* feat: 新增 cloud-artifacts 包（Cloudflare Worker HTML artifact 托管）
POST /upload 鉴权上传 HTML 到 R2 返回 hash URL，GET /<7d|30d>/<id>.html
由 Worker 代理读取并直出 text/html。R2 lifecycle rule 自动 7/30 天删除。
独立服务，不被主 CLI 引用（类似 packages/remote-control-server/ 定位）。
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* docs: 完善 cloud-artifacts 文档并统一出口域名
- CLAUDE.md 加 cloud-artifacts 到 Workspace Packages 表和新增 HTML Artifact Hosting 段落
- docs.json 注册 cloud-artifacts 到运行模式 group
- README 加 Quickstart、架构图（含 Deno Deploy 代理层）、Security Considerations、Troubleshooting
- 统一出口域名为 https://cloud-artifacts.claude-code-best.win（wrangler.toml PUBLIC_URL、test.sh 默认 WORKER_URL、所有文档示例）
- test.sh expect() 加 [via body] fallback：经 Deno Deploy 代理（status 抹平为 200）时按 body 的 error 字段断言
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* docs: 修正 CLAUDE.md cloud-artifacts 引用死链
之前指向不存在的 docs/features/cloud-artifacts.md（用户未注册到 docs.json），
改为指向已存在的 packages/cloud-artifacts/README.md，并补充生产出口域名
与 Deno Deploy status 抹平副作用的说明。
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* chore: 同步 cloud-artifacts 测试默认 TOKEN 到新值
用户已通过 wrangler secret put 把生产 TOKEN 改为 claude-code-best，
test.sh 的默认值（之前用旧 token 作 fallback）和注释示例同步更新。
现在直接 bash scripts/test.sh 即可跑通（无需显式传 TOKEN）。
src/index.ts 不依赖具体 token 值（只读 env.TOKEN 做比较），
wrangler.toml 不含 secret，README/.dev.vars.example 用 <your-token>
占位符故无需改。
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* docs: add artifacts feature implementation plan
* feat(artifact): add cloud-artifacts config with token/URL defaults
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* feat(artifact): add HTTP client with body-error parsing
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* feat(artifact): add tool name, description, and prompt
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* feat(artifact): add buildTool definition with file validation
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* test(artifact): add end-to-end tool tests for upload/error paths
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* feat(artifact): export ArtifactTool from builtin-tools barrel
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* feat(artifact): register ArtifactTool in tools list
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* feat(artifact): add /use-artifacts bundled skill
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* feat(artifact): add extractArtifacts message scanner
Scans Message[] for artifact tool_use/tool_result pairs, parses URL/id/expires
from the upload response string, and returns ArtifactInfo[] newest-first.
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* fix(artifact): scanner type narrowing and url regex
- Use double assertion (`as unknown as Record<string, unknown>`) at lines 30
and 90 to fix TS2352 per project convention
- Tighten URL_REGEX to avoid capturing trailing punctuation (parens,
quotes, commas) when URL is embedded in text
- Add test case for array-form tool_result content path
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* feat(artifact): add ArtifactsMenu Ink component
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* feat(artifact): add /artifacts slash command entry
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* feat(artifact): register /artifacts command
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* fix(artifact): use setClipboard instead of pbcopy for cross-platform support
* fix(artifact): drop userFacingName override so display matches /artifacts
* fix(rcs): add resJson helper to resolve strict mode type errors in tests
Hono Response.json() returns Promise<unknown> under strict TypeScript,
causing 121 TS errors across middleware and routes test files.
Co-Authored-By: glm-5-turbo <zai-org@claude-code-best.win>
* fix(cloud-artifacts): add type stubs so tsc passes without worker-configuration.d.ts
The wrangler-generated worker-configuration.d.ts is gitignored, causing CI to
fail with missing ExportedHandler/Env/R2Bucket types. This file provides minimal
stubs for all Cloudflare Workers types used by the artifact upload Worker.
Co-Authored-By: glm-5-turbo <zai-org@claude-code-best.win>
* fix(query): shallow-copy messages before stripping toolUseResult
Previously the per-query cleanup mutated messagesForQuery entries in
place via `delete msg.toolUseResult`. Those entries are references
shared with mutableMessages (UI state), so the delete stripped the
field from the live message object. The next query can start within
milliseconds of tool_result creation — before the React UI commit
lands — so UserToolSuccessMessage's `!message.toolUseResult` check
returned null and tool.renderToolResultMessage was never called,
leaving tool-result rows blank.
Map to a stripped copy instead so mutableMessages keeps the original
for the UI. Downstream API transformations (applyToolResultBudget,
snip, microcompact) already build new arrays via .map(), so they
compose cleanly with this copy.
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* feat(artifact): show uploaded URL inline below ExecuteExtraTool
Deferred tools (shouldDefer: true) are invoked via SearchExtraTools →
ExecuteExtraTool, so their tool_result rows used to render blank —
the UI looked up ExecuteExtraTool, which had no renderToolResultMessage,
and returned null. Add a generic delegation in ExecuteTool that forwards
renderToolResultMessage to the inner tool when it defines one, unwrapping
the { result, tool_name } envelope and the params from the input shape.
All 28 deferred tools can now render their own UI by defining
renderToolResultMessage.
For ArtifactTool specifically, render the uploaded URL as an OSC 8
hyperlink (Link component) in warning color so it's visually prominent,
with the expiry timestamp on a second line and a separate error branch.
Also add `error: z.string().optional()` to outputSchema — zod's default
strip mode was dropping the field, so error states never reached the UI.
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
* fix(cloud-artifacts): make Env stubs actually take effect in CI
The previous stub file (2e29e362) wrapped `interface Env` in
`declare global { ... }`, but the file has no top-level import/export so
it's a script, not a module. TS2669 forbids `declare global` in scripts,
and in .d.ts files that error is silently swallowed — so the Env stubs
were never merged into the global scope. Locally typecheck passed only
because worker-configuration.d.ts (gitignored) provided Env separately;
in CI / fresh clones, `BUCKET`, `MAX_BYTES`, `DEFAULT_TTL_DAYS`,
`PUBLIC_URL` were all missing on Env.
Drop the wrapper. Top-level `interface Env` in a script .d.ts is already
global ambient and merges with worker-configuration.d.ts via interface
declaration merging, so both environments typecheck cleanly.
Co-Authored-By: glm-5.2 <zai-org@claude-code-best.win>
---------
Co-authored-by: glm-5.2 <zai-org@claude-code-best.win>
OpenAI's prompt_tokens includes cached tokens, but Anthropic's
input_tokens semantic excludes them. The adapter was mapping
prompt_tokens → input_tokens verbatim, causing downstream code
(cache hit rate, cost, autocompact) to double-count.
Real-world impact: DeepSeek returns prompt_tokens=34097 with
cached_tokens=34048, displayed as 50% hit rate instead of 99.86%.
Co-Authored-By: glm-5.1 <zai-org@claude-code-best.win>
DeepSeek v4 in thinking mode sometimes returns reasoning_content: ""
when the model answers directly without internal reasoning. Two places
were filtering the empty string out, which dropped the thinking block
from the assistant turn entirely. The next request then omitted
reasoning_content for that prior turn, and DeepSeek rejected with
400 "reasoning_content ... must be passed back to the API".
Fix:
- openaiStreamAdapter: open a thinking block whenever reasoning_content
is present (including ""); skip the empty thinking_delta event since
the empty value is already conveyed by the block's initial state.
- openaiConvertMessages: preserve empty thinking blocks as
reasoning_content: "" when serializing assistant messages back to
the OpenAI/DeepSeek format.
Tests:
- New: empty reasoning_content opens a thinking block (adapter).
- Updated: empty thinking blocks now round-trip as reasoning_content: ""
instead of being dropped.
- New: assistant messages with no thinking block still omit
reasoning_content (regression guard for non-thinking models).
Root causes:
1. ThemeProvider was imported but never used in App.tsx and showSetupDialog
2. setThemeConfigCallbacks was never called to inject persistence callbacks
3. Preview/save/cancel theme lifecycle had no provider to coordinate
Changes:
- Export setThemeConfigCallbacks from @anthropic/ink
- Wrap App.tsx children with ThemeProvider (initialState from config, onThemeSave persists)
- Wrap showSetupDialog with ThemeProvider for onboarding/trust dialogs
- Call setThemeConfigCallbacks in init.ts to register load/save callbacks
- Update SnapshotUpdateDialog test to account for new ThemeProvider wrapper
Fixes #theme-switching
Twelve actionable items (7 Major + 5 Minor) from the CodeRabbit review on
claude-code-best/claude-code#386:
- docs/internals/autonomy-jira.md: typo "due input close" → "due to input close".
- src/utils/autonomyRuns.ts:
- selectPersistedAutonomyRuns no longer evicts active (queued/running) runs
when the combined list exceeds AUTONOMY_RUNS_MAX. Active runs are kept in
full and the inactive history is capped to the remaining budget so
persisted ownership for live work survives.
- isValidOwnerProcessId now allows pid <= 4_194_304 so a live run owned by
the maximum Linux PID is not treated as stale.
- src/utils/autonomyAuthority.ts: maskCodeFencedLines tracks the active fence
length and only closes the fence when a same-character run of equal-or-
greater length appears with no trailing content, so a nested ```yaml inside
an outer ```` block no longer leaks fake `tasks:` entries into the parser.
- src/cli/print.ts: late-shutdown branches in the cron and scheduled-task
paths now call cancelQueuedAutonomyCommands({ commands: [command] }) instead
of markAutonomyRunCancelled(...). Updating run state alone left the
queue-side record orphaned for resume/recovery.
- src/utils/processUserInput/processSlashCommand.tsx: scheduled-task-result
notification is enqueued before finalizeAutonomyRunCompleted (which queues
follow-up autonomy commands) so both at priority: 'later' land in order and
the next autonomy step can not run before the worker's output is observed.
- src/screens/REPL.tsx + src/utils/handlePromptSubmit.ts:
- onQuery now returns Promise<boolean>: false from the concurrent-guard
skip path, true otherwise. Other call sites use `void onQuery(...)` and
are unaffected. handlePromptSubmit's onQuery prop type matches.
- The autonomy-prompt callsite captures the executed flag, finalizes
claim.claimedCommands as { type: 'completed' } only when onQuery actually
ran, and runs the completed-finalize in its own try/catch so a failure
there does not propagate into the outer catch and trigger a second
finalize as { type: 'failed' } for the same commands.
- Removed the unsafe `command.value as string` cast; createUserMessage
already accepts `string | ContentBlockParam[]`.
- createUserMessage mock in src/__tests__/handlePromptSubmit.test.ts now
matches the new Promise<boolean> shape.
- packages/builtin-tools/src/tools/RemoteTriggerTool/__tests__/
RemoteTriggerTool.test.ts:
- Inline auth mock replaced with the shared tests/mocks/auth (added).
- The full mock of src/constants/oauth.js is replaced by a narrow
side-effect-only mock that overrides the env-reading helpers
(getOauthConfig, fileSuffixForOauthConfig, MCP_CLIENT_METADATA_URL) and
delegates pure data exports to the real module.
- tests/integration/dependency-overrides.test.ts:
- mermaid does not export `./package.json` in its exports map, so
require.resolve('mermaid/package.json') throws
ERR_PACKAGE_PATH_NOT_EXPORTED in runtimes that honor exports semantics.
The test now resolves the package entry and walks up to the package
root via a small findPackageJson helper.
- readFileSync from node:fs is replaced with `await Bun.file(...).text()`
to match the project's Bun-API requirement.
Validation:
- bun run typecheck (clean).
- bun test → 3996 pass / 0 fail across 305 test files.
Targets PRs:
- amDosion/claude-code-bast#8 (fork-internal review)
- claude-code-best/claude-code#386 (upstream review, same head branch)
This PR consolidates a coordinated batch of fixes around autonomy run/flow lifecycle, scheduled task deduplication, provider-boundary state finalization, and matching memory-bound treatments for adjacent long-running subsystems (REPL fullscreen scrollback, skill-search/skill-learning runtime activation). All changes were developed and reviewed together because they touched the same lifecycle invariants and were uncovered by the same long-running session reproductions.
## Lifecycle correctness
- Queued autonomy prompts are not injected unless the persisted run was successfully claimed; queued run claiming is now terminal-safe so a once-consumed/cancelled/failed run can not slip back into `queued`.
- Autonomy run/flow finalization happens on completion, provider error, generator close, and cancellation — not just the happy path. New `src/__tests__/queryAutonomyProviderBoundary.test.ts` covers these provider-boundary transitions.
- `requestManagedAutonomyFlowCancel` and `resumeManagedAutonomyFlowPrompt` carry `rootDir` and `currentDir` explicitly across detached async boundaries (proactive-tick, cron, daemon restart) instead of inferring from process state.
- Active runs/flows are protected from janitor pruning so a running step can not be garbage-collected mid-flight (`src/utils/autonomyAuthority.ts`).
- Heartbeat parser now ignores fenced code blocks; the two-phase commit window for autonomy state transitions is documented in `docs/internals/autonomy-jira.md`.
## Ownership and dedup
- `src/utils/autonomyRuns.ts`: ownership stamping (run id + rootDir carried end-to-end), source-based dedup against active runs.
- `src/hooks/useScheduledTasks.ts`: scheduled ticks deduplicate against runs already active on the same source label.
- `src/utils/processUserInput/processSlashCommand.tsx`: forked slash commands now thread the autonomy `runId` so completion finalizers can find the originating run for deferred completion.
- New `src/utils/autonomyQueueLifecycle.ts` and tests collect the queue-side lifecycle invariants in one place.
## Memory bounds (related, same review pass)
- `src/screens/REPL.tsx`: caps fullscreen scrollback after the compact boundary and updates trailing progress rows in place. Long-running fullscreen sessions could otherwise retain thousands of post-compaction messages and duplicate progress rows, keeping Ink trees alive long after their useful context had moved on.
- `src/services/skillSearch/*` and `src/services/skillLearning/*`: runtime activation is strictly opt-in via existing env toggles; session caches are capped so long-running processes can not grow them forever. Build presence is preserved so operators can still discover and opt into the slash commands.
## CI / test contract
- `tests/integration/dependency-overrides.test.ts`: smoke test no longer drives Mermaid's browser renderer; it validates the package-resolution contract directly so CI does not regress on unrelated browser timing.
- New `tests/integration/autonomy-lifecycle-user-flow.test.ts`: end-to-end CLI subprocess flow exercising `status --deep`, `flows`, `flow <id>`, `flow resume`, `flow cancel` against persisted state.
- `src/entrypoints/cli.tsx`: `claude autonomy …` routes through an entrypoint fast path that reuses the slash-command formatter without booting the full interactive CLI. Stdout is flushed before forced exit so coverage subprocesses do not terminate with empty stdout.
- `packages/builtin-tools/src/tools/RemoteTriggerTool/__tests__/RemoteTriggerTool.test.ts`: stabilized to prevent audit flake under coverage.
## Tests added
- `src/__tests__/queryAutonomyProviderBoundary.test.ts`
- `src/hooks/__tests__/useScheduledTasks.test.ts`
- `src/utils/__tests__/autonomyAuthority.test.ts`
- `src/utils/__tests__/autonomyFlows.test.ts` (extended)
- `src/utils/__tests__/autonomyPersistence.test.ts` (extended)
- `src/utils/__tests__/autonomyQueueLifecycle.test.ts`
- `src/utils/__tests__/autonomyRuns.test.ts` (extended)
- `src/utils/processUserInput/__tests__/processSlashCommand.test.ts`
- `tests/integration/autonomy-lifecycle-user-flow.test.ts`
## Docs
- `docs/agent/sur-loop-scheduled-oom.md`: System Understanding Report covering the scheduled/loop OOM problem, the call graphs investigated, and the lifecycle invariants this PR establishes.
- `docs/agent/sur-skill-overflow-bugs.md`: SUR for the related skill-overflow context.
- `docs/internals/autonomy-jira.md`: documents the two-phase commit window and ownership stamping invariants.
- `docs/memory-leak-audit.md`: audit notes covering the REPL/scrollback and skill-search bounds.
## Invariants this PR establishes
1. Queued autonomy prompts are not injected unless the persisted run was successfully claimed.
2. Terminal run/flow states are terminal — completion, failure, and cancellation all finalize state regardless of which provider/error path triggered them.
3. Autonomy run/flow `rootDir` is carried explicitly across detached async boundaries instead of inferred from a shared singleton.
4. State-only CLI subcommands (`autonomy status|runs|flows|flow …`) bypass full interactive bootstrap so they do not hold unrelated handles open.
5. REPL fullscreen scrollback and skill-search/skill-learning session caches are explicitly bounded.
## Validation
```bash
bun run typecheck
CI=true GITHUB_ACTIONS=true bun test # 3996 pass / 0 fail across 305 files
bun test src/__tests__/queryAutonomyProviderBoundary.test.ts \
src/hooks/__tests__/useScheduledTasks.test.ts \
src/utils/__tests__/autonomy{Runs,Flows,Authority,QueueLifecycle,Persistence}.test.ts \
src/utils/processUserInput/__tests__/processSlashCommand.test.ts \
tests/integration/autonomy-lifecycle-user-flow.test.ts
```
## Origin
This PR is the consolidated, upstream-targeted version of two fork-side review PRs (fix/loop-scheduled-autonomy-oom and fix/autonomy-lifecycle). The fork-side review history is preserved at https://github.com/amDosion/claude-code-bast/pull/7 . The fork's own internal `chore: keep fork current with upstream` sync commits and the `docs: update contributors` automation are intentionally not included in this PR.
The autonomy CLI handler `rootDir` threading that the fork added (78f64d8a, 98d04ddb) is intentionally omitted here because upstream `a2cfaf91` (fix: 修复 RemoteTriggerTool 和 autonomy 测试的全量运行失败) already performed the equivalent change with an additional `currentDir` option. Keeping the upstream version avoids regressing that improvement.
