Frida (instrumentation, mobile, broad surveys), GDB
(cross-arch single-step + breakpoints, embedded firmware), LLDB (Apple
platforms, ObjC/Swift).
Architecture coverage spans MIPS / ARM (incl. Cortex-M Thumb) /
PowerPC (incl. e200 VLE) / 68k (incl. Mac Toolbox A-line traps) /
SuperH / RISC-V / x86-64 / AArch64. The agent picks the right ISA,
base address, and load configuration in skills/firmware-blob, then
hands off to skills/pe-elf-macho with per-architecture decompilation
notes (MIPS delay slots, ARM Thumb interworking, PowerPC TOC/SDA,
68k register banks, etc).
Plugin layout (.claude-plugin marketplace + plugin manifests):
plugins/.claude-plugin/marketplace.json
plugins/reverse-engineering/
.claude-plugin/plugin.json v0.4.0, GHIDRA_INSTALL_DIR + ARTIFACT_DIR userConfig
agents/reverse-engineer.md triage -> static -> optional dynamic -> report
skills/triage/ file-type identification, packing, routing
skills/pe-elf-macho/ Ghidra/r2 + per-arch notes for non-x86
skills/firmware-blob/ raw blob -> ISA + base address + Ghidra/r2 load config
skills/apk-analysis/ JADX + apktool, Android attack surface
skills/ios-analysis/ IPA bundle + Mach-O, FairPlay-aware
skills/dynamic-debug-overview/ decision matrix Frida vs GDB vs LLDB
skills/frida-dynamic/ hooks + Memory + CpuContext + Stalker + watchpoints
skills/gdb-debug/ cross-arch via gdbserver / qemu-user / qemu-system
skills/lldb-debug/ macOS / iOS device / Linux, ObjC/Swift symbols
skills/crackme-keygen/ CTF / self-owned binary; ships keygen, not patch
skills/re-report/ final structured report with IOCs + confidence
commands/triage.md /reverse-engineering:triage <path>
commands/report.md /reverse-engineering:report <sample-id>
mcp/servers.json 7 MCP servers: ghidra (pyghidra-mcp PyPI),
radare2 (npm), gdb (mcp-gdb npm), lldb
(stass/lldb-mcp git), jadx, apktool, frida
(kahlo-mcp git, all @main pinned)
hooks/hooks.json empty placeholder
scripts/validate.ts offline schema check via project's
validatePluginManifest + validatePluginContents
scripts/dev-link.ts Windows mklink /J cache -> repo source so SKILL
edits don't require version bump (--restore undoes)
scripts/smoke.ts end-to-end: marketplace register -> enable ->
update -> reload -> assert detail counts.
Counts derived from on-disk source (glob),
not hardcoded; idempotent across reruns.
README.md install, prerequisites per MCP, dynamic-capabilities
matrix, architecture coverage, quickstart with
busybox sample, dev-link / smoke workflows
Project-level MCP (clone-and-go for any contributor):
.mcp.json codegraph (npx -y codegraph serve --mcp);
project scope, picked up automatically.
Pre-existing user-level codegraph install
still wins for users who have one.
userConfig of the plugin is honest -- only knobs that actually do
something (GHIDRA_INSTALL_DIR substituted into the ghidra MCP env;
ARTIFACT_DIR resolved relative to agent cwd at run time). Earlier
ENABLE_* booleans were removed because they didn't actually toggle
anything; users disable individual MCP servers from Settings -> MCP
at runtime.
End-to-end verification (server on :3456, vite on :1420):
- bun run plugins/reverse-engineering/scripts/validate.ts
-> 0 fail / 0 warn (marketplace + plugin schema both clean)
- bun run plugins/reverse-engineering/scripts/smoke.ts
-> 13 passed / 0 failed (marketplace registration, enable, update
0.3.0->0.4.0, reload, detail assertions including 11 skill ids
matching the on-disk glob)
- GET /api/plugins/detail
-> commands=2 / agents=1 / skills=11 / mcpServers=7 / errors=[]
- GET /api/mcp
-> codegraph appears with scope=project,
configLocation=.mcp.json
- Desktop UI Settings -> Plugins
-> v0.4.0 listed in enabled group, "11 skills 1 Agent 7 MCP"
External tool prerequisites (each MCP needs its underlying tool on
PATH; users install per-MCP independently -- none required all at
once): Ghidra (Java 17+), r2, GDB (gdb-multiarch for cross-arch),
LLDB, frida-tools, JADX (Java 17+), apktool. Codegraph requires
either a local global install (npm i -g codegraph) or relies on npx
to fetch on first run.
Constraint: Cannot single-step from Frida alone -- that's the gap GDB
and LLDB fill in this commit. dynamic-debug-overview SKILL is the
canonical decision guide for which lane to use.
Confidence: high
Scope-risk: narrow (additive plugin under plugins/, additive
.mcp.json; zero changes to existing source). Plugin loads via the
existing PluginManifestSchema path -- no new server-side code added.
Tested: bun run plugins/reverse-engineering/scripts/validate.ts (pass),
bun run plugins/reverse-engineering/scripts/smoke.ts (13/13 pass), live
chrome-devtools MCP smoke against running desktop UI verifying plugin
appears with correct version + counts.
Not-tested: real underlying-tool integration (Ghidra/r2/JADX/GDB/LLDB
must be installed by the user; the plugin only validates manifest
shape and component loading). Reverse-debugging (rr) flow is
documented in skills/gdb-debug but not exercised in smoke.
* fix: detect & isolate fake tool_use leaks from non-Anthropic providers
Some third-party Anthropic-compatible gateways (mimo, lgfzer, certain
proxies) don't relay native tool_use blocks: when the model wants to
call a tool, it ends up emitting an XML-style `<tool_use ...>{...}
</tool_use>` element as plain text inside content_delta. The desktop
chat renders that as markdown, marked passes the unknown element
through as raw HTML, the browser collapses whitespace, and the user
sees garbage like `<tool_useid="..."` followed by a smushed shell
command. Worse, the model has no signal the call never executed and
follows up with apologies ("工具用错了, 重来:") and retries — every
"call" is text and nothing runs.
Three layers of defense, lowest to highest in the stack:
1. **Source-side priming reduction** (server). The specialistRouter
docstring already warned that `key="value"` attribute fragments in
model-facing strings make some gateway models switch from real
tool_use blocks into XML mode. Three model-facing nudges still
embedded `subagent_type="verification"` in their reminders — fix
them to use prose ("set the subagent_type parameter to verification")
so we stop priming the failure mode:
- src/utils/messages.ts (verification_gate_reminder)
- src/tools/TodoWriteTool/TodoWriteTool.ts
- src/tools/TaskUpdateTool/TaskUpdateTool.ts
New regression test src/utils/noKeyValueNudges.test.ts pins all
three call sites so a future "typo fix" doesn't accidentally
re-introduce the attribute form.
2. **Detection + sanitization** (desktop). New
desktop/src/lib/fakeToolUseDetection.ts extracts XML-style
`<tool_use>` blocks (closed, half-open mid-stream, multiple
consecutive retries, `name`/`id` in either order, quoted or
unquoted, inside or outside fenced code blocks) and returns
`{ cleanText, blocks[] }`. AssistantMessage uses this before
handing content to MarkdownRenderer so the user never sees the
XML garbage; copyText also uses cleanContent so users don't paste
broken markup. Fenced code blocks (```xml ... ```) are preserved
so legitimate documentation examples render as-is.
3. **Provider compatibility tracking** (desktop). New
desktop/src/stores/providerCompatStore.ts counts fake tool_use
leaks per provider id, persisted to localStorage. After 3 leaks
it fires a one-time toast suggesting the user switch providers.
Settings → Provider list shows a "工具调用异常" badge on offending
providers; saving an edit on a flagged provider re-arms the
warning (clearProvider). Above-threshold detection is silent
afterward so we don't spam — the badge stays as the persistent
signal.
The new FakeToolUseNotice component renders an inline grey card
above the assistant bubble naming the attempted tool ("Bash") and
making it clear nothing ran, so the user knows not to trust any
follow-up "Done." claim that depended on the call's output.
Verified:
- desktop: bun run lint clean
- desktop: 28 new tests + existing AssistantMessage.linkrouting (15
total) pass
- server: 31 tests across verificationGate, specialistRouter, and the
new noKeyValueNudges regression all pass
Tested: bun run lint (desktop), bunx vitest run (3 desktop suites),
bun test (3 server suites)
Confidence: high
Scope-risk: narrow
---------
Co-authored-by: cc-haha <cc-haha@users.noreply.github.com>
Co-authored-by: 你的姓名 <you@example.com>
|
||
|
小橙子
|
9a0ae6a556
|
feat(desktop): make welcome task cards project-aware (#3)
Welcome-screen task cards previously rendered four hardcoded prompts
regardless of the actual repo state, so "PR pre-merge review" always
said `against main` and "fix failing test" / "write tests" always
showed `[fill in test name]` placeholders that the user had to edit
before sending.
Make each card's prompt resolve against live project context fetched
from `/api/projects/recent-activity`:
- preMergeReview now substitutes the actual `git.defaultBranch` so a
branch off `develop` no longer asks for a `main` review.
- investigateTest auto-suggests a recently-edited test file (matched
on `__tests__/`, `.test.*`, `.spec.*`, `_test.{py,go,rs}`) from the
new `dirtyFiles[]` list returned by recent-activity. Falls back to
the localized placeholder when no test is dirty.
- writeTests auto-suggests a recently-edited source file, skipping
test files, lock files, build output, and binary assets.
- Card 4 renamed from "解释陌生代码" / "Explain unfamiliar code"
→ "了解项目" / "Understand this project". The prompt is now a
project-overview brief (read CLAUDE.md/AGENTS.md/README, list tech
stack, top-level dirs, current branch state) rather than a
single-file explainer, which is what users actually want when they
open a fresh session.
- Soften preMergeReview wording from "三件事都要做完" to
"能合在一起做就一起做,你也可以根据改动量决定先做哪一件" so
small-diff PRs aren't forced through the full three-step ritual.
- Each card button now has the FULL resolved prompt as its native
`title` attribute, so users can hover to preview what they're about
to send before clicking — no surprises.
Server-side, `deriveGitActivity` runs `git status --porcelain=v1 -z`,
parses the NUL-separated paths (handles renames/copies safely), stats
each file for mtime, sorts DESC, caps at `DIRTY_FILES_SAMPLE_LIMIT=20`.
Cached behind the existing recent-activity TTL so the cards don't add
filesystem load.
`WelcomeTaskCards` now fetches its own project context internally
given a `workDir` prop, instead of receiving a pre-resolved
`projectContext`. Both call sites (`EmptySession`, `ActiveSession`)
pass `workDir` (and `excludeSessionId` from `ActiveSession` so we
don't accidentally pick the just-created empty session as "latest").
Verified end-to-end via Chrome MCP smoke on `feat/welcome-cards-polish`:
all four cards rendered with real `feat/welcome-cards-polish` branch
substituted in, dirty test/source files auto-filled, and clicking a
card prefilled the composer with the resolved prompt.
Tested: bun run lint, EmptySession.test.tsx (22/22 pass), Chrome MCP
smoke against running server + vite.
Confidence: high
Scope-risk: narrow
Co-authored-by: 你的姓名 <you@example.com>
|
||
|
小橙子
|
a7a48d15f3
|
feat: zero-prompt session handoff via two-layer LLM summary (#2)
* feat(server): two-layer session summary service for cross-session handoff
Backs the desktop "Continue from here" auto-handoff path. When a user
returns to a project to start a new chat session, the next-session AI
needs to know what the previous session was about; the existing
zero-token textarea-prefill carries 80 tokens of metadata that's good
for a human to read but useless for an AI ("title" alone tells it nothing
about the actual conversation). This service generates a compact
two-layer summary (project-level + recent-detailed) of the previous
session, caches it on disk, and lets the WS handler stage it as
`--append-system-prompt` on the next CLI launch so the receiving AI
starts with context but without paying for the whole prior transcript.
Token economics:
- One LLM call per session, capped at 1500 output tokens
(CLAUDE_CODE_HANDOFF_MAX_TOKENS, env-overridable).
- Input transcript is tail-sliced at 80k chars
(CLAUDE_CODE_HANDOFF_INPUT_CHARS) — recent context dominates the
hand-off, older turns drop first; tool uses are condensed to
one-liners so the input budget isn't spent on tool mechanics.
- Cached on disk as `<sessionId>.summary.json` next to the JSONL.
First call after a session has new turns (baseMessageCount drift)
triggers regeneration; otherwise it's an instant disk hit.
- Generation reuses the user's active provider via the same
resolution pattern as titleService.ts: prefer the configured
haiku/cheap model on the active provider, fall back to its main
model. OpenAI Codex (ChatGPT OAuth) path uses the existing
anthropicToOpenaiResponses + streaming response path.
- All failures degrade silently to `null` so the welcome-screen
falls back to the existing zero-token textarea prefill.
Wiring:
- sessionSummaryService.ts (NEW) exports getSessionSummary,
invalidateSessionSummary, and formatHandoffSystemPrompt for the
WS handler.
- sessions API gains GET/POST/DELETE /api/sessions/:id/summary.
- conversationService SessionStartOptions gets handoffSystemPrompt;
getRuntimeArgs appends it via --append-system-prompt independently
of orchestration so both can be active at once.
- WS handler adds `set_handoff_summary` ClientMessage type, an
in-memory handoffSummarySessions map (one-shot consumed at next
CLI start), getRuntimeSettings reads-and-deletes the staged
summary so unrelated restarts don't re-attach a stale prompt,
and session-end cleanup drops it.
Tested live via Chrome DevTools MCP (commit 2 covers the frontend
side):
- POST /api/sessions/<id>/summary on a 9-message transcript:
489 input + 335 output tokens, mimo-v2.5 produced clean two-layer
JSON, written to <sessionId>.summary.json (~3KB).
- Subsequent GET hits cache in ~40ms.
- End-to-end: clicked "Continue from here" → server resolved cached
summary → WS staged → CLI relaunched with --append-system-prompt
carrying the formatted hand-off → mimo received it and listed
exactly the modified files in the previous session it never saw,
correctly identifying `feat/session-handoff-summary` branch state.
Confidence: high
Scope-risk: moderate (new endpoint, new service, new WS message type,
new SessionStartOptions field; all read-only / append-only; failures
fall back to existing zero-token path).
Tested: live MCP smoke + targeted curl on this branch.
Not-tested: server-side unit tests for sessionSummaryService (planned
follow-up — covers JSONL parsing, transcript tail-slice, summary
parsing, cache staleness detection, formatHandoffSystemPrompt
formatting). Live integration validated the happy path end-to-end.
* feat(desktop): auto-handoff flow on "Continue from here"
When a user clicks the Recent activity panel's "Continue from here"
button, the desktop now resolves the previous session's two-layer
summary server-side, stages it as the next session's system prompt
addendum (via WS set_handoff_summary), and auto-sends a short trigger
message so the receiving AI starts with full context — no textarea
preview, no manual confirm. Falls back to the original zero-token
textarea-prefill path on any failure.
User flow:
1. User clicks "从这里继续" → button shows spinner + label
"正在准备上下文..." while the summary resolves.
2. projectsApi.resolveSessionSummaryForHandoff tries cache first
(instant) and only falls back to LLM generation on miss.
3. EmptySession path: createSession → connectToSession → WS
set_handoff_summary → sendMessage(continueTriggerMessage). Server
stages the summary in handoffSummarySessions and the next CLI
launch picks it up via --append-system-prompt.
4. ActiveSession's empty welcome state: same WS staging + auto-send
against the live session — server schedules a runtime restart so
the CLI relaunches with the hand-off context.
5. On any error (provider down / generation failed / network), card
falls back to dispatching the existing composer-prefill event with
the static hand-off paragraph; user can edit and send manually.
Files:
- desktop/src/api/projects.ts: SessionSummary type + getSessionSummary
+ generateSessionSummary (90s timeout — first generation can take
30-60s on long transcripts) + resolveSessionSummaryForHandoff helper
that prefers cache.
- desktop/src/components/welcome/RecentActivityCard.tsx: replaced
onApplyHandoff (sync, just writes to textarea) with onAutoHandoff
(async, host owns the full flow). Button shows progress_activity
spinner + i18n'd "preparing context..." label while the host's
promise is in flight; disabled during pending.
- desktop/src/pages/EmptySession.tsx, ActiveSession.tsx: implement
the host-side handoff flow — resolve summary, then either create
new session + WS stage + auto-send, or fall back.
- desktop/src/types/chat.ts: ClientMessage union gains
set_handoff_summary.
- i18n: 2 new keys per locale (handoffGenerating, continueTriggerMessage)
across en/zh/zh-TW/jp/kr.
Tested live (companion to ce53f503 server-side commit):
- Cache-hit path: card click → spinner ~50ms → new session → CLI
launched with --append-system-prompt → mimo-v2.5-pro received the
formatted hand-off and listed exactly the previously-modified files
on feat/session-handoff-summary, identified the feature state
correctly, and asked to verify TS — proving it had ground-truth
context from the previous session it never directly saw.
- Cache-miss path: ~10-15s LLM generation, button stays in loading
state, then proceeds.
- Failure path: simulated by manually breaking the provider URL —
button completes silently, textarea gets the fallback static
paragraph (existing zero-token path).
- Screenshot: artifacts/desktop-handoff-auto-resume.png
bun run lint passes (tsc --noEmit clean).
Confidence: high
Scope-risk: moderate (new auto-send-on-click behavior; mitigated by
silent fallback to existing textarea path and a generous timeout).
Tested: live MCP smoke for cache-hit happy path + manual failure path.
Not-tested: vitest unit tests for the new RecentActivityCard handoff
states (planned follow-up).
* fix(handoff): cache-only WS handler so summary generation can't double-run
Acted on a code review against the auto-handoff feature. Two findings,
one real one false-positive (left a defensive note for the false one
to keep future maintainers from "fixing" what isn't broken):
REAL ISSUE: handleSetHandoffSummary used getSessionSummary(), which
falls back to LLM generation on cache miss. The frontend's "Continue
from here" path always calls POST /api/sessions/:id/summary first
(which performs any needed LLM call), and only dispatches the WS
set_handoff_summary message AFTER the HTTP returned a successful
summary. So the WS handler should always find the cached summary on
disk. If it somehow doesn't, the OLD behavior would silently re-invoke
the LLM — blocking the WS handler for up to 60s and double-charging
the user. New behavior: read cache only, fail-fast with a clear
warning log if the cache is missing, and let the new session start
without hand-off context (the trigger message reads as a normal
"continue" prompt). Better than hanging or surprise-billing.
- sessionSummaryService.ts: new exported getCachedSessionSummary
helper — pure disk read, never calls the LLM.
- ws/handler.ts: handleSetHandoffSummary swapped over with a
detailed comment explaining the contract.
FALSE POSITIVE (kept as inline doc): the review claimed
EmptySession's flow has a race because wsManager.send happens before
the WS open. Actually wsManager.send tolerates a not-yet-OPEN socket
by queueing into pendingMessages and flushing on ws.onopen (see
desktop/src/api/websocket.ts). The current code is correct. Added a
defense-in-depth comment at the call site so a future "fix" doesn't
introduce an isConnected() gate that would break the contract.
Confidence: high
Scope-risk: narrow (one WS handler swap + one new export, no
behavioral change on the happy path; only the LLM-double-call edge
case is now fail-fast).
Tested: bun run lint passes (tsc --noEmit clean). Live MCP smoke
already covered the happy path on the previous commit; this commit
narrows a failure mode the smoke didn't actively exercise.
* feat(desktop): handoff progress stages + preview panel
Two UX additions on top of the auto-handoff flow:
1. Stage-aware progress label inside the "Continue from here" button.
Replaces the opaque "Preparing context..." spinner with a localized
walk-through:
preparing (default while host kicks off)
reading-cache (during the GET /api/sessions/:id/summary)
generating-summary (during the POST → LLM round-trip on cache miss)
starting-session (during createSession + WS staging + auto-send)
The card stays dumb — host calls a setStage(...) callback handed to
it as the third arg of onAutoHandoff. Card maps the stage to the
corresponding i18n key; defaults to "preparing" when the host hasn't
advanced. Falls back gracefully if a host doesn't call setStage at
all (the spinner just shows "preparing" the whole time).
2. "Preview summary" toggle next to "Continue from here". Click expands
a 280px-max scrollable inline panel showing the cached summary's
main + recent layers, plus a one-liner with the model used and token
counts. If no summary is cached yet (first time the user is about to
click Continue), the panel shows "尚未生成摘要…" so the user knows
what to expect.
Card fetches the cached summary on mount via projectsApi
.getSessionSummary (cache-only GET, never triggers an LLM call). The
fetch is opportunistic: if it fails or returns null, the preview
panel just shows the "no preview yet" hint.
i18n: 9 new keys per locale across en/zh/zh-TW/jp/kr — three stage
labels (handoffStage.readingCache, generatingSummary, startingSession),
preview toggle/close labels, three preview-panel section labels, and
the "no preview yet" placeholder.
Tested live in browser via Chrome DevTools MCP:
- Empty cache state: preview button visible, panel shows "no preview
yet" placeholder.
- Primed cache (mimo-v2.5 summary, 17.5s LLM call): reload → preview
panel renders with full main + recent content (292px high), token
metadata line at the bottom.
- Stage progression visible to the eye on the next "Continue from
here" click during the cache-miss path; cache-hit path skips the
"generating-summary" stage and goes straight to "starting-session".
- Screenshot: artifacts/desktop-handoff-preview-panel.png
bun run lint passes (tsc --noEmit clean).
Confidence: high
Scope-risk: narrow (UI-only additions; existing onAutoHandoff signature
gained a third arg, both hosts updated; default value pathway preserved
when callers don't use setStage).
* feat(desktop): handoff chip in chat header + tests
The previous commits in this PR plumbed in the auto-handoff machinery
(server summary service, frontend resolution + auto-send, progress
stages, preview panel). What's missing is a *persistent visual signal*
in the active chat that the AI was bootstrapped with prior context.
Without it, a returning user sees an ordinary chat with no hint that
they pre-loaded a summary, and may distrust or forget that context is
present.
This adds a small chip in the ActiveSession chat header next to the
existing token / message-count chips:
↗ 接续上次 (639 t)
with a hover tooltip:
接续自"<previous session title>"。AI 启动时已带上了 639 tokens
的上次会话摘要作为系统提示。
The chip is purely informational — clicking does nothing. Token count
is a frontend-side estimate (chars / 4) of the staged summary's
main+recent text size, so it tells the user "roughly how big is the
hand-off addendum in my system prompt right now". The exact tokens are
also surfaced server-side in ContextUsageIndicator's "System prompt"
category, so this chip doesn't double-count.
Plumbing:
- sessionRuntimeStore gains a new handoffInfo: Record<sessionId,
SessionHandoffInfo> field, persisted to localStorage under
cc-haha-session-handoff. Mirrors the existing coordinatorModes
pattern: setHandoffInfo / clearHandoffInfo actions, automatic
cleanup in clearSelection and migration in moveSelection so the
drafts → real-session-id transition during session creation
doesn't lose the handoff record.
- SessionHandoffInfo carries previousSessionId, snapshotted previous
title, approxTokens, and generatedAt for staleness display.
- RecentActivityCard's onAutoHandoff signature gains a third arg
previousSessionTitle so the host can stash it without re-fetching
the recent-activity payload.
- EmptySession + ActiveSession hosts call setHandoffInfo on the
target session right before WS staging, so the chip lights up the
moment the new session opens (or the live session is restarted).
- i18n: 2 new keys per locale (session.handoffChip,
session.handoffChipTooltip).
Tests: new desktop/src/stores/sessionRuntimeStore.test.ts with 6
focused tests:
- setHandoffInfo persists to store + localStorage
- clearHandoffInfo removes selectively
- clearHandoffInfo on missing key is a no-op
- clearSelection cleans up handoffInfo for the same key
- moveSelection migrates handoffInfo from draft → real key
- handoffInfo and coordinatorModes are independent
Verified live in the browser via Chrome DevTools MCP:
- Click "Continue from here" → cache-hit summary path → chip appears
in the new session's header showing exact previous title and
639-token approx count.
- localStorage persists across reload (chip survives F5).
- Multiple sessions: the chip is per-session, cleared on session
close (via clearSelection wiring).
- Screenshot: artifacts/desktop-handoff-chip-in-header.png
bun run lint passes (tsc --noEmit clean).
bun run vitest passes for chatStore + EmptySession (124/124) +
sessionRuntimeStore (6/6 new).
Confidence: high
Scope-risk: narrow (one new persisted store field, additive UI in the
header, no behavioral change on the handoff path itself).
---------
Co-authored-by: 你的姓名 <you@example.com>
|
||
|
程序员阿江(Relakkes)
|
0d45439fbe |
feat(trace): add session trace monitoring (#606)
Tested: - cd desktop && bun run test -- --run src/pages/TraceList.test.tsx - bun test src/server/__tests__/trace-capture.test.ts - bun run check:desktop - bun run check:server Scope-risk: broad |
||
|
程序员阿江(Relakkes)
|
56661c7967 |
fix: support desktop output style config (#652)
Fixes #652. Add desktop/server output style settings APIs and a General Settings picker that mirrors the Claude CLI outputStyle sources. Persist active-project choices to .claude/settings.local.json and global choices to user settings, and route /config to the local settings UI. Tested: - bun test src/server/__tests__/settings.test.ts - cd desktop && bun run test -- src/components/chat/composerUtils.test.ts src/stores/settingsStoreOutputStyle.test.ts src/pages/SettingsOutputStyle.test.tsx - cd desktop && bun run test -- src/__tests__/generalSettings.test.tsx - bun run check:desktop - bun run check:server - bun run verify Confidence: high Scope-risk: moderate |
||
|
你的姓名
|
f41d88673d | release: v0.5.7 | ||
|
你的姓名
|
ae533041de |
fix(thinking): default any third-party Anthropic-compatible proxy to thinking-capable
Two fixes that together unblock visible thinking on third-party Anthropic proxies (mimo, lgfzer, kiro-account-manager loopback, etc.): 1. src/utils/thinking.ts: when the API provider is firstParty but the base URL is not Anthropic's own, treat the gateway as thinking-capable rather than relying on a per-host whitelist. Drops the dead isMiniMaxAnthropicEndpoint helper. SUPPORTED_CAPABILITIES=none still opts out for any endpoint that genuinely cannot return reasoning. 2. desktop ThinkingBlock now defaults to expanded so reasoning is visible the moment thinking deltas start arriving, matching the streaming experience users expect from reasoning models. Click still toggles. Verified end-to-end against mimo-v2.5-pro through the desktop UI: thinking content streams in 40-110 char increments over a few seconds with the "思考中" cursor visible, then collapses to "已思考" on completion. Tested: - src/utils/__tests__/thinking.test.ts (113 utils tests pass) - desktop ThinkingBlock.test.tsx + chatBlocks.test.tsx (16 tests pass) - Live mimo SSE probe confirms many small thinking_delta events upstream - Browser MCP smoke: complex prompts show real-time thinking growth Confidence: high Scope-risk: narrow |
||
|
小橙子
|
1401107509
|
feat: harden agent routing, ship welcome surfaces, and unblock browser MCP smoke (#1)
* feat(agent-tool): rewrite contradictory review verdicts at the harness layer
The code-reviewer and security-reviewer subagents end with a parseable
verdict (`REVIEW: APPROVE` / `SECURITY: PASS`) and their prompts forbid
emitting the positive form alongside `[CRITICAL]` or `[HIGH]` findings.
That rule is enforced only in prose, so when the model slips, the
parent agent reads "APPROVE" and ships.
Add a pure post-processing pass over the subagent's final text in
`finalizeAgentTool`: detect the verdict line, look for severity tags
above it, rewrite to `CHANGES_NEEDED` when they conflict, and prepend
a one-line audit notice so the parent (and a human reading the
transcript) can see the harness intervened. Logs a
`tengu_agent_sentinel_mismatch` analytics event for fleet visibility.
Debugger's `ROOT CAUSE: FOUND` is intentionally out of scope — its
"evidence from a real command" rule isn't mechanically verifiable.
Tested: bun test src/tools/AgentTool/sentinelCheck.test.ts (11 cases)
Confidence: high
Scope-risk: narrow
* feat(agent-tool): show subagent_type in tool-use transcript line
Each `Agent` tool call previously rendered as just its description in
the transcript, which made it invisible whether the main agent picked
a specialist or fell back to the default. Diagnosing "why didn't it
use code-reviewer?" required reading analytics or guessing.
Append `→ <subagent_type>` to the rendered description when the type
is explicit. Omitted (general-purpose default or fork) keeps the old
format — absence of the marker is itself the signal.
Tested: visual smoke only — pure UI render change with no behaviour
Confidence: high
Scope-risk: narrow
* feat(agent-tool): nudge verification subagent after edits accumulate
Verification is the only built-in agent that's *required* by the
session-specific guidance for non-trivial implementations, but the
trigger condition ("3+ file edits / backend / infra change") is
evaluated by the main agent from its own work — a classic LLM
self-audit failure mode. The model can convince itself that 4 edits
"are mostly one core change with small adjustments" and skip
verification entirely.
Add a `verification_gate_reminder` attachment that fires once when
the main thread accumulates `editCount >= threshold` (default 3)
file-mutating tool uses (Edit / Write / NotebookEdit) without
invoking the verification subagent. The reminder renders as a
`<system-reminder>` block on the next turn telling the model to
spawn `subagent_type="verification"` before reporting completion,
along with a permission to skip if the change is genuinely trivial.
A verification subagent invocation resets the counter; a previously
fired reminder suppresses re-firing until the next reset, so the
nudge isn't spammed every turn.
Subagents don't see the reminder (it's main-thread only). The gate
also no-ops when the verification agent isn't loaded in the current
session (e.g. SDK build with built-ins disabled). Disabled by
`CLAUDE_CODE_VERIFICATION_GATE_OFF=1`; threshold tuned via
`CLAUDE_CODE_VERIFICATION_GATE_THRESHOLD=N`.
Tested: bun test src/utils/verificationGate.test.ts (10 cases)
Confidence: high
Scope-risk: moderate
* feat(agent-tool): tighten subagent routing and ship real coordinator mode
The flat 15-agent routing has three known weak spots that this commit
addresses together because they share AgentTool.tsx call-path edits:
1. **General-purpose default is a vacuum cleaner.** Omitting
`subagent_type` falls back to general-purpose, which has full tool
access and cheerfully takes on review/security/perf/migration work
that a specialist would have done better and cheaper. Add a regex
heuristic over the prompt: when it strongly signals a specialist
(e.g. "code review", "security audit", "root cause", "migrate from
X to Y") and that specialist is available, refuse the default and
throw an error pointing the model at the right type. Disabled with
`CLAUDE_CODE_GP_DEFAULT_STRICT=0`. Skipped in fork and coordinator
modes (they have their own routing).
2. **No bound on verifier-style loops.** The verification prompt says
"On FAIL: fix, resume, repeat until PASS" — if the verifier
incorrectly keeps flagging the same change, the loop only stops
when the token budget runs out. Add a per-session counter for each
built-in agent type. Cap defaults are 5 for verification (loop
target) and 8 for everything else. When exceeded, throw with a
message asking the model to consult the user. Caps tunable per
type via `CLAUDE_CODE_AGENT_LIMIT_<TYPE>=N`; off via
`CLAUDE_CODE_AGENT_LIMITER_OFF=1`. Counts main-thread invocations
only.
3. **Coordinator mode was a stub.** The `coordinator/workerAgent.ts`
that `getBuiltInAgents()` requires when `COORDINATOR_MODE` is on
was an auto-generated Proxy returning nothing useful. Replace with
a real registry: a new `WORKER_AGENT` (full-tool-access generic
delegate matching the existing coordinator prompt's
`subagent_type: "worker"` references) plus the 11 specialists
minus general-purpose, claude-code-guide, statusline-setup. Also
harden the coordinator's own prompt with a "you orchestrate, you
do not implement" rule (no direct Edit/Write/NotebookEdit) and a
specialist roster table so the coordinator picks the right
delegate. Improve the AgentTool error message when coordinator
mode receives a request without `subagent_type`.
Constraint: cannot restrict the coordinator's own tool pool at the
tool layer without invasive changes to main-thread tool assembly —
enforcement is prompt-level, consistent with the rest of the
architecture.
Rejected: a tighter heuristic that requires a domain-specific phrase
(e.g. "review THIS PR") was considered for #1 but rejected — too
narrow to catch the routing problems we actually see in fleet logs.
Tested: bun test src/tools/AgentTool/specialistRouter.test.ts
bun test src/tools/AgentTool/invocationLimiter.test.ts
bun test src/coordinator/workerAgent.test.ts
(29 cases total, all pass)
Confidence: medium
Scope-risk: moderate
Directive: if specialistRouter false-positives in production, prefer
tightening the regexes over removing the gate — the failure mode
it catches (general-purpose taking specialist work) is worse than
the failure mode of an extra retry.
* docs(desktop): add local Chrome DevTools MCP testing guide
Document the workflow for driving the desktop UI end-to-end via
Chrome DevTools MCP without going through Electron. The pure-browser
dev path normally fails — CSP blocks non-loopback origins, the
H5-disabled CORS gate blocks cross-origin browsers, and the desktop's
loopback exemption clears the H5 token so even the loopback path
401s. The stable bypass is a Vite proxy that same-origins API
traffic to the renderer.
This commit covers the docs side only:
- `docs/desktop/10-local-mcp-testing.md`: full how-to with Quick
Start, MCP control snippets, can/can't test matrix, the exact
reproduction recipes for each `feat/agent-routing-hardening`
change (sentinel, gp-strict, limiter, verification gate, routing
observability), a Windows-specific `electron:dev` workaround, and
a fault dictionary mapping the symptoms each blocker produces back
to its cause.
- `docs/desktop/index.md`: link the new section in the docs index.
- `.kiro/steering/desktop-mcp-testing.md`: concise rule file with
`inclusion: manual` so it loads via #-mention only when relevant,
not as default-included context.
The Vite proxy itself is intentionally NOT committed here. The docs
explain it as a dev-only change the developer adds locally and
either reverts or commits to a separate `feat/desktop-browser-dev-proxy`
branch — the production renderer relies on Electron IPC for the
server URL and must not see the dev proxy in main.
Tested: docs render via VitePress local preview; steering file
loads via Kiro `#desktop-mcp-testing` mention; instructions
verified against the live setup that produced
artifacts/desktop-bootstrapped.png and artifacts/desktop-agents-page.png.
Confidence: high
Scope-risk: narrow
* feat(desktop): unblock pure-browser dev MCP smoke with proxy + forceH5
The standalone-browser dev workflow (vite + Chrome DevTools MCP)
fails three ways without these escape hatches:
1. CSP `connect-src` only allows loopback origins, so the renderer
can't talk to the API server cross-origin even on a LAN.
2. With H5 access disabled the server returns 403 to all
cross-origin browser requests.
3. With H5 access enabled the desktop's loopback exemption
(`requiresH5AuthForServerUrl` returns false for `localhost:1420`)
calls `setAuthToken(null)`, so `buildSessionWebSocketUrl` omits
`?token=`, and the session WS handshake 401s into a 1006 close
reconnect loop. The UI shows "处理中..." but the message never
reaches the server — `wsManager.connections` stays `{}`, server
stdout is silent, and no `POST /api/sessions/.../message` ever
fires.
Two dev-only changes break that deadlock without affecting
production:
- `desktop/vite.config.ts`: add `server.proxy` for `/health`,
`/api`, `/ws`, `/local-file`, `/preview-fs` to `127.0.0.1:3456`.
Same-origins all backend traffic so CSP and CORS pass. Vite dev
only — Electron production path is unaffected because Electron
resolves the server URL via IPC at runtime.
- `desktop/src/lib/desktopRuntime.ts`: add a `?forceH5=1` query
param check in `initializeBrowserServerUrl`. When present, treat
the URL as needing H5 auth even if it's loopback, so the H5 token
survives bootstrap and gets attached to the session WS URL. In
production the param is never set, so behavior is identical.
Workflow with both in place:
http://localhost:1420/?serverUrl=http%3A%2F%2Flocalhost%3A1420
&forceH5=1&h5Token=<TOKEN>
Verified end-to-end via WS sniffer + server log:
- ws://localhost:1420/ws/<sid>?token=... opens
- recv {"type":"connected","sessionId":"..."}
- server logs "[WS] Client connected" + "Starting CLI for ..."
- Sending a "use Task with subagent_type=Explore" prompt produced
a `tool_use_complete` for the Agent tool with
`input.subagent_type="Explore"` exactly as routed.
Also rewrites `docs/desktop/10-local-mcp-testing.md` to record:
- both patches as required steps (was missing the forceH5 piece)
- exact PowerShell commands to mint a one-shot H5 token
- the WebSocket sniffer script and three-signal diagnosis recipe
for "is the backend actually processing"
- the Item 5 (routing observability) gap: the change in
`src/tools/AgentTool/UI.tsx` only affects CLI/Ink rendering;
the desktop's separate `ToolCallGroup.tsx` doesn't surface
`subagent_type` and would need its own follow-up patch.
Tested: ran `bun run src/server/index.ts` + `bun run dev` in the
desktop/, opened the documented URL via Chrome DevTools MCP,
sent a Task-with-explicit-subagent_type chat message, observed
the full WS frame sequence and server log lines listed above.
Confidence: high
Scope-risk: narrow
Directive: do not generalize the forceH5 escape hatch to a
permanent feature — when it's needed, the dev-mode
loopback-clears-token branch is doing the right thing for
Electron and should not be removed.
* feat(desktop): show subagent_type badge next to Agent tool header
The CLI/Ink change in src/tools/AgentTool/UI.tsx surfaces routing
in the terminal transcript as `<description> → <subagent_type>`,
but the desktop renderer is independent (`ToolCallGroup.tsx` /
`AgentCallCard`) and was dropping that signal entirely. Diagnosing
"why didn't it use code-reviewer?" required reading analytics or
guessing.
Add a small `→ <subagent_type>` chip next to the Agent header in
AgentCallCard. The badge mirrors the CLI behavior:
- Renders only when `input.subagent_type` is a non-empty string;
general-purpose / fork / omitted defaults stay quiet.
- Carries `title="subagent_type: <name>"` for hover detail.
- Uses the same border-pill treatment as other secondary
transcript chips so it doesn't compete with the description.
Verified end-to-end via the local Chrome DevTools MCP path: a
real chat with `subagent_type=Explore` renders `Agent → Explore
查找specialistRouter相关文件` in the live transcript, screenshot
saved to artifacts/desktop-routing-arrow-highlighted.png.
Tested: cd desktop && bun run test -- --run -t "subagent_type"
2 tests pass:
- renders subagent_type as → Explore badge next to Agent header
- omits subagent_type badge when input has no subagent_type
Confidence: high
Scope-risk: narrow
* feat(desktop): MCP tool visibility, per-tool toggle, marketplace install
Surface MCP capabilities so the agent never under-uses a configured server,
and add a one-click install path for new servers.
Tool visibility & control:
- GET /api/mcp/:name/tools returns the live tool catalog (handles disabled /
needs-auth / host-preflight-failed / connected states)
- POST /api/mcp/:name/tools/:tool/toggle hides a single tool from the agent,
persisted to ~/.claude.json disabledMcpTools (user scope, all projects);
fetchToolsForClient filters on it and the cache is invalidated on toggle
- Desktop MCP detail page gains an Overview/Tools tab strip (both edit and
read-only views) listing name, description, annotations, JSON schema, plus
an inline enable/disable switch with a "hidden from agent" marker
Marketplace:
- Curated builtin catalog (14 servers across 8 categories) plus opt-in remote
catalog sources cached under ~/.claude/cc-haha/mcp-marketplace.json
- Endpoints: list / refresh / add-source / remove-source
- Desktop marketplace page with category grouping, install dialog (with
required-env prompts), and source management
Plugins:
- Plugin list rows get inline enable/disable + uninstall, matching the MCP
settings UX, instead of requiring users to open the detail panel
- Extract shared ToggleSwitch component
Tested: bun test src/server/__tests__/mcp.test.ts (tools list + per-tool
toggle + marketplace), cd desktop && bun run lint, mcpSettings vitest, and a
browser smoke pass via the local Chrome DevTools MCP flow (tool toggle
persistence, marketplace render, plugin enable/disable + uninstall dialog).
Not-tested: full bun run verify gate
Scope-risk: moderate
* fix(agent-tool): rephrase gp-strict error to stop poisoning sessions
Live testing surfaced an unintended side effect of the gp-strict
redirect message. The original wording embedded attribute-style
fragments like `subagent_type="code-reviewer"`. When that error
came back to the model as a tool result, the model copied the
shape into a TEXTUAL `<tool_use name="Agent">{...}` block instead
of issuing a real tool call — and every subsequent Agent call in
that session degraded to text. Confirmed by inspecting the
session JSONL via /api/sessions: messages 4..N in the affected
session were `assistant: text(...)` carrying simulated tool_use
XML, not `tool_use` content blocks. Reproduced with two unrelated
models (claude-haiku-4.5 and mimo-v2.5-pro) on the same poisoned
session, and crucially DID NOT reproduce in a fresh session with
either model — so the failure is the message text inducing
text-form mimicry, not the model itself.
Fix:
- Extract the redirect text into `formatSpecialistRedirectMessage`
in specialistRouter.ts so it has its own test surface.
- Rephrase as prose that names the parameter and value without
any `key="value"` assignment-and-quotes form. New shape:
"This task looks like a job for the code-reviewer specialist
rather than the general-purpose default. Re-call Agent with
the subagent_type parameter set to code-reviewer. ..."
- Wire AgentTool.tsx through the helper so the throw site is one
line.
Add a regression assertion to specialistRouter.test.ts that the
formatted message contains NO `key="value"` shapes, no XML-ish
open tags, and no `"subagent_type":` JSON fragments — across all
ten specialist names. This is the property the live failure
violated; lock it.
The invocation-limiter message uses shell-style `KEY=N` syntax
(not `key="value"`), did not exhibit the same behavior in
testing, and is left untouched.
Tested: bun test src/tools/AgentTool/specialistRouter.test.ts
17 pass (13 existing + 4 new), 61 expect() calls
Confidence: high
Scope-risk: narrow
Directive: any future change to redirect/error text returned
to the model should preserve the no-key="value" property.
* feat(orchestration): require copying project tool rules into sub-agent prompts
Live test on the desktop `+` orchestration mode showed mimo-v2.5-pro fan
out three sub-agents in parallel for a multi-task PR review prompt — but
none of the dispatched prompts mentioned the project's mandated codegraph
MCP tool. The sub-agents fell back to plain Bash + git diff + grep, so the
project's preferred code-exploration tooling went unused.
Root cause: the orchestrator's `Propagate project conventions` rule was a
soft "for example, restate codegraph rules" bullet. The model read it as
optional. Built-in specialist system prompts (code-reviewer, security-
reviewer, debugger, etc.) explicitly enumerate Bash/grep/git as inspection
tools and never mention codegraph; CLAUDE.md is loaded but the system
prompt outweighs it. The orchestrator was the only place the gap could be
closed, and it skipped it.
This commit upgrades the rule from optional to REQUIRED in the
orchestration system prompt, names the concrete check ("scan CLAUDE.md,
AGENTS.md, .claude/rules"), and tells the orchestrator to copy matching
rules verbatim. Read-only research agents (Explore, Plan) are called out
explicitly because they run with omitClaudeMd:true and absolutely depend
on the orchestrator to forward project tool conventions.
A new ORCHESTRATION_PROPAGATE_RULES_MARKER export plus a regression test
in conversations.test.ts lock the imperative phrasing so it can't be
quietly downgraded back to a soft suggestion.
Wiring is unchanged: built-in code-reviewer/security-reviewer/commit-pr
already inherit CLAUDE.md and have MCP tools available. This is purely a
prompt-strength change, only active when the user enables the desktop
`+` orchestration toggle.
Tested: bun test src/server/__tests__/conversations.test.ts (new test
plus the two existing orchestration-prompt tests pass).
Confidence: high
Scope-risk: narrow
* fix(verification-gate): preserve reminder flag across verification reset
Caught by an orchestrator-mode code-reviewer dispatch on this branch.
When a verification subagent invocation reset the edit counter, the early
return in getVerificationGateState() hardcoded reminderAlreadyFired:false,
discarding any reminderFired flag we'd accumulated walking back from the
tail. Concretely: if a verification_gate_reminder fired AFTER the verify
(i.e. newer than verify in the transcript), the reverse walk would set
reminderFired=true on its way to the verify boundary, then throw it away
on the early return. The gate would then inject a fresh reminder every
turn while the post-verify edit count stayed above the threshold,
ballooning the prompt.
Fix: carry the accumulated reminderFired through the early return. The
reminder we saw is necessarily newer than this verify (we're walking
backwards from the tail and only got here after seeing it), so it's the
valid signal that the model was already nudged for the current edit batch.
Tests: extend verificationGate.test.ts with a "preserves a reminder fired
AFTER a verification reset (no spam loop)" case that fails on the old
hardcoded false and passes with the fix. The pre-existing "ignores a
reminder that fired BEFORE a verification reset" test still passes because
in that ordering the reminder is older than the verify, so reminderFired
stays false on the way back.
Tested: bun test src/utils/verificationGate.test.ts (11/11 pass).
Confidence: high
Scope-risk: narrow
* chat(i18n): rename `协调模式` to `编排模式` (zh / zh-TW)
Brings the simplified- and traditional-Chinese label for the desktop `+`
menu's orchestration toggle in line with the English (Orchestration mode),
Japanese (オーケストレーションモード), and Korean (오케스트레이션 모드)
labels — all five locales now use the same `orchestration` word family.
`协调` was accurate but vague; `编排` matches the term Chinese
developers already see in LangChain, CrewAI, AutoGen, and Anthropic docs,
and tells a user reading just the label what the toggle actually does
(plan → fan out → synthesize) rather than a generic `coordinate`.
UI-text only. No behavior, store, WS message, or i18n-key changes.
* feat(desktop): welcome-screen task cards with one-click orchestration
Adds four quick-start task cards to the new-session welcome screens — both
EmptySession (the no-session-yet entry) and ActiveSession's empty state
(when a fresh session tab has no messages yet). Each card pre-fills the
composer with a starter prompt for a common workflow:
- Pre-merge code review (auto-enables Orchestration mode)
- Investigate a failing test (auto-enables Orchestration mode)
- Write unit tests (no orchestration)
- Explain unfamiliar code (no orchestration)
Cards flagged `orchestrate: true` automatically turn on Orchestration
mode for the session that gets created (or for the live session in
ActiveSession's empty state), so a new user sees fan-out behavior on
first contact instead of having to discover the `+` menu first. This is
the intended discovery surface for the orchestration directive shipped on
this branch.
Plumbing:
- WelcomeTaskCards.tsx is a shared component used by both welcome
surfaces, so card list, copy, and styles stay in one place.
- EmptySession owns its own composer textarea, so card click flips
component state directly (setInput + draftOrchestrate flag) and the
flag is applied via setSessionCoordinatorMode after createSession()
resolves and before connectToSession() — chatStore replays the
persisted toggle on connect, so the CLI launches with the right
--append-system-prompt.
- ActiveSession's session is already live, so a card click dispatches a
`cc-haha:composer-prefill` window event that ChatInput listens for
and applies to its composer state when the sessionId matches the
active tab. Orchestration cards call setSessionCoordinatorMode
directly, which sends `set_coordinator_mode` over WS and triggers a
CLI restart with the orchestration directive — verified live: the
server logs `[WS] Restarted CLI for <id> with runtime override`
immediately after the click.
- Cards never disable an existing Orchestration toggle. Non-orchestration
cards simply leave the toggle alone, so users who pre-enabled
Orchestration via the `+` menu don't have it silently turned off.
- Hidden on phone-sized H5 viewports (composer is already dense there).
i18n: ten new keys under `empty.tasks.*` with localizations for en,
zh, zh-TW, jp, kr (the same five locales the orchestration label
already covers). The orchestration hint reads `将通过编排模式分派给
专家子代理处理` in zh — aligning with the
`协调模式`→`编排模式` rename shipped in the previous commit.
Tests: five new tests in EmptySession.test.tsx covering: cards render on
desktop, hidden on mobile, click pre-fills the composer, orchestration
cards persist coordinator mode after submit, non-orchestration cards
leave coordinator mode untouched. `bun run vitest` 22/22 pass.
`bun run lint` (tsc --noEmit) clean.
Tested live in browser: clicked the Pre-merge review card → composer
filled with the 78-char zh prompt → localStorage carries
`coordinator-modes[<sessionId>]: true` → server log shows the CLI
restarted with `--append-system-prompt`. Screenshot:
artifacts/desktop-welcome-task-cards.png.
Confidence: high
Scope-risk: narrow
* chore(scripts): one-click MCP smoke setup for Windows
Wraps the recurring 4-step setup from docs/desktop/10-local-mcp-testing.md
into a single idempotent script. Same workflow we'd otherwise type by hand
every time we want to drive the desktop UI from Chrome DevTools MCP.
scripts/dev-mcp-test.ps1 does:
1. Health-check the API server on :3456 — fail fast with the start
command if it's down.
2. Health-check Vite on :1420 — fail fast with the start command if
it's down.
3. Confirm Vite's /health proxy is wired through to the server (catches
stale vite.config.ts).
4. Ensure http://localhost:1420 is in H5 allowedOrigins (PUT only when
missing).
5. Regenerate a fresh H5 token via /api/h5-access/regenerate.
6. Build the full URL with serverUrl + forceH5=1 + h5Token, copy it to
the clipboard, and print it.
7. With -Open, also Start-Process the URL in the default browser.
8. With -Quiet, only print the URL on stdout (for piping into other
tools, e.g. un run mcp:test:open chaining).
Surfaced via two npm scripts:
bun run mcp:test # generate URL + clipboard
bun run mcp:test:open # also open in default browser
Deliberate non-goals:
- Does NOT start server / Vite. Those are persistent dev processes the
developer wants to control lifecycle for; auto-starting them from a
one-shot script makes "is it still running?" questions ambiguous and
leaves zombies on script exit. The script tells the user the exact
command to run if either is down.
- Does NOT touch Electron. This workflow is the documented browser path
for Chrome DevTools MCP smoke; the Electron path doesn't need any of
this and runs through bun run electron:dev.
- Does NOT modify vite.config.ts proxy or desktopRuntime.ts forceH5
bypass. Both are already on this branch, and validation of those two
being correctly wired is what step 3 covers.
Doc: docs/desktop/10-local-mcp-testing.md grew a new "step 0 一键脚本"
section pointing at the script and naming the two npm targets, ahead of
the original 4 manual steps so future maintainers find the script first.
Verified by running it: server + vite both up, allowedOrigins pre-existed
so no PUT needed, fresh token issued, URL copied to clipboard, browser
launched into the welcome screen with the four task cards rendering
correctly. Screenshot in artifacts/desktop-welcome-task-cards-final.png.
Confidence: high
Scope-risk: narrow
* feat(desktop): zero-token "Recent activity" panel with hand-off button
Closes the painful gap where opening a new chat in a project means
re-explaining "what was I just doing" to the model. The user explicitly
called out that they don't want the obvious fix (auto-feeding the
previous transcript or an LLM-generated summary) because that burns
tokens on every new session.
This ships a different shape: derive the activity summary on the server
from on-disk state (session JSONL + git working tree), render it as a
read-only panel on the welcome screen so the user sees it, and only
move bytes into the model when the user explicitly clicks "Continue
from here" — and even then, only a 4-5 line hand-off paragraph (~60
tokens), not the previous transcript.
Server (zero LLM, all derivation):
- GET /api/projects/recent-activity?workDir=<abs>&excludeSessionId=<id>
- projectActivityService.getRecentActivity reads:
- sessionService.listSessions to find the most recent meaningful
session (skips empty messageCount=0 sessions and any
excludeSessionId, e.g. the just-created Untitled tab in
ActiveSession's empty welcome state, so the panel surfaces the
ACTUAL previous work session).
- Streams that session's JSONL and derives:
* lastUserMessageExcerpt (160 chars max, mid-word ellipsis)
* filesEdited list — Edit/Write/NotebookEdit tool_use file_paths,
de-duplicated in first-appearance order, capped at 8.
Hard-capped at 50k JSONL lines so giant transcripts don't hang
the welcome render.
- getRepositoryContext (existing, cached) for branch + default
branch + dirty state, plus two cheap git rev-list/status calls
for ahead/behind counts and exact dirty file count.
- Strict timeouts on each git command so the panel never blocks UI.
- Wired into router.ts under case 'projects'.
Frontend:
- RecentActivityCard reads via projectsApi.recentActivity.
- Two paths into it:
1. EmptySession (sidebar "New session" → user picks workDir):
shows once a workDir is chosen. "Open this session" switches
to the previous tab; "Continue from here" prefills the
hand-off into the empty composer's textarea.
2. ActiveSession's empty welcome state (sidebar "在 X 中新建会话"
creates a session immediately): excludeSessionId={activeTabId}
skips the brand-new empty session, hideContinueSessionButton
hides "Open this session" since the user is already on an
empty tab. "Continue from here" dispatches the existing
cc-haha:composer-prefill window event so ChatInput picks it
up — same plumbing the welcome task cards use.
- Auto-refreshes every 60s — git state changes between renders
(commits in another terminal, etc.) get picked up without UI work.
- Hidden on phone-sized H5 (composer is dense enough already).
Hand-off paragraph contents (i18n'd, ~60-100 tokens):
Last session on <branch>: "<title>".
Files touched: <up-to-5-files> (+N more).
Local is ahead of upstream by N commit(s).
N file(s) have uncommitted changes.
Please continue from there. Pick up by ...(describe the next step).
Token cost summary:
- Render: 0 tokens. Pure on-disk derivation, never sent to a model.
- "Open this session": 0 tokens. Just a tab switch.
- "Continue from here": ~60-100 tokens, ONLY if the user types more
and presses send. The user sees the prefill in the textarea before
sending and can edit or delete it.
i18n: 18 new keys (empty.recentActivity.*) localized for the same five
locales as the orchestration toggle (en/zh/zh-TW/jp/kr).
Live-tested via Chrome DevTools MCP on this branch:
- Opened cc-haha welcome path.
- Server returns correct shape: branch=feat/agent-routing-hardening,
aheadCount=6, dirtyCount=13, lastSession with 10 messages and
correct title.
- excludeSessionId correctly skips the empty just-created session and
surfaces the previous "请审查我当前分支..." session.
- "Continue from here" click prefills the textarea with the 152-char
Chinese hand-off paragraph; localStorage and WS state untouched
(zero token cost confirmed).
- Screenshots: artifacts/desktop-recent-activity-card.png and
artifacts/desktop-recent-activity-handoff.png.
bun run lint passes (tsc --noEmit clean).
Confidence: high
Scope-risk: moderate (new endpoint, but read-only and isolated; new UI
panel, but additive only — empty workdir or no prior sessions just
hides the card)
Tested: live MCP smoke per above.
Not-tested: server-side unit tests for projectActivityService (planned
follow-up; live integration validated the happy path end-to-end).
* fix(desktop): compact recent-activity card so composer stays in view
Live MCP smoke caught a layout regression. Welcome screen vertical
budget on a 923px viewport is roughly:
79 tab bar
+ ~250 hero block (logo + title + subtitle)
+ ~165 task cards
+ ~222 composer (ChatInput in hero variant)
+ ~64 flex padding
≈ 780px before activity panel
The first cut of RecentActivityCard rendered a 235px column block
(title row, chips row, italic excerpt row, file-chips row, action row).
Together with the task cards that pushed total content to ~410px
beyond what fits, and ActiveSession's empty-state wrapper used
flex flex-1 + justify-center without overflow handling — so the
sibling ChatInput got pushed below viewport bottom (composer.bottom
1112 on a 923 viewport, visible:false confirmed via DOM measurement).
Two changes:
1. Compact the card to ~127px (down 108px, roughly half) by collapsing
to a single horizontal row: icon | title + chips column | action
buttons. The italic last-user-message excerpt and the file-name
chip strip both go away — they're nice-to-haves, not load-bearing.
The data they carried is preserved: filesEditedCount stays as a
chip with a tooltip showing the first 5 file basenames; the lead
excerpt is still in the hand-off paragraph the "Continue from here"
button injects, so the user gets it where it counts (in the
composer) instead of as ambient ornament on the welcome screen.
Action buttons collapse their labels under sm: breakpoints to keep
the card single-row even in narrow side panels.
2. Add min-h-0 + overflow-y-auto to ActiveSession's isEmpty wrapper.
Belt-and-suspenders: future taller content (extra cards, longer
localized strings) now scrolls inside the welcome region instead of
shoving the composer offscreen. Composer remains a flex sibling and
stays anchored at the bottom regardless of content height above it.
Verified live in MCP browser:
recentActivity height: 235 → 127px
composer.bottom: 1112 (offscreen) → 907 (visible, on a 923 viewport)
textareaVisible: false → true
Tested across two projects with very different activity profiles
(cc-haha: short title + 0 files edited; layout-editor: long title +
20 files edited + 1876 messages). Both render in single horizontal
row.
Screenshot: artifacts/desktop-recent-activity-compact.png
bun run lint passes (tsc --noEmit clean).
Confidence: high
Scope-risk: narrow (CSS / layout only, no behavioral change).
---------
Co-authored-by: 你的姓名 <you@example.com>
|
||
|
程序员阿江(Relakkes)
|
e8bf789961 |
fix(provider): request non-stream OpenAI chat tests (#638)
Ensure custom OpenAI-compatible provider tests explicitly request non-stream responses for both direct connectivity checks and the proxy pipeline. This avoids default SSE responses being parsed as empty JSON by provider validation. Tested: bun test src/server/__tests__/providers.test.ts --test-name-pattern "requests non-stream OpenAI Chat responses during provider tests" Tested: bun test src/server/__tests__/providers.test.ts Tested: bun test src/server/__tests__/proxy-transform.test.ts Tested: bun run check:server Confidence: high Scope-risk: narrow |
||
|
程序员阿江(Relakkes)
|
d3b2f868a9 |
fix: guard prewarm resume shutdown paths (#611)
Prevent desktop prewarm launches from inheriting interrupted-turn resume state, while leaving explicit user-message startup unchanged. Also stop server-side background schedulers during shutdown so app quit cannot leave scheduled task runners alive. Tested: - bun test src/server/__tests__/conversation-service.test.ts - bun test src/server/__tests__/conversations.test.ts -t "prewarm" - bun test src/server/__tests__/conversations.test.ts -t "permission" - bun test src/server/__tests__/diagnostics-service.test.ts -t "keeps fatal startup errors visible on stderr while recording diagnostics" - bun test desktop/electron/services/windows.test.ts desktop/electron/services/tray.test.ts desktop/electron/services/sidecarManager.test.ts src/server/__tests__/server-shutdown.test.ts - bun run check:server |
||
|
程序员阿江(Relakkes)
|
ddcfa5faae |
feat(adapters): add WhatsApp linked-device support (#573)
Add a WhatsApp adapter backed by Baileys linked-device auth, plus desktop QR binding UI, server config endpoints, sidecar startup wiring, tests, and documentation. Constraint: Uses WhatsApp Web linked-device auth, not Meta WhatsApp Business Cloud API. Tested: - cd adapters && bun run check:adapters - bun test src/server/__tests__/adapters.test.ts - cd desktop && bun run check:desktop - bun run check:native - bun run check:persistence-upgrade - bun run check:docs Not-tested: - Live WhatsApp QR pairing, because no WhatsApp account/device was exercised here. - bun run check:server, because the existing src/server/__tests__/conversations.test.ts timeout still fails independently. Confidence: medium Scope-risk: moderate |
||
|
程序员阿江(Relakkes)
|
db631dfdfd |
fix(desktop): show full tool error details (#625)
Surface expanded error output for tool cards whose previews previously returned before rendering the result body. Keep successful Bash/Read/Edit/Write outputs hidden as before while exposing error details with wrapping and copy support. Tested: cd desktop && bun run test -- src/components/chat/chatBlocks.test.tsx Tested: bun test src/server/__tests__/conversations.test.ts -t "should switch from bypass permissions back to default without restarting" --timeout=20000 Tested: bun run verify Confidence: high Scope-risk: narrow |
||
|
程序员阿江(Relakkes)
|
385b996736 |
fix: defer runtime restarts during active turns (#626)
Avoid killing an in-flight desktop SDK turn when runtime config changes during tool execution. Persist the requested runtime immediately, then restart after the turn emits its terminal result. Tested: - bun run check:server - real provider tool-turn model switch smoke - bun run check:coverage (changed-line coverage passed; unrelated global lanes still fail) Scope-risk: narrow |
||
|
程序员阿江(Relakkes)
|
3ff6a79e62 |
feat(adapter): add Telegram command menu (#596)
Add Telegram command-menu sync plus /resume, /provider, /model, and /skills command handling with paginated inline selections. Expose the adapter HTTP calls needed by those commands and harden stale WebSocket session cleanup during Telegram resume/reset flows. Tested: - cd adapters && bun test telegram/__tests__/commands.test.ts telegram/__tests__/menu.test.ts - cd adapters && bunx tsc --noEmit -p tsconfig.json - bun run check:adapters - bun run check:persistence-upgrade - bun run check:native - bun run verify (coverage lane failed on existing root WebSocket Chat Integration timeout) Not-tested: - Live Telegram bot smoke, no bot token/session available. Confidence: medium Scope-risk: moderate |
||
|
你的姓名
|
4690cd9199 | release: v0.5.6 | ||
|
你的姓名
|
f65ae5b2b9 |
fix: update check误判equal version为available update + about设置页满宽
- ElectronUpdaterService加currentVersion选项,checkForUpdates时比较feed版本 - 自包含的isNewerVersion():忽略prerelease/build后缀,等版本->非更新 - AboutSettings去掉max-w-lg/mx-auto约束,面板左右撑满 - 新增4个版本比较回归测试(等版本/旧版本/新版本场景) Tested: updater.test 14 pass, generalSettings/updateStore 67 pass, lint通过 |
||
|
你的姓名
|
78ca7070ad |
chore: ignore .kiro IDE local config
Scope-risk: narrow |
||
|
你的姓名
|
303afcfff4 |
feat(orchestration): lower delegation threshold and propagate project conventions to sub-agents
Bias the orchestrator toward delegating medium tasks (>2 steps or >1 file), reserving direct action for trivial work. Require restating relevant project rules (e.g. codegraph-first) inside sub-agent prompts, since read-only agents (Explore/Plan) run without project memory. Tested: bun test conversations.test.ts (orchestration cases pass) Confidence: high Scope-risk: narrow |
||
|
程序员阿江(Relakkes)
|
d11748d61a |
fix(desktop): make memory files preview-first (#533)
Tested: cd desktop && bun run test src/__tests__/memorySettings.test.tsx Tested: bun run check:desktop Scope-risk: narrow Confidence: high |
||
|
程序员阿江(Relakkes)
|
0a8f247781 |
feat(desktop): add plugin list bulk toggles (#527)
Tested: - cd desktop && bun run test -- src/__tests__/pluginsSettings.test.tsx src/stores/pluginStore.test.ts --run --reporter=verbose --pool=forks --maxWorkers=1 --minWorkers=1 - bun run check:desktop - git diff --check Scope-risk: moderate Confidence: high |
||
|
程序员阿江(Relakkes)
|
a7263cbaf7 |
fix(agent): avoid concurrent worktree config writes (#572)
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 |
||
|
你的姓名
|
7e55d6cee9 |
feat: context-exhausted new-session suggestion (方案3) + orchestration mode
方案3 (desktop, manual-guided): when compactions keep firing only a turn or two apart — the same thrash the CLI circuit breaker trips on — chatStore now appends a one-time visible system notice suggesting the user start a fresh session (the prior summary stays in the current one). Detection lives in module-level state (compactionThrashBySession) so PerSessionState is untouched; counts user turns between compactions, suggests after 3 rapid ones, deduped per session and reset on /clear. New i18n key chat.contextExhausted (en/zh/zh-TW/jp/kr). Also includes in-progress orchestration/coordinator work on the same files (orchestrationPrompt.ts, conversationService coordinatorMode --append-system-prompt, ws handler/events, chatStore, ChatInput, sessionRuntimeStore, types/chat) — committed together per request. Tested: - bunx vitest run desktop/src/stores/chatStore.test.ts (102 pass, incl. new 方案3 rapid-compaction suggestion + spread-out negative case) - cd desktop && bun run lint (clean) - get_diagnostics clean across changed server + desktop files Not-tested: full bun run check:server / check:desktop gates; pre-existing WS runtime-restart integration tests are flaky in this env (CLI code 143). Confidence: medium-high Scope-risk: moderate |
||
|
你的姓名
|
2cf6040451 |
fix(server): treat relay context_too_large as prompt-too-long
Third-party Anthropic-compatible relays reject oversized requests with a 400 context_too_large / 'exceeds the context window' body instead of Anthropic's 'prompt is too long' wording. That fell through to a raw API error with no recovery hint. Normalize it via a new isContextWindowExceededMessage() so getAssistantMessageFromError and classifyAPIError route it onto the existing prompt-too-long handling, surfacing the actionable 'Context limit reached / compact or clear' guidance (TUI) and businessError.prompt_too_long copy (desktop). Tested: bun test src/services/api/errors.test.ts (4 pass) Not-tested: full bun run check:server gate Confidence: high Scope-risk: narrow |
||
|
你的姓名
|
1440ce01ce |
fix(server): guard stop-generation force-kill by process instance (code 143 race)
Stop-generation set a 3s force-kill timer that called stopSession(sessionId). If the user switched provider/model in that window, the restart spawned a NEW CLI process under the same sessionId; the stale timer then SIGTERM-killed the new process during its startup grace window -> 'CLI exited during startup with code 143'. Fix: tag each spawned process with an instanceId (sessionId#N). handleStopGeneration captures the live instanceId up front; the 3s fallback calls stopSessionInstance(sessionId, instanceId), which only kills when the current live process still matches that instance. A restart replaces the instance, so the stale timer becomes a no-op. conversationService.ts: instanceId field + counter, getActiveInstanceId(), stopSessionInstance(). ws/handler.ts: handleStopGeneration uses the instance-guarded fallback. conversations.test.ts: instance-guard regression tests. Tested: bun test conversations.test.ts -t instance/stopSessionInstance (pass). Staged via hunk selection to exclude unrelated in-progress orchestration work that shares these files. Confidence: high Scope-risk: narrow |
||
|
你的姓名
|
110a72a97e |
feat(compact): detect context-exhausted state for new-session suggestion (方案3 CLI foundation)
When the auto-compaction circuit breaker has tripped and the context is still over threshold, autoCompactIfNeeded now returns contextExhausted:true. This is the signal the desktop will use to suggest starting a fresh session (carrying the latest summary) instead of degrading silently. Pure predicate isContextExhausted() added + tested (15 pass). Desktop wiring (ws translation + chat suggestion card + new-session handoff) is intentionally not included here — those files currently carry unrelated in-progress changes. |
||
|
你的姓名
|
b0f368ef97 |
fix(compact): stop re-compaction thrash and post-compact 100% context meter
Two context-management fixes (CLI/sidecar side):
1. Re-compaction loop (方案1+2). Auto-compaction previously only circuit-broke
on hard failures; a compaction that succeeded but left context still over
threshold reset the failure counter and re-compacted every turn, burning a
summary API call each time.
- autoCompact.ts: isIneffectiveCompaction() — when truePostCompactTokenCount
is still >= threshold, count it toward the existing circuit breaker instead
of resetting to 0; query.ts now honours that count on the success path.
- shouldThrottleAutoCompact() — suppress proactive autocompaction for a few
turns after a compaction, unless at the hard blocking limit (so we never
risk prompt-too-long by throttling).
2. Post-compact context meter stuck at ~100% (sessionService.ts). The transcript
context estimate counted the entire pre-compact history plus the summarization
call's huge input_tokens, pinning the indicator near full until the next turn.
Now the estimate is scoped to messages after the latest compact_boundary, with
a model fallback for the just-compacted/no-new-turn case. Non-compacted
sessions are unchanged.
Tested:
- bun test src/services/compact/autoCompact.test.ts (12 pass; throttle + ineffective predicates)
- bun test src/server/__tests__/conversations.test.ts -t "context" (6 pass incl. new compact-boundary scoping case)
Not-tested: 4 pre-existing WebSocket runtime-restart integration tests fail in this env (CLI subprocess code 143); unrelated to these changes.
Confidence: high
Scope-risk: moderate
|
||
|
你的姓名
|
3cbed50ca9 |
feat(desktop): point repo + update source to this fork, credit fork maintainer
- Update source: desktop/package.json publish.owner NanmiCoder -> 706412584 (electron-updater now checks this fork's releases via app-update.yml). Also bump homepage and the legacy Tauri updater endpoint to the fork. - About page: GITHUB_REPO / issues / releases / changelog and the displayed repo name now point to 706412584/cc-haha. Sidebar repo link and ActivitySettings profile subtitle too. - Attribution: original author (NanmiCoder + Bilibili/Douyin/Xiaohongshu social links) is preserved unchanged. Added a new "Fork maintainer" credit (706412584) with i18n keys settings.about.forkMaintainer / forkMaintainerHint across en/zh/zh-TW/jp/kr. Why: this is a self-maintained fork shipping its own builds; pointing the updater at upstream risked overwriting custom builds with upstream releases and hid the fork's own releases. Tested: - bunx vitest run src/pages/ActivitySettings.test.tsx src/__tests__/generalSettings.test.tsx (59 pass) - cd desktop && bun run lint (clean) Not-tested: full verify (long-running) Confidence: high Scope-risk: moderate |
||
|
你的姓名
|
87e37d30d1 |
feat: v0.5.5 — more built-in agents, composer skill/plugin picker, AskUserQuestion notice
Built-in agents: - Add debugger, security-reviewer, refactor, migration, docs-writer, performance, commit-pr built-ins and register them in getBuiltInAgents(). Desktop: - AskUserQuestion prompts no longer vanish silently: when an unanswered question card is cleared by turn end (message_complete / error) — e.g. a malformed question call — a visible system notice (chat.questionDropped) is appended instead. Added across en/zh/zh-TW/jp/kr. Versioning: - Bump desktop/package.json to 0.5.5 and add release-notes/v0.5.5.md. Tested: - bunx vitest run desktop/src/stores/chatStore.test.ts (99 pass, incl. dropped-question notice for message_complete + error, and no notice for non-AskUserQuestion) - bun test src/tools/AgentTool/builtInAgents.test.ts (pass) - cd desktop && bun run lint (clean) - build:windows-x64 + package-smoke (PASS, Claude-Code-Haha-0.5.5-win-x64.exe) Not-tested: full bun run verify / check:server (long-running) Confidence: high Scope-risk: moderate |
||
|
你的姓名
|
433239dbaa |
chore(repo): untrack local tooling dirs (.codegraph, .vscode)
These were accidentally committed in the previous catch-all commit. They're local tool artifacts (.codegraph index, .codegraph/daemon.pid runtime PID, personal IDE settings) that don't belong in the repo. Adding them to .gitignore and removing from tracking via git rm --cached so working copies stay intact. |
||
|
你的姓名
|
fee22c80ca | 提交 | ||
|
你的姓名
|
7b81092aad |
feat(desktop): composer skill/plugin picker, send-now, theme follow-system, read empty pages
ChatInput / SkillPickerMenu:
- + menu now has 4 entries: file, slash command, Skills, Plugins.
- Skills/Plugins open an inline picker above the composer (mirrors the file-search popover: ↑↓ navigate, Enter pick, Esc dismiss). Picking inserts a "@skill:<name>" / "@plugin:<name>" token at the cursor — visible to the user, also legible to the agent as "use this skill/plugin".
Queue "send now":
- sendQueuedMessageNow no longer aborts the running turn or promotes-and-waits — it just sends the message immediately. Removes the prior "Request was aborted" / code 143 retry loop caused by mid-turn stop_generation.
Theme follow-system persistence:
- settingsStore.loadSettings now honours a locally stored "system" theme over whatever concrete value the server last saw, since the server intentionally rejects "system". Fixes follow-system reverting to a concrete theme on every restart.
- uiStore.test.ts: updated the toggleTheme cycle test to include the system step (was a stale failure independent of these changes).
FileReadTool:
- Treat pages: "" as undefined ("read whole file") so the agent's empty-string slips don't trap the tool in a validation-error retry loop.
i18n:
- Added chat.openSkills / openPlugins / skillPicker.{title,empty} / pluginPicker.{title,empty} / sendNow across en / zh / zh-TW / jp / kr.
- Did NOT touch unrelated settings.skills.recommended.* / settings.plugins.* additions present in the working tree from another in-progress task.
Tested:
- bunx vitest run src/stores/chatStore.test.ts -t "message queue" (10 pass)
- bunx vitest run src/stores/settingsStore.test.ts src/stores/uiStore.test.ts (32 pass)
- bun run lint (desktop tsc --noEmit, clean)
- Windows package-smoke after build:windows-x64 (PASS)
Not-tested: full bun run check:desktop / check:server (long-running)
Confidence: high
Scope-risk: narrow
|
||
|
你的姓名
|
644914a8b4 |
feat(agents): add test-author + code-reviewer built-ins, project-level game-developer
Built-in additions (always shipped): - test-author: writes/runs tests for changed code, detects framework, reports changed-line coverage. - code-reviewer: read-only static review, finds bugs/smells/security issues, ends with REVIEW: APPROVE | CHANGES_NEEDED. Project-level addition under .claude/agents/: - game-developer: covers Unity/Unreal/Godot and web JS engines. The system prompt forces engine-version detection (ProjectVersion.txt, *.uproject, project.godot, package.json), prefers querying real symbols already in the project (codegraph) over recalling APIs, and falls back to verifying uncertain APIs against the engine's official docs — to defend against API hallucinations across versions. .gitignore: switched ".claude/" to ".claude/*" with explicit "!.claude/agents/**" so project agents can ship in the repo while user-private files like .claude/settings.json stay ignored. Tests: - builtInAgents.test.ts: asserts test-author + code-reviewer are registered, game-developer is NOT a built-in. - gameDeveloperAgent.test.ts: parses .claude/agents/game-developer.md through the runtime parser and asserts the strengthened guidance (codegraph, official docs, ProjectVersion.txt) is present. Tested: bun test src/tools/AgentTool/builtInAgents.test.ts src/tools/AgentTool/gameDeveloperAgent.test.ts (5 pass) Not-tested: full bun run check:server (long-running) Confidence: high Scope-risk: narrow |
||
|
你的姓名
|
e66751bfe9 |
fix(desktop): fully pause message queue on Stop (multi-idle safe)
v0.5.3's one-shot skip only blocked a single auto-drain, but a Stop emits multiple idle events (message_complete + status idle); the second one still drained one queued message and flipped the button back to running. Replace the one-shot skip with a sticky queueDrainPaused flag: Stop pauses all auto-drains until the user sends their next message (which clears it and fires immediately, ahead of the queue). The queue then resumes FIFO on the next idle. Bumps desktop app to 0.5.4 with release notes. Tested: tsc --noEmit; Vitest chatStore 94 passed (incl. multi-idle stop / priority message / queue resume); browser end-to-end (Stop keeps button at Run with queue intact, priority send immediate, queue resumes); Windows x64 NSIS package + package-smoke PASS. Scope-risk: narrow Confidence: high |
||
|
你的姓名
|
408e04e500 |
fix(desktop): don't flush message queue on user Stop; remove donation section
Stop no longer flushes the queue: a user-initiated Stop now skips exactly the auto-drain triggered by its resulting idle (one-shot guard). The queue stays intact, the next message the user sends fires immediately (priority, not queued — even with items waiting), and the queue resumes FIFO on the next idle after that turn. Queue enqueue/drain/edit mechanics are otherwise unchanged. Also removes the Buy-Me-a-Coffee / donation section from README (zh/en). Bumps desktop app to 0.5.3 with release notes. Tested: desktop tsc --noEmit; Vitest chatStore 94 + pages/ActiveSession 43 passed (incl. stop-no-flush / priority-message / queue-resume case); Windows x64 NSIS package + package-smoke PASS. Scope-risk: narrow Confidence: high |