3093 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Hyeonsang Cho	9146bfa03d	feature(gateway): issue request trace ids unconditionally (#5119) ... * refactor(gateway): issue request trace ids unconditionally The request trace id was gated behind logging.enhance.enabled at every entry point, so downstream code had to keep asking whether one existed: a header-provenance flag in its own ContextVar, a precedence resolver, and three-level carrier fallbacks at each consumer. Bind one unconditionally instead. TraceMiddleware covers Gateway HTTP; ensure_trace_context covers the entry points that never touch ASGI -- scheduled occurrences, MCP task notification runs, IM channel messages, and the embedded client -- each scoped to one unit of work so a long-lived worker task cannot leak one occurrence's id into the next. The ContextVar becomes the only source; the response header, runtime context, run metadata and log records are derived outputs. Consumers now use ensure_trace_id() or resolve_trace_id(*carriers) and drop their presence guards. Removed: resolve_deerflow_trace_id, the header-provenance flag and its three helpers, set/reset_current_trace_id, is_trace_correlation_enabled and its gateway alias. BREAKING CHANGE: every Gateway HTTP response now carries X-Trace-Id and it cannot be turned off; logging.enhance.enabled controls log output only. Installations on the default enabled: false will start seeing the header. No config keys were added or removed. * fix(gateway): stop persisting a caller-supplied trace id on the run record body.metadata forks two ways: through build_run_config into the live run config, which the run worker restamps, and through create_or_reject into the run record that the runs API echoes verbatim. Only the first was covered, so a client sending metadata.deerflow_trace_id made the most durable and most visible surface of a run disagree with the X-Trace-Id and the log lines the same request produced -- a correlation id that does not match the logs is worse than none. Stamp the server-issued id once at the trust boundary so both forks receive it, preserving the caller's own metadata keys. Close the same gap on config.context, which reaches the runtime context by a separate path: _build_runtime_context no longer merges server-owned keys from the caller, and _install_runtime_context assigns rather than setdefaults. A thread's metadata is no longer seeded with the run-scoped id of whichever run created it -- one thread spans many runs and as many trace ids. Found by driving a real run through the Gateway and reading the run back from the runs API; every unit test built its metadata by hand and so could not see it. * fix(gateway): expose X-Trace-Id to split-origin browser clients X-Trace-Id is not on the CORS safelist, so a browser client served from a separate origin could not read it -- and those are exactly the clients that cannot read the Gateway's logs either, leaving them with nothing to quote in a bug report. Same-origin nginx deployments were unaffected, which is why this stayed hidden. Add it to CORS_EXPOSED_HEADERS beside Content-Location, referencing TRACE_ID_HEADER rather than repeating the literal. * fix(gateway): keep X-Trace-Id on unhandled-exception 500s Starlette's ServerErrorMiddleware sits outside every user middleware and emits unhandled-exception 500s through the raw send, so those responses never pass TraceMiddleware's header-writing wrapper. The 500 for a server bug is exactly the response a user most needs to correlate with a log line, and it was the one response that shipped without the id. TraceMiddleware now tracks whether http.response.start has been sent. On an exception with no response started it emits its own plain 500 carrying the header, then re-raises: the outer ServerErrorMiddleware sees the response already started and only re-raises too, so the server's exception logging is untouched. An exception mid-stream keeps propagating unchanged — a second response start cannot be sent, and the already-written header stands. The trace id is printable ASCII by construction (normalize_trace_id / generate_trace_id), which is what makes the raw latin-1 header encoding safe. * fix(gateway): strip the forged trace id from the persisted request echo The run-record fix stopped a forged metadata.deerflow_trace_id on the authoritative metadata surface, but the raw request echo still carried one: create_or_reject persists body.config verbatim as runs.kwargs_json, which the runs API serves back. A client posting config.context.deerflow_trace_id therefore still got its forged value stored and echoed on one API surface while the header, logs, run metadata, and checkpoint all carried the real id — the id is ignored as input there, so echoing it back only manufactures disagreement. Two changes close it. redact_config_secrets — already the shared scrub for that echo, applied at admission and again at serve time, so historical records are covered too — now also drops deerflow_trace_id from config.metadata and config.context. And build_run_config now merges run metadata onto a copy of the caller's config["metadata"] instead of updating it in place: the nested values of the request config are reference copies, so the in-place merge was writing the server-stamped key through into body.config, contaminating the "what the client sent" record before it was persisted (and incidentally masking the forged-value echo on the metadata container). The regression test posts a forged id through body.metadata, config.metadata, and config.context at once and reads the kwargs echo back off the run record, failing if either leak returns. * docs(harness): record the trace-echo scrub, 500 fallback, and accepted retry divergence The trace section of the harness AGENTS.md now covers the two fixes that close the derived-output rule (the kwargs-echo scrub in redact_config_secrets plus build_run_config's copy merge, and TraceMiddleware's own 500 for unhandled exceptions), and CHANGELOG gains their Fixed entries. It also writes down the one accepted divergence: a crash-recovered scheduled launch reuses the durable run through its idempotency key, and start_run returns early on idempotency_reused without restamping — so the run record keeps the first attempt's deerflow_trace_id while the retry's own log lines carry the freshly minted id of its ensure_trace_context binding. The divergence is confined to the crash-recovery window and is accepted rather than fixed: restamping on reuse would rewrite a persisted record for a run that already exists, which is worse than two ids that each correlate their own attempt's logs. Written down so the next reader of the scheduler recovery path does not diagnose it as a bug. * docs(config): align the logging.enhance schema note with the unconditional trace id The config-module AGENTS.md still described logging.enhance as the gate for the Gateway X-Trace-Id header and Langfuse deerflow_trace_id. That model is gone: ids are issued unconditionally and this block decides log output only. Left as-is, the stale wording invites an agent to "restore" a header gate it believes was lost. Reworded to match the sibling AGENTS.md files and config.example.yaml, with a pointer to the Request Trace Context section that owns the full model. * docs(changelog): link the trace entries to #5119 The five new entries pointed at the ([#XXXX]) placeholder with no reference definition, rendering as literal text instead of a link — and RELEASING.md step 2 relies on those references when the section becomes release notes. All five now point at #5119, with the definition appended to the reference block. * refactor(harness): rename _stream_without_trace_context to _stream_turn The name asserted the opposite of what the method now does. It was accurate while logging.enhance.enabled could route stream() around the trace scope; with the gate gone it is the only stream implementation left, and it binds the id itself via ensure_trace_id(). Private, so the rename touches only the definition and the one stream() call site. * docs(harness): fit the trace-context guidance inside the AGENTS.md chain budget The expanded Request Trace Context section pushed the effective AGENTS.md chain for agents/middlewares to 99,815 bytes, past the 98,304 hard limit scripts/check_agent_guidance.py enforces in CI (AG002). Compressed the section from 7,359 to 4592 bytes with no facts removed: the entry-point table, the derived-output rule and its enforcement points, the accepted scheduled-retry divergence, the two resolution helpers, the stream() binding rationale, the log-output-only gate, the CORS listing, the 500 fallback, and the test map all remain. Sized against the merge, not just the branch: current main grew the same chain by ~724 bytes, so the check was verified on the merged tree as well (97,772 bytes; branch tree 97,048). * fix(gateway): declare content-length on the fallback 500 The pre-response 500 declared content-type but no content-length, leaving the framing to the ASGI server: chunked on HTTP/1.1, close-delimited on HTTP/1.0 — the one wire difference from the ServerErrorMiddleware response it replaces, which sends content-length: 21. The explicit header keeps the fallback byte-identical to what clients saw before. * docs(readme): drop the trace-correlation condition from the translations The zh/ja/fr/ru Langfuse sections still said metadata.deerflow_trace_id matches X-Trace-Id "when request trace correlation is enabled". The id now always matches and that condition no longer exists, so each bullet states the unconditional match and that logging.enhance.enabled only controls whether the id is printed into logs — the one piece of the feature a user can still configure. * test(gateway): pin TraceMiddleware wiring through create_app() Every X-Trace-Id test exercised a hand-built four-route app, so the real stack's add_middleware(TraceMiddleware) line was pinned by nothing: deleting it — or short-circuiting above it — passed CI while silently dropping both the response header and the ambient id the run-record stamp and enhanced log records derive from. One case now drives /health through create_app() and asserts the inbound id round-trips; mutation-checked by removing the wiring line, which fails exactly this test. * docs(gateway): note the fallback 500 is CORS-opaque The pre-response 500 is emitted outside CORSMiddleware — the exception has already unwound past it — so it carries no Access-Control-Allow-Origin and a split-origin browser client cannot read the id on this one response, unchanged from the ServerErrorMiddleware 500 it replaces. Documented on the class and in the CHANGELOG entry rather than fixed: replicating the origin allowlist outside CORSMiddleware would let the two policies drift. * fix(harness): keep abandoned-stream cleanup inside the trace binding stream() binds the turn's id around each next(inner) and resets it before yielding, but the finally's inner.close() ran after that binding was gone. Abandoning the stream therefore drove the inner LangGraph generator's GeneratorExit/finally path with no trace id — or an unrelated ambient one from whichever context ran the close — so cancellation and finalization logs and callbacks did not correlate with the turn they belong to. inner.close() is now wrapped in a local bind/reset of the same turn id. The token is set and reset in the same frame, never across a yield, so the per-step cross-context safety is preserved even when GC closes the generator from another Context — pinned by the existing copy_context close test, which now exercises this path. The regression test records the id from the inner generator's finally and fails without the binding. * test(harness): teach the worker-trace fake about RunManager.cleanup Upstream #5112 (bound gateway memory after terminal runs) added a run_manager.cleanup(run_id) call to run_agent's finalization, so the merge-commit CI run failed all five worker-trace-binding tests with AttributeError on this PR's _FakeRunManager. The fake gains the same no-op shape as its other methods. * docs(gateway): bring the gateway AGENTS.md back under its soft budget Upstream #5092 grew backend/app/gateway/AGENTS.md to 40,966 bytes, 6 over the 40,960 soft budget that test_agent_guidance_check.py::test_repository_guidance_stays_below_soft_budgets_and_avoids_doc_indexes enforces — its Unit Tests run on main was cancelled by push concurrency, so main is currently red on that test and every PR merge-run inherits the failure. Two whitespace/wording trims in the row #5092 touched (a doubled space, and "its configured `context_window`" → "its `context_window`") bring the file to 40,953 with no content change. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com>	2026-09-01 16:49:39 +08:00
Willem Jiang	56a7185f30	fix(ci): fix the ci check of gateway AGENTS.md (#5130) ... * fix(ci): fix the ci check of gateway AGENTS.md * fix(ci): fix the ci check of gateway AGENTS.md	2026-09-01 16:34:45 +08:00
Zeren Wang	a06a6fed7e	feat(harness): deterministic acceptance checklist for subagent delegations (RFC #4651, layer 2) (#5109) ... * feat(harness): deterministic acceptance checklist for subagent delegations (RFC #4651, layer 2) PR4 of RFC #4651: check lead-supplied acceptance_criteria in code when a subagent completes, so objectively checkable requirements can never be silently passed by a self-report. - subagents/acceptance_checks.py: deterministic leaf families — file:<path> exists|non-empty and file_written:<path> read through read_current_file_content scoped to the shared thread workspace; the read uses the sandbox-native virtual path form (the local read validator and provider mount tables resolve /mnt/user-data/... paths, not host paths); the scope decision canonicalizes with realpath on the local sandbox so workspace symlinks cannot escape into uploads; a remote provider's "Error: ..." return string is normalized to a failed check (provider-typed via is_local_sandbox); a UnicodeDecodeError marks a binary deliverable as existing and non-empty; out-of-scope paths degrade to UNVERIFIED. tests_passed:<command> anchors to a matching recorded bash execution with status=success and a test-summary shape; matching is shell-structure aware with control-flow attribution (span must end at the last segment with provable execution), negating-option values are ineligible evidence and a target negated anywhere in the command degrades the match, extra flags must be selection-preserving, extra positionals widen only after a path-scoped criterion, truncated commands degrade via command_truncated, the summary shape is read only from output attributable to the matched segment (preceding segments provably silent by invocation form), and pass shapes require a nonzero passed count. Criterion text is neutralized with neutralize_untrusted_tags before storage/rendering. Anything else renders UNVERIFIED, never silently passed. - executor: accumulate bounded bash command/output evidence per streamed chunk (merged by tool_call_id, newest-capped) so subagent summarization compacting earlier messages cannot erase a recorded execution; the recorded status is the actual shell exit status parsed from the output's exit marker (signed codes included; the remote Command exited with code N form is accepted only as the whole trimmed output), falling back to deerflow_tool_meta only when no marker exists. - sandbox providers: e2b/opensandbox/tenki/boxlite append the LocalSandbox-style "Exit Code: N" marker on nonzero exit even with non-empty output; aio propagates the SDK's structured exit_code on both exec paths the same way; local timeouts append Exit Code: 124; and _truncate_bash_output always preserves a trailing exit marker (signed included) inside its budget, with a 32-char floor raising any smaller configured limit, so the actual shell outcome always survives in the output text. - task_tool: run the checklist offloaded (asyncio.to_thread) on the completed branch, failure-isolated; stamp the verdict into result metadata and render the per-criterion section into the model-visible result text. - status contract: additive subagent_acceptance_verdict transport with read-side structural validation. - delegation ledger: entry carries the verdict and renders a compact acceptance segment; gateway strips caller-forged verdicts from both ledger entries and message metadata, like the citation verdict. - blocking-IO anchor pins the offload (teeth proven red->green); leaf read errors catch only OSError/SandboxError so unexpected errors reach the task-tool-level isolation instead of being mislabeled. * fix(harness): close acceptance evidence gaps from review (RFC #4651 PR4) - negating options: overlap with a matched criterion target is now checked by path/nodeid prefix, not exact token equality — excluding a sub-path of the criterion's selection (pytest tests --deselect tests/unit/test_auth.py) degrades to UNVERIFIED instead of holds - output attribution: any redirection token in the matched final segment makes the recorded tail non-attributable (> / >> / 2> are word characters to the parser, so redirection was invisible to the matcher) - silent-source allowlist narrowed from any *activate suffix to the */bin/activate shape - status_contract docstring: restore the shared-fixture sentence and note subagent_acceptance_verdict is deliberately outside the fixture - executor: update_bash_executions publishes [] (stream carried no bash-family calls) instead of collapsing it into None, mirroring update_tool_receipts * fix(harness): close acceptance residual gaps from re-review (RFC #4651 PR4) - tests_passed: add error outcomes to the fail shapes — "4 passed, 1 error" and pytest's "ERROR <nodeid>" short summary no longer satisfy the pass shape when the exit status is swallowed (|| true) or absent; zero-error counts stay clean. - file leaves: bound the deliverable read — a "wc -c" shell size probe answers files above 50k bytes without loading ~2x their size, honoring the host-bash kill switch and falling back to the full read on any non-integer rendering, so verdicts never get less sound. - executor: record the exit marker text as status_marker on harvested bash evidence; the leaf detail now reports the marker actually seen instead of asserting a failure indistinguishable from the command's own trailing text. - extend the blocking-IO anchor to drive the probe branch inside the offload; teeth re-verified red->green. * fix(harness): close acceptance forgery and bound gaps from P2 re-review (RFC #4651 PR4) - file leaves: never read unbounded — size is established first (os.stat on the validated local host path, so the host-bash-disabled configuration needs no shell; a guarded wc -c on remote providers that renders missing/unreadable in its own words). Above the 50k cap the leaf answers from the size alone, at/below it the full read runs, and an unestablishable size degrades to UNVERIFIED instead of an unlimited fallback read. - output attribution: source/. prefixes are never provably silent — a crafted */bin/activate path shape says nothing about what the script prints, so sourced segments can no longer lend a passing summary. - executable identity: an explicitly path-spelled criterion now requires the same normalized executable path; the basename rule stays only for deliberately bare criterion commands. * fix(harness): run acceptance size probe outside subagent-controlled state (RFC #4651 PR4) - remote probe no longer runs in the sandbox's persistent shell: a fresh env -i /bin/sh with absolute-path stat/realpath (poisoned functions, aliases, PATH, exported functions, IFS, locale cannot steer it), plus a marker env routing AIO onto a fresh per-call bash.exec session. - metadata-only: stat never opens content, so a FIFO deliverable cannot block the parent for the provider's idle timeout; non-regular files (fifo/dir/symlink) degrade to UNVERIFIED. - containment canonicalized against the literal mount root: a final-component symlink or a swapped parent directory (root included) cannot redirect the check outside shared storage; unprovable layouts degrade to UNVERIFIED. * fix(harness): canonicalize probe containment against the canonical mount root (RFC #4651 PR4) Literal-root equality made every remote file leaf permanently UNVERIFIED on e2b and Tenki, which realize /mnt/user-data as a symlink to the home dir by default (e2b bootstrap 'sudo ln -sfn', Tenki best-effort symlink). Containment now compares the file's realpath against the mount root's realpath — exactly what the provider's own read path resolves, so probe and read-back stay consistent; final-component symlinks stay rejected by the non-dereferencing stat, and an intermediate dir-link escape under a sane root still lands ESCAPED. The inner script is a module constant and the suite now executes the composed probe for real against on-disk layouts (real dir, symlinked prefix, final symlink, fifo, missing, dir-link escape), which the canned-output stub could not see. * fix(harness): close bare-criterion negation and CDPATH summary channels (RFC #4651 PR4) - matching: a criterion with no positional selection target (bare pytest, make test) stands for the runner's default selection, so ANY negating option (--ignore/--deselect/...) makes the recorded run a different selection — unprovable. The overlap guard only sees consumed criterion tokens, which a bare criterion does not have; scoped criteria keep the unrelated-exclusion behavior. - attribution: cd is no longer blanket-silent — CDPATH makes cd print the resolved (subagent-chosen) destination and the pass shapes match as substrings, so one mkdir 'all tests passed' plus an export minted a pass for any quiet command. A cd argument or CDPATH= value (export or leading assignment) carrying any summary shape makes the segment non-silent; shape-free cd dir wrappers keep matching. - docs: _truncate_bash_output states the effective 32-char floor (the guarantee previously read as an unconditional max_chars bound). * fix(harness): close env-assignment and expansion channels in acceptance matching (RFC #4651 PR4) Self-audit in the shape of the last review rounds — channels the matcher classified as accounted-for that can change what runs, narrow the selection, or lend the summary text: - env assignments are no longer blanket-stripped: only an allowlist of inert display/CI knobs (CI, NO_COLOR, PY_COLORS, ...) may prefix a matched span, and a non-allowlisted assignment in any preceding segment (pure-assignment or export NAME=) is state pollution — PATH redirects the executable, LD_PRELOAD/PYTHONPATH/NODE_OPTIONS inject code, PYTEST_ADDOPTS/GOFLAGS/MAKEFILES inject selection-changing inputs, BASH_ENV runs arbitrary shell startup. All degrade to unprovable. - runtime expansions: any span token carrying /$( )/backticks, any negating-option value carrying an expansion or glob (unknown excluded set), and any extra executed token carrying glob metacharacters (crafted option-looking filenames narrow invisibly) are unprovable. Criterion-side globs stay self-consistent (literal match). - cd: an argument carrying a runtime expansion or glob is non-silent (unknown destination, unknown print); CDPATH= assignments are now handled as state pollution at the match layer, subsuming the value-shape special case. * fix(harness): persistent-shell evidence, exact env sets, option-arity scoping (RFC #4651 PR4) - tests_passed: on a persistent-shell provider (new Sandbox.persistent_shell_sessions capability, set by AioSandbox) every leaf degrades to UNVERIFIED — any earlier call in the shared session could have mutated the state the clean-looking run executed in, and only a fresh controlled session (RFC section 6 verifier) can prove otherwise. The flag is read from the provider registry without acquiring a sandbox. - env assignments: the allowlist is gone — no variable is provably inert across repositories (CI/DEBUG are routinely read by tests). The span's assignment prefix must equal the criterion's exactly (values included, order-insensitive); any assignment or export NAME= in a preceding segment is state pollution. - scoping: positional targets are now read by option arity, so a path embedded in an option (--basetemp=/tmp/p, --junitxml=/tmp/r.xml) never counts as a selection target and an extra positional after such a criterion narrows the default selection it denotes. * fix(harness): stamp shell provenance at harvest, close export/unset and arity gaps (RFC #4651 PR4) * fix(harness): split physical newlines as shell separators in acceptance matching (RFC #4651 PR4) * fix(harness): scope cd wrappers to thread data roots, pin accepted boundaries (RFC #4651 PR4) * fix(harness): preserve criterion connectors, prove file_written readable, fail-closed shell capability (RFC #4651 PR4) * fix(harness): compare only the connector prefix, tolerate trailing criterion semicolons (RFC #4651 PR4) * fix(harness): preserve continuation-line operators, keep ./-spelled executable identity (RFC #4651 PR4) * fix(harness): render criteria single-line so a multiline criterion cannot inject a forged checklist line (RFC #4651 PR4) * fix(harness): reject parent-traversal executable tokens in acceptance matching (RFC #4651 PR4) * fix(harness): reject parent-traversal negated values in acceptance matching (RFC #4651 PR4)	2026-09-01 16:13:41 +08:00
Sunshine	a956bbc030	fix(runs): reject cancel actions on GET stream joins (#5092) ... * fix(runs): reject cancel actions on GET stream joins stream_existing_run is registered for both GET and POST, and its ?action=interrupt|rollback branch cancels the run. The CSRF middleware exempts GET, so a session-authenticated browser could be forced cross-site (img/script/top-level navigation) into GET /api/threads/{id}/runs/{run_id}/stream?action=interrupt|rollback — a state-changing GET that bypasses the CSRF protection guarding the POST variant. Introduced with the dual registration in #1403. The handler's docstring already documents cancel-then-stream as POST-only (the LangGraph SDK's joinStream/useStream stop button uses POST); enforce it: GET with an action answers 405, action-less GET joins and POST cancel-then-stream are unchanged. Regression drives the real router: GET+action is 405 with the run left running, plain GET join still streams, POST+action still cancels. * fix(runs): scope the 405 detail to the action requirement "GET is a read-only stream join" overstates the current main: on a locally-owned run with the default on_disconnect=cancel, a GET join's disconnect can still trigger cancellation. That observer-disconnect vector is closed by #5041; the detail here should only claim what this guard enforces. * fix(runs): harden GET stream action rejection * fix(runs): align stream schema with method contract * test(runs): pin GET stream action 405 through the production stack Review follow-up (defence-in-depth): the GET-action suite drove bare FastAPI() apps, so nothing pinned that a session-authenticated cross-site GET reaches the route gate at all once CSRF exempts the safe method. test_pat_auth.py already assembles the production middleware order (AuthMiddleware inner, CSRFMiddleware outer), so its mirror app now registers the real _reject_get_stream_action dependency on a GET join route. The new case pins the end-to-end premise: an authenticated GET ?action=interrupt is answered 405 + Allow: POST by the production route dependency, while the same unauthenticated GET dies at AuthMiddleware's 401 before any route logic runs. Validation: focused suites (test_pat_auth, test_stream_get_action, test_csrf_middleware) — 62 passed; ruff check + format clean; the new case errors on the pre-fix baseline (guard absent), confirming the pin.	2026-09-01 15:51:37 +08:00
Daoyuan Li	df57f8e269	fix(lark): preserve app secrets during credential switches (#4820)	2026-09-01 15:37:19 +08:00
betterkite	b552b5015c	fix(messages): drop legacy <uploaded_files> tag handling (#4826) ... * fix(messages): drop legacy <uploaded_files> tag handling (#4212) PR #4174 unified upload-context injection on <current_uploads> (IM and web both flow through UploadsMiddleware), and #4632 documented the current path. This removes the remaining backward-compat parsing of the pre-#4174 <uploaded_files> tag, the final cleanup item tracked by the issue: - deermem: only <current_uploads> is stripped from human turns before memory persistence, and the upload-sentence scrubber drops the legacy tag alternative. - mem0: the mirrored message filter recognises only <current_uploads>. - InputSanitizationMiddleware: remove the legacy tag from the blocked-tag denylist (it existed only because deermem parsed the old tag). - frontend: stripUploadedFilesTag / stripInternalMarkers / parseUploadedFiles and the message-list fallback parse only <current_uploads>; demo thread fixtures are migrated to the current tag. Scope decision: a <uploaded_files> block in pre-#4174 history is now treated as ordinary user content (pinned by tests in both layers) instead of being silently dropped or stripped. * style: apply prettier formatting to stripUploadedFilesTag * fix(uploads): keep legacy <uploaded_files> stripping for display/export only Addresses review feedback on #4826: removing the legacy tag from the frontend display layer made pre-#4174 threads render raw <uploaded_files> XML (with server-side upload paths) in chat, copy data, and JSON exports. The backend cleanup stands — memory pipelines and the sanitization denylist treat only <current_uploads> as an internal marker. The frontend keeps the legacy spelling in its display/export-only utilities (stripUploadedFilesTag / INTERNAL_MARKER_TAGS / parseUploadedFiles and the message-list fallback) so old history renders cleanly without leaking internal paths, while the memory/sanitization scope-decision tests remain unchanged. Frontend tests now pin both spellings: <current_uploads> and legacy <uploaded_files> are stripped from copy data, markdown leak-stripping, and JSON exports. * docs(ui): record accepted display-spoof tradeoff for legacy upload tag Review note (willem-bd): since <uploaded_files> is off the sanitization denylist, a live user can type the legacy spelling and fabricate file chips / hide their own message text in display. Display-only and self-inflicted with no backend semantics, so it is accepted for now; documented at both the message-list fallback and stripUploadedFilesTag. Age-gating the legacy spelling remains a possible follow-up. --------- Co-authored-by: betterkite <313258397+betterkite@users.noreply.github.com>	2026-09-01 15:26:33 +08:00
Aari	cdc886ae85	fix(sandbox): make tool descriptions optional (#4878) ... * fix(sandbox): make tool descriptions optional * fix(sandbox): address optional description review * test(sandbox): pin optional description contracts	2026-09-01 14:15:26 +08:00
Janlay	45adb8fbb5	perf(runtime): bound gateway memory after terminal runs (#5112) ... * fix(runtime): clean up terminal run records * perf(sandbox): bound local path caches * perf(runtime): release terminal run cycles * fix(runtime): address terminal cleanup review * fix(runtime): clean up after end publish failure * fix(runtime): guard terminal cleanup from cancellation * fix(runtime): discard fenced journal buffers * fix(runtime): harden abort and teardown paths	2026-09-01 10:56:43 +08:00
Yufeng He	a4f6665ef4	fix(security): sanitize MCP-sourced tool results through the same trust boundary (#4839) ... * fix(security): sanitize MCP-sourced tool results through the same trust boundary Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com> * fix(security): sync the trust-boundary docs with tag coverage and pin the untagged branch Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com> --------- Signed-off-by: Yufeng He <40085740+he-yufeng@users.noreply.github.com>	2026-09-01 09:49:32 +08:00
Willem Jiang	530b4cf6a0	fix(ci): keep fixing the skill reviewer error (#5122) ... * fix(ci):resolve the skill_review errors * fix(ci): split skill creator fixes from waiver rollout * fix(skill-creator): address review findings	2026-08-31 23:40:08 +08:00
hataa	17cac3420a	fix(subagents): clean up background task entry on unexpected poller exit (#5069) ... * fix(subagents): clean up background task entry on unexpected poller exit * fix(subagents): pin deferred cleanup to the persistent subagent loop The non-terminal fallback scheduled the deferred registry cleanup with asyncio.create_task on the poller's own loop. Under synchronous tool invocation the sync wrapper runs the tool coroutine through asyncio.run(), which cancels caller-loop tasks at teardown, so the cleanup died before executing and the _background_tasks entry leaked — the same lifecycle leak the terminal path already fixed. Schedule the deferred cleaner on the process-owned persistent subagent loop instead, via the new public executor helper run_on_isolated_subagent_loop (asyncio.run_coroutine_threadsafe). The cleaner only touches thread-safe registry helpers, so it is loop-agnostic. A caller-loop fallback remains for the unreachable case where the persistent loop cannot be obtained, so scheduling never raises out of an unwind path that is already handling an error. The polling-timeout return path, which shares the scheduler, is fixed the same way. Tests no longer stub the scheduler: the non-terminal fallback test drives the real scheduling wrapper on an equivalent long-lived loop and asserts cleanup runs after asyncio.run() tears the caller loop down, and run_on_isolated_subagent_loop itself is covered against the real persistent loop with the caller loop closed underneath. * fix(subagents): harden interrupted finalization against failing status path Three edge cases from review on the unexpected-exit unwind: 1. Finalization no longer depends on the failing status accessor. _peek_subagent_result distinguishes a gone entry from an unreadable one instead of letting the accessor's exception abort the unwind; _finalize_interrupted_subagent never raises (so the original poller exception is preserved) and attaches the deferred cleaner, whose last resort force-removes a persistently unreadable entry via the new executor force_cleanup_background_task. 2. The generic-error unwind waits only a short grace period (_UNEXPECTED_EXIT_GRACE_SECONDS) instead of the full execution timeout before re-raising; the remaining lifecycle stays with the deferred cleaner on the persistent subagent loop. 3. The deferred cleaner reports the subagent's final usage (deltas since the unwind snapshot included, via final=True bypassing usage_reported; the journal dedupes by source_run_id) before removing the terminal entry. The report is transferred in a plain worker thread so the RunJournal's loop-bound progress flush is skipped rather than scheduled on a foreign loop. * fix(subagents): pin deferred final usage delivery to the parent run loop _report_deferred_final_usage ran record_external_llm_usage_records in a to_thread worker, making it the first cross-thread RunJournal writer: the unlocked accumulators can lose token updates and _tokens_by_model mutations race get_completion_data() iteration on the parent loop. Capture the parent loop at unwind time (it is alive in every path that continues the run) and deliver the final report onto it with call_soon_threadsafe, serialized with all other journal access; when that loop is already closed (asyncio.run teardown) the report is dropped on purpose — the run has persisted and nothing reads the counters back. The live-loop test exercises the real recorder path (journal captures the running loop of every call) instead of stubbing _report_subagent_usage, so a cross-thread report would surface as a wrong-loop entry. Also gates the two teardown tests on the caller loop actually closing (the deferred cleaner could otherwise legitimately deliver while that loop is still winding down), and adds a task_tool-level regression test for execute_async submit failure leaving no registry residue (rolled back inside execute_async since #5086). * docs(subagents): document the reverse loop boundary; observability + test fixes Extend subagents/AGENTS.md's Isolated-loop callback boundary with the reverse-direction contract from #5069: deferred registry cleanup is pinned to the persistent subagent loop via run_on_isolated_subagent_loop, and the final usage report is handed back onto the parent run's loop captured at unwind time — never invoked from the persistent loop or a worker thread, which would silently reintroduce the journal accumulator/iteration race. Dropping the final report (closed parent loop) is the one path where a subagent's tail usage goes permanently unaccounted, so both drop branches now log at info with the execution id and the unaccounted record count. Restore the retention assert in test_deferred_cleanup_task_retained_and_ survives_gc: the bounded wait observes the production done-callback discard, the assert (not a manual discard) is what fails if that callback is deleted. * fix(subagents): honour grace-wait cancellation and shrink deferred-cleaner captures Two review follow-ups on the unwind: - The shared unwind absorbs CancelledError (never-raise contract), so a graph-node cancellation landing inside the generic-error grace wait was swallowed and the node ended as a failed tool call instead of an interrupted run. The generic branch now re-checks task.cancelling() after the unwind and re-raises CancelledError; the absorb site documents why the cancellation path needs it and where the discrimination lives. - The deferred cleaner captured the whole run runtime, pinning the parent run's journal and event store for up to a full poll budget (~31 min) via the strongly-held task handle — worst on the polling-timeout path, where a stuck subagent pinned its run's journal for a second full timeout after the tool returned. The recorder is now resolved on the unwind path and is the only capture (plus ids and the report loop); a None recorder skips reporting entirely. Both behaviours are regression-tested (red on the previous head, green after): a cancellation parked inside the grace wait surfaces as CancelledError, and the runtime is collectable while the cleaner still polls. The closed-loop drop test now uses a real recorder via runtime.callbacks so the drop it pins is loop-based, not recorder-absence.	2026-08-31 23:38:12 +08:00
早上肚子疼	3b601922ff	fix(buzz): move seen-event persistence off event loop (#5103) ... * fix(buzz): move seen-event persistence off event loop * fix(buzz): address seen-event persistence review * fix(buzz): replace stale scheduled flush tasks * fix(buzz): harden final seen-event flush * fix(buzz): make seen-event shutdown retryable * fix(buzz): quiesce persistence after channel stop * fix(buzz): drain late events on repeated stop --------- Co-authored-by: zaoshangduziteng <309590849+zaoshangduziteng@users.noreply.github.com>	2026-08-31 23:18:34 +08:00
Willem Jiang	1af79c7bcf	fix(ci):resolve the skill_review errors (#5121) ... * fix(ci):resolve the skill_review errors * fix(ci): split skill creator fixes from waiver rollout	2026-08-31 23:17:39 +08:00
PeaceMaker-best	72ba661b84	feat(skills): install local skill archives (#5039) ... * feat(skills): install local skill archives Signed-off-by: PeaceMaker-best <221849497+PeaceMaker-best@users.noreply.github.com> * fix(skills): enforce upload limits before parsing * fix(nginx): scope skill upload limit to upload route * fix(nginx): harden skill upload proxy handling * fix(skills): improve archive upload feedback * fix(skills): address upload review polish --------- Signed-off-by: PeaceMaker-best <221849497+PeaceMaker-best@users.noreply.github.com> Co-authored-by: PeaceMaker-best <221849497+PeaceMaker-best@users.noreply.github.com>	2026-08-31 15:22:45 +08:00
Terminator666666	c17aa8b98f	fix(mcp): reject credentials that cannot travel as HTTP header values (#5066) ... * fix(mcp): reject credentials that cannot travel as HTTP header values A request-scoped secret or user_auth credential with a trailing newline (the usual result of reading a token from a file, or a CRLF env-file), CR/LF, surrounding whitespace, or characters outside Latin-1 sailed through the credential interceptors into the HTTP client, where httpx/h11 reject it with an exception that echoes the full value: LocalProtocolError: Illegal header value b'Bearer sk-...\n' ToolErrorHandlingMiddleware copies that message into a model-visible ToolMessage, so the secret landed in the prompt, the checkpoint, and traces - everywhere headers_from_context promises it never goes. Add illegal_header_value_reason to mcp/headers.py, mirroring the transport's own rules (Latin-1 encodable; h11's field_vchar is [^\x00\s] with SP/HTAB legal only between visible characters), and fail closed in both interceptors before the value can reach the client. The denial names only the secret key (plus the reason) and never repeats the value. Illegal values are denied regardless of on_missing: the key is present, so a passthrough fallback would silently run the call under the shared discovery credential - the exact authority confusion the deny default exists to prevent. Values the transport accepts are not rejected: embedded SP/HTAB ('Bearer <token>'), Latin-1 high bytes, and DEL all still pass, pinned by tests against h11's observed behaviour. * fix(mcp): tighten header value validation to httpx's ASCII boundary The validator mirrored h11's Latin-1 boundary, but the transport rejects more than h11 does: build_server_params hands dict[str, str] headers through the MCP SDK's create_mcp_http_client into httpx.AsyncClient, and httpx (pinned 0.28.1) encodes str header values as ASCII - so a Latin-1 high byte like 'Bearer caf\xe9' passed validation here only to raise UnicodeEncodeError inside httpx before h11 ever ran, with the exception message repeating the offending value. Validate str values against ASCII instead, flip the tests that pinned Latin-1 high bytes as transportable, and pin the boundary against the real client: create_mcp_http_client must reject what the validator flags and construct cleanly for what it accepts (embedded SP/HTAB and DEL still pass). Addresses review feedback on the ASCII vs Latin-1 boundary. * fix(mcp): validate OAuth and static header values at the same boundary The validator added for headers_from_context and user_auth left two paths uncovered. A token endpoint returning an access_token or token_type with a newline reached httpx/h11, which raise with the full token in the message, and ToolErrorHandlingMiddleware copies that message into a model-visible ToolMessage -- the leak this PR set out to close. The operator's static headers had the same hole. OAuthTokenManager.get_authorization_header now renders the Authorization value through one checked helper, so the tool interceptor, the initial discovery headers and the durable task path are all covered by a single guard. The rendered value is what gets checked rather than the two fields separately, because that is what the transport sees: an access_token with leading whitespace is legal once it follows "Bearer ". build_server_params applies the same check to statically configured headers. build_servers_config already isolates a per-server failure, so a bad value drops that one server and logs the reason instead of the value. * docs(mcp): correct which transport echoes the full header value The rationale claimed httpx and h11 both render the full value into their exception message. Only h11 does, on the line break and surrounding whitespace cases. httpx's ASCII failure is a UnicodeEncodeError naming the offending character and its position, not the credential, so at most one character escapes there; refusing the value up front buys an actionable error rather than an encode failure raised from inside the client. Corrected in headers.py and in every copy of the claim: context_headers.py, user_scoped_auth.py, oauth.py, client.py, mcp/AGENTS.md, docs/MCP_SERVER.md, the frontend mcp.mdx, and the test comments carrying the same wording. No behavior change. --------- Co-authored-by: Terminator666666 <Terminator666666@users.noreply.github.com>	2026-08-31 15:07:30 +08:00
Aari	317577e285	fix: enforce custom agent skill allowlists in sandboxes (#5077) ... * fix: enforce agent skill allowlists in sandboxes * fix: guard E2B skill projection resets * fix: preserve agent skill isolation across delegation * fix: close sandbox skill isolation bypasses * fix(sandbox): close skill isolation review gaps * fix(sandbox): harden skill isolation lifecycle	2026-08-31 14:35:08 +08:00
luo jiyin	42796d7086	test: isolate Docker bridge gateway fallback from host DNS (#5107) ... * test: isolate Docker bridge gateway fallback from host DNS Force the fallback-path test to bypass host DNS resolution. Production bind-host behavior is unchanged. Refs #5106 * test: document Docker fallback isolation Explain why the fallback test must replace host DNS resolution. Refs #5106	2026-08-30 22:24:32 +08:00
Stellar鱼	11e6cdd7e7	fix(frontend): preserve interrupted uniform-run order (#4834)	2026-08-30 22:19:52 +08:00
luo jiyin	3820515155	fix(test): exclude blocking I/O suite from make test (#5105) ... * fix(test): exclude blocking I/O suite from make test Keep make test-blocking-io as the dedicated suite owner. Add regression coverage for the Makefile contract. Refs #5088 * test: pin blocking I/O workflow ownership Document both targets required for full offline validation. Keep the dedicated workflow and Makefile target under contract coverage. Refs #5088 * docs(test): align blocking-I/O test guidance	2026-08-30 22:05:24 +08:00
Ryker_Feng	8c8c5ac246	feat(search): add native recency filters (#5099) ... * feat(search): add native recency filters * fix(search): enforce recency across backends * docs(search): record recency provider contract	2026-08-30 21:25:05 +08:00
Yuzhong Zhang	8eda71fd97	fix(agents): normalize Command-wrapped tool results (#4977) ... * fix(agents): normalize Command-wrapped tool results Command-wrapped ToolMessages skipped result metadata and progress tracking, so error receipts could be recorded as success. * fix(agents): stamp error meta from subagent_status failures Delegated task Commands leave ToolMessage.status at success and do not use an Error: content prefix, so normalize_tool_message was labeling failed/cancelled/timed_out results as success. Honor structured subagent_status before content heuristics and cover the four statuses. * style: ruff-format tool_result_meta tests --------- Co-authored-by: Yuzhong Zhang <BetterAndBetterII@users.noreply.github.com>	2026-08-30 15:37:38 +08:00
PeaceMaker-best	137a3cb60d	fix(authz): recheck policy before sandbox reuse (#5006) ... * fix(authz): recheck policy before sandbox reuse * fix(authz): avoid duplicate async sandbox checks * fix(authz): scope sandbox decision across middleware * fix(authz): construct async providers on the event loop * test(authz): avoid cold imports under Blockbuster --------- Co-authored-by: 嗜鵼 <hy2010hy2010@qq.com> Co-authored-by: PeaceMaker-best <221849497+PeaceMaker-best@users.noreply.github.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com>	2026-08-30 15:29:51 +08:00
Wu Shuwen	a4e2a2b934	fix(sandbox): bound Windows command execution (#4946) ... * fix(sandbox): bound Windows command execution * fix(sandbox): preserve Windows output encoding * fix(sandbox): honor Python UTF-8 mode * fix(sandbox): normalize captured command newlines * fix(sandbox): scope newline normalization to Windows	2026-08-30 15:06:55 +08:00
hataa	d1c06eee96	test(gateway): sweep mcp_tasks and subagent_batches in thread_id route contract, fixes #5061 (#5098)	2026-08-30 14:30:16 +08:00
hataa	56454af931	perf(frontend): cache settled copy-data derivation across streaming chunks (#5095) ... * perf(frontend): cache settled copy-data derivation across streaming chunks Every SSE values chunk re-renders MessageList, and the re-render re-derived copy/toolbar text for every settled row: getAssistantTurnCopyData re-ran the O(turn bytes) content extraction per settled group, and MessageListItem's toolbar recomputed getMessageCopyData per message. Settled group arrays keep their identity across chunks (deriveStableMessageGroups), so both derivations now cache on that stable reference: a WeakMap keyed on the messages array for turn copy data, and a useMemo on message identity for the toolbar copy text. Fixes #5094 * fix(frontend): gate row copy-data memo and correct cache win claim Address review: derive one memoized copy value only when isHuman || (!isLoading && showCopyButton) and reuse it for both editing and the toolbar, so settled assistant rows (whose toolbar never renders) skip the derivation and human rows derive once, not twice; correct the assistantTurnCopyDataCache comment — the regex/trim split is already cached per message, the cache's win is the traversal/allocations for string turns and the uncached O(bytes) map/join/trim for array-content turns (benchmarked: 5.1x / 17.2x per settled history sweep). * style(frontend): expand single-line messages array for Prettier	2026-08-30 14:28:43 +08:00
Zeren Wang	22b0456e45	feat(harness): subagent report contract and delegation acceptance criteria (#5090) ... * feat(harness): subagent report contract and delegation acceptance criteria (RFC #4651 PR3) Layer 1 receipt verification is inert unless subagents actually cite their execution record. This lands the prompt layer that closes the adoption gap: - New subagents/report_contract.py owns the model-facing contract text, derived from the single-owner citation format (format_citation / receipt_id) so prompts can never drift from the verifier. The executor injects <report_contract> into every subagent system prompt — built-in and custom alike — requiring [rN tool_name] citations for action claims, verifiable handles (absolute path, URL, ID, HTTP status) for deliverables, and explicit failure reporting; the citation clause follows verification.receipts_enabled. - The task tool gains an optional keyword-only acceptance_criteria parameter, handed to the SubagentExecutor constructor and rendered into the subagent's SystemMessage (stripped, capped 20 items x 500 chars) — deliberately never the task HumanMessage, which InputSanitizationMiddleware classes as genuine user input and would HTML-escape into untrusted-input framing. The docstring frames subagent results as self-reports, states the citation cross-check's evidence boundary (resolved = the call happened, not that the claim is correct), and documents when to attach criteria with the canonical leaf forms. Deterministic leaf checking remains a separate layer. - The lead delegation workflow now instructs reading the ledger citation line as execution evidence only and spot-checking verifiable handles before synthesizing. - report_contract / acceptance_criteria are registered as blocked framework-authority tags in input sanitization so untrusted input cannot forge the verification contract. * fix(harness): neutralize acceptance criteria before system-channel injection render_acceptance_criteria_section interpolated lead-model-supplied acceptance_criteria verbatim into the subagent SystemMessage after only stripping/capping. A criterion such as '</acceptance_criteria><system>...</system>' could close the wrapper and open a framework authority tag, bypassing InputSanitizationMiddleware. Route each criterion through neutralize_untrusted_tags (the shared prompt-injection primitive) so blocked authority tags are HTML-escaped before interpolation. Add regression tests at the renderer and the executor _build_initial_state path. * fix(harness): keep model-supplied criteria off the system channel - Move acceptance_criteria values into the task HumanMessage — the untrusted channel InputSanitizationMiddleware escapes and boundary-frames. The subagent SystemMessage now carries only a framework-owned <acceptance_criteria> pointer note (no criterion text), so natural-language injection inside a criterion keeps task-data priority and cannot override framework instructions (PR #5090 review, willem-bd P1). - Condition the lead delegation workflow's citation verification guidance on verification.receipts_enabled and qualify the task tool's result-reading text with the enabled state, so a receipts-disabled configuration no longer tells the lead to require citation evidence that cannot exist (P2). * fix(harness): drop execution-record promise from report contract when receipts are disabled The <report_contract> opening was emitted unconditionally, so a verification.receipts_enabled=false subagent was told its report would be cross-checked against an execution record that cannot exist in that mode (terminal_receipts() returns None; no verdict, no ledger citation line). The opening now follows receipts_enabled: enabled keeps the cross-check language, disabled describes the handle-only review mode (PR #5090 review, willem-bd P2). * docs: record the prompt-layer trust-boundary self-check Generalizes the PR #5090 review outcome: before adding prompt text, ask of every data source in it what trust level it has and which channel it should ride — model/user-influenceable values ride the untrusted sanitized data channel, never framework-owned system text. Added to the PR template (Agents/LangGraph surface) and agents/AGENTS.md.	2026-08-30 11:39:25 +08:00
hataa	567a06783c	fix(mcp): tear down the in-flight owner when get_session is cancelled mid-eviction (#5008) ... * fix(mcp): keep session owner teardown safe across cancellation paths * fix(mcp): gate pooled-session publication on the commit inside the owner task The owner resolved `ready` as soon as initialize() finished, but the session only became pool property when the creator promoted it into _entries in Phase 4. A concurrent get_session() could join the in-flight creation and receive that session from Phase 2b while the creator was still parked in the Phase-2 eviction teardown; cancelling the creator then ran the Phase-2 unwind, which unconditionally shut the owner down — closing the session underneath the joiner (#5008 review). Move the commit into the owner task: initialize() success now pops the in-flight record, registers the session in _entries, and resolves ready with the session in one atomic critical section, so 'ready resolved with a result' is exactly 'session registered and pool-owned'. Joiners can therefore only ever receive a committed session, and both creator unwind paths (Phase 2 and Phase 3) skip teardown when the creation already committed, leaving the pooled session to LRU eviction / close_*. When the record was removed before the commit (close_* or creator unwind), the owner aborts and ready carries the same cancellation the old Phase-4 not-still-ours path raised, so joiners fail with the creation's outcome instead of hanging or holding an unmanaged session. test_cancelled_creator_does_not_close_session_held_by_joiner reproduces the review's scenario deterministically (MAX_SESSIONS=1, hung LRU victim, gated initialize, second caller receives the session, creator cancelled): red on the previous commit, green now. test_joiner_follows_creation_outcome_when_creator_is_cancelled pins the joiner outcome-gating semantics as a drift guard.	2026-08-30 11:36:26 +08:00
luo jiyin	0dd233afc4	feat(sandbox): make E2B mount upload deadline configurable (#4876) ... * feat(e2b-sandbox): make mount upload deadline configurable Replace the hardcoded 120-second mount upload deadline with a configurable `mount_upload_deadline_seconds` key read from SandboxConfig (extra=allow). The value is validated: zero and negative inputs are clamped to 1 second. Omitting the key preserves the existing 120-second default. This addresses the follow-up from PR #4842 review: operators with large mounts or slow networks can now size the deadline to their deployment without changing code. * fix(e2b-sandbox): address review feedback on configurable deadline - Remove import-time default capture from _mount_deadline_reason() and _MountUploadBudget.deadline_seconds to prevent silent drift. - Add warning log when mount_upload_deadline_seconds is clamped to 1 (was silent before). - Update AGENTS.md E2B Mount Uploads section: deadline is now configurable, not fixed 120. - Add mount_upload_deadline_seconds to YAML examples in provider docstring and __init__.py. - Add config-path test that exercises SandboxConfig -> _load_config -> _apply_mounts end-to-end. * fix(e2b-sandbox-provider): handle non-numeric mount_upload_deadline_seconds Guard _resolve_mount_upload_deadline against None, non-numeric strings, and other invalid values. None returns the default; non-numeric strings like '120s' or 'abc' log a warning and fall back to the 120-second default instead of crashing provider init with TypeError/ValueError. Extend the parametrized clamp test with None, suffix, and alpha cases, and add a warning assertion. Update CONFIGURATION.md with the new mount_upload_deadline_seconds key and its behavior. * fix(sandbox): handle infinite mount deadline	2026-08-30 11:31:53 +08:00
Stellar鱼	468eab4b5d	fix(frontend): stabilize model load error feedback (#5021)	2026-08-30 10:56:55 +08:00
Wuong	e12925458a	feat(streaming): make heartbeat interval configurable (#5017) ... Co-authored-by: Wuong <26929475+Wuong@users.noreply.github.com>	2026-08-30 10:46:01 +08:00
hataa	2f8d1cfc21	fix(subagents): harden background-task registry and capacity snapshot edge cases (#5086) ... * fix(subagents): harden background-task registry and capacity snapshot edge cases - execute_async drops the just-registered background entry when submitting to the isolated loop fails. The caller sees the exception and never polls, and cleanup_background_task refuses non-terminal entries, so the entry would otherwise stay as a PENDING zombie forever. - SubagentExecutionCapacity.snapshot derives queued from len(_waiters) instead of iterating it. snapshot is read from non-loop threads (e.g. configure_subagent_execution_capacity) while the loop thread mutates the deque, so iteration can raise 'deque mutated during iteration'. The raw length may count a waiter that just timed out but has not removed itself yet, which only makes the busy-check more conservative. * fix(subagents): close failure-path gaps around background submit Address both review findings on the background submission lifecycle: - execute_async() copies the isolated-loop context before registering the _background_tasks entry, so a context-copy failure (callback- manager copy or loop-bound handler filtering) can no longer strand a permanent PENDING entry the caller will never poll. - _submit_to_isolated_loop_in_context() resolves the loop before calling the coroutine factory. As direct run_coroutine_threadsafe arguments the coroutine was created first, so a loop-startup failure stranded a never-awaited coroutine (RuntimeWarning + retained captures until collection). Both call sites share the fix. New tests verified red on the previous implementation, green after: - context-copy failure leaves no registry residue - the real submit helper (only the loop getter patched) never invokes the coroutine factory when loop startup fails * fix(subagents): close the coroutine when scheduling rejects it run_coroutine_threadsafe can itself raise once the coroutine exists (e.g. the loop closes between the lookup and the internal call_soon_threadsafe). Wrap the call, close the rejected coroutine, and re-raise; a focused test patches only run_coroutine_threadsafe and asserts the created coroutine reaches CORO_CLOSED.	2026-08-30 10:43:58 +08:00
Aniket Wagh	8a830f6354	fix(deps): depend on renamed tenki package instead of tenki-sandbox (#5087) ... * fix(deps): depend on renamed tenki package instead of tenki-sandbox tenki-sandbox has been removed from PyPI and republished as tenki. Its old wheel URL still resolves, so existing lockfiles keep installing and the breakage is invisible to anyone with a warm lock; any fresh resolution fails with 'tenki-sandbox was not found in the package registry'. tenki 1.0.2 still ships the tenki_sandbox module, so the imports in community/tenki/provider.py and sandbox.py are unchanged. Fixes #5081 * fix(tenki): point install guidance at the renamed distribution The rename to `tenki` left the user-facing remediation still naming the removed package. `_import_client` raised "pip install tenki-sandbox" on the missing-extra path — the exact instruction this change proves now 404s on PyPI, handed to the user at the exact moment they need it to work. Update that message and the remaining `tenki-sandbox` references in the provider, sandbox adapter, README, sandbox AGENTS.md and the test docstring. The imported module stays `tenki_sandbox`, so the distribution and module names now differ; each mention says so rather than just swapping the string. No behavior change beyond the error text. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * fix(tenki): migrate the provider to the 1.x workspace-only API Renaming the dependency was not enough. tenki 1.0.2 keeps the tenki_sandbox module name but not its contract: Client.create dropped project_id and has no **kwargs to absorb it, and IdentityWorkspace no longer carries `projects` (the attribute is gone from the package entirely). Both configuration paths therefore failed before a sandbox could be created — explicit project scope raised TypeError, and automatic scope raised AttributeError walking workspace.projects. Scope is now the workspace alone. _resolve_scope returns a single workspace id, auto-selecting when the account has exactly one, and project_id is gone from create_kwargs and from the documented config surface. A stale project_id in config.yaml warns rather than fails. SandboxConfig is extra="allow", so simply not reading the key would leave it scoping nothing with no signal; it also used to short-circuit the identity lookup, so operators with more than one workspace need to know they must now set workspace_id. The suite passed against the broken provider because the fake client took **kwargs and swallowed the project_id the real SDK rejects. The double now mirrors 1.0.2 — keyword-only, no **kwargs — so an unexpected argument is a TypeError in tests exactly as it is against the SDK. Reintroducing the old create call fails 20 tests; before this change it failed none. Verified against the exact locked wheels: every other kwarg the provider passes (name, workspace_id, sticky, wait, max_duration, image, cpu_cores, memory_mb, env) and every SDK surface it touches (who_am_i, Identity.workspaces, wait_ready, exec, close, the fs API, the four terminal exception classes) is unchanged in 1.0.2. Reported by willem-bd in review. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> * docs(config): drop sandbox.project_id from the Tenki example The canonical example still documented project_id as a supported optional key after the provider stopped honouring it, so an operator following it could set the key, get no scope from it, and hit a workspace-resolution failure with nothing in the example to explain why. Replaced with a migration note rather than a silent deletion: someone upgrading already has the key in their config.yaml and needs to know it is inert now and that workspace_id is what scopes a sandbox on Tenki 1.x. --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com> Co-authored-by: Aniket Wagh <aniketwaghh@users.noreply.github.com>	2026-08-30 10:37:58 +08:00
Zeren Wang	bb75f8d736	feat(sandbox): share sandbox identity derivation and acquire serialization (#4741) (#5089) ... * feat(sandbox): share sandbox identity derivation and acquire serialization (#4741) Remote providers (AIO, E2B, BoxLite, Tenki, OpenSandbox) each inlined the same sha256(user:thread)[:16] sandbox-id expression and kept per-scope lock dicts that grew unboundedly until shutdown. This extracts both mechanisms into shared components without changing provider lifecycle, ids, capacity semantics, or public tool behavior: - sandbox/identity.py: keyword-only derive_sandbox_scope_token (byte-pinned compatibility contract) + is_sandbox_scope_token; per-provider golden vectors pin current behavior including BoxLite's raw-None quirk and each provider's private user_id resolution. - sandbox/acquire_serialization.py: AcquireSerializer — per-key lock table with holder/waiter refcount reclamation, bounded dedicated executor (async waits off both the event loop and the default executor), worker-owned cancellation cleanup (no event-loop callback dependency), idempotent close(). - Each provider adopts both components; AIO/E2B key by (user_id, thread_id) with acquire and (E2B) release serialized; BoxLite/Tenki/OpenSandbox key by derived sandbox id and offload the whole sync acquire to the serializer's executor so a cancelled awaiter cannot overlap a retried same-scope body (leaked-remote-VM regression caught in review). - thread_id=None acquires stay unserialized; provider shutdown()/reset() close the serializer; E2B capacity/ledger/reconciliation and AIO ownership/flock machinery untouched. - blocking-IO anchor proves contended OpenSandbox acquire_async stays off the event loop (teeth verified red/green); AGENTS.md documents the shared components. * refactor(sandbox): address review on acquire serialization (#5089) - Replace unreachable checkin branch with an assertion: run() returns False only after abandon(), which the except handler always re-raises; the old _checkin would have double-decremented the refcount. - Document the task.cancelling() == 0 assumption in hold_async. - Drop unused thread_id/user_id kwargs from BoxLite and Tenki _acquire_scope_locked (OpenSandbox still forwards them). * fix(sandbox): preserve request ContextVars in acquire executor bridge (#5089) loop.run_in_executor() does not copy contextvars, unlike the inherited SandboxProvider.acquire_async() which used asyncio.to_thread(). The BoxLite/OpenSandbox/Tenki acquire_async bridges introduced in this PR therefore dropped the request trace id (logged as trace_id=-). Add AcquireSerializer.run_on_executor(), which copies the calling context and runs the callable through ctx.run, and route all three providers through it. Add regression tests binding request_trace_context and verifying the worker thread observes it.	2026-08-30 10:30:34 +08:00
Sunshine	bf740ffa90	feat(auth): add personal access tokens for programmatic API access (#5041) ... * feat(auth): add personal access tokens for programmatic API access (#4849) Backend-first implementation of the PAT contract from #4849: show-once dfp_ tokens bound to their owning user (AUTH_SOURCE_PAT, is_internal=false), digest-only storage (migration 0017), strict credential precedence (invalid Bearer is a 401, never cookie fallback), CSRF double-submit skipped only for Bearer requests while auth-endpoint origin checks still run, scopes intersecting the authz route permissions, session-auth-only PAT management and password changes, and throttled best-effort last_used_at stamps. * fix(auth): harden PAT scope boundary and schema parity from adversarial review Independent review of the initial draft found: (1) scopes only constrained the threads/runs permission axis while admin routes treated a PAT as its (possibly admin) owner — is_admin_user now rejects PAT callers outright since no scope grants admin capability; (2) the model declared a column UNIQUE constraint while migration 0017 created a named unique index, so downgrade failed on create_all-bootstrapped DBs — both now use the named unique index; (3) auth-disabled mode is an operator override and now stays ahead of the Bearer check so a stray Authorization header cannot 401 an E2E sandbox; plus wiring the previously-unused constants, bounding the last_used_at stamp cache, and four new tests (middleware-level expiry, expires_in_days, admin-capability rejection with session control, and the auth-disabled precedence). * docs(api): document personal access tokens for programmatic API access * fix(auth): close PAT security boundaries from review (default-deny routes, extension admin suppression) P1-1: scope intersection only constrains @require_permission routes, so undecorated mutation routes (DELETE /api/memory, POST /api/agents, Lark credential switching, channel config) accepted a PAT holding a single read scope. AuthMiddleware now enforces a default-deny route policy in auth/pat.py: PAT requests are admitted only to the thread/run lifecycle routes the v1 scopes govern; everything else answers 403 regardless of scopes. Session-cookie callers are unaffected. P1-2: the extension principal resolver projected is_admin/roles from the raw system_role, so an admin-owned PAT passed deerflow_extension_api.require_admin on contributed routes despite the documented no-admin guarantee. The projection is now PAT-aware and suppresses every admin signal for PAT callers, mirroring deps.is_admin_user. Both fixes carry regression tests (route outside policy 403 + session control; production resolver admin suppression), and API.md documents the default-deny boundary. * fix(auth): enforce PAT scopes on stateless run entry and harden decorator Follow-up hardening from an independent audit of the P1 fixes: - POST /api/runs/stream and /api/runs/wait were the only allowlisted run entrypoints without @require_permission, so a threads:read-only PAT could still start runs (same bug class as P1-1, now closed): both now carry @require_permission("runs", "create"). POST /api/threads and POST /api/threads/search gain threads:write / threads:read for the same reason. Authorization-disabled deployments see no change (the permission set resolves to all permissions). - require_permission now binds the wrapped signature to locate a positionally-passed request before injecting the test stub, fixing 'got multiple values for argument' on direct positional unit-test calls. - API.md: the intro PAT example used GET /api/models, which the new default-deny policy 403s — replaced with GET /api/threads; the default-deny route list now spells out method sets. Regression test: threads:read-only PAT is 403 on the decorated stateless entry while a runs:create PAT passes. * fix(auth): address review P2s (empty Authorization header, PAT name trimming, API example) - CSRFMiddleware treats an explicitly empty Authorization header as present (is None), so an invalid credential always reaches AuthMiddleware's uniform 401 instead of a CSRF 403 that varies by method/CSRF state. Regression: empty-header request dies at auth. - PATCreateRequest strips the name and rejects whitespace-only values before token generation; created names are stored trimmed. - API.md intro PAT example now uses the implemented POST /api/threads/search endpoint (GET /api/threads does not exist). - AGENTS.md trimmed back under the guidance soft budget after the upstream merge. * fix(auth): tighten PAT route policy to implemented methods only The allowlist admitted GET /api/threads, a method no router implements. Pre-authorizing a dead method weakens the default-deny boundary: a future GET collection route added without a permission decorator would become PAT-reachable without an explicit policy change. Restrict the rule to POST, fix the stale GET description in API.md's PAT constraints, and document the default-deny boundary accurately in the gateway AGENTS.md guidance (only the threads/runs allowlist is PAT-reachable; every other authenticated route 403s PAT callers). Audited every remaining rule against the mounted routers: all other method+path entries map to real routes. Regression: test_pat_policy_does_not_pre_authorize_unimplemented_methods. * test(auth): guarantee the negative digest test mutates the token token[:-1] + "X" is identical to the original whenever the generated token already ends in X (1/62), making the negative digest assertion fail intermittently. Choose the replacement character based on the existing tail so the mutated token always differs. * fix(auth): require runs:cancel for cancel-then-stream requests stream_existing_run is gated at runs:read so action-less stream joins work with read-only credentials, but its ?action=interrupt|rollback branch cancels the run — a separate permission. A runs:read-only PAT passed both the PAT route policy and the route decorator and could interrupt or roll back an active run, bypassing the runs:cancel scope. Decorators cannot express query-parameter-conditional permissions, so the check lives in require_cancel_permission_when_action(), applied at the top of the handler. Regression drives the real helper through the production middleware: runs:read-only PAT + action is 403, the same token joins action-less, runs:read+cancel passes, session control unaffected. * docs(changelog): add the PAT feature entry * docs(readme): add personal access tokens section Repo documentation-update policy requires user-facing features to update README.md in the same changeset; the PAT feature previously touched only backend/docs/API.md and the gateway AGENTS.md. * fix(auth): require runs:cancel for mutating multitask strategies All five run-creation entrypoints were gated only by runs:create, but RunCreateRequest.multitask_strategy accepts interrupt/rollback and start_run forwards it to create_or_reject, which terminates an already-active run. A runs:create-only PAT could therefore kill an existing run through a create request, bypassing runs:cancel. Decorators cannot express body-parameter-conditional permissions, and per-route checks leave the same hole for the next entrypoint, so the gate lives in start_run itself — the single choke point every run-creation path (HTTP routes and internal launchers) flows through. Regenerate launches pass multitask_strategy="reject" and are unaffected; requests without a stamped auth context (internal/test compositions) skip the gate. The check is the shared authz.require_cancel_permission_if primitive; require_cancel_permission_when_action now delegates to it, so every request dimension that carries cancel capability (query action, body strategy) flows through one gate. Regression drives the real middleware stack: runs:create-only PAT + interrupt/rollback is 403 with the exact detail, reject (explicit and default) stays available, runs:create+cancel passes, session control unaffected; a source anchor pins the gate inside start_run. * fix(runs): keep observer joins from applying creator cancel-on-disconnect sse_consumer's finally block applied the record's on_disconnect=cancel policy on ANY consumer's disconnect. The join surfaces (GET /join and the action-less GET/POST stream join) feed it the existing RunRecord, so anyone with thread read access — including a runs:read-only PAT — could cancel a locally-owned running run simply by closing the SSE connection, without runs:cancel. The policy expresses the creator's intent for their own connection; an observer's disconnect must never be read as that intent. sse_consumer gains apply_on_disconnect (default True). The two join surfaces pass False; the creating endpoints (thread-scoped and stateless create-and-stream) keep the creator semantics unchanged. wait_for_run_completion needs no change: its callers are creator-side or post-explicit-cancel paths only. Regression exercises a real generator close — the same machinery Starlette drives on client disconnect — against the production sse_consumer: creator stream disconnect cancels, observer join disconnect does not; a wiring anchor pins both join call sites and the creator defaults. API.md documents the cancel-capability constraint (this fix plus the action/strategy gates) in PAT Constraints. * test(auth): pin the multitask gate behaviorally; state wait invariant Independent adversarial review of the round-5 fixes found the P1-a regression only mirror-pinned: the source anchor could be satisfied by a comment, and deleting the gate from start_run would not fail the suite. This drives the production start_run directly — a create-only auth context gets 403 with the exact detail for interrupt, and a reject request with no cancel permission at all proceeds past the gate (never a permission 403). Also documents wait_for_run_completion's creator-side invariant (every caller is the creating endpoint or post-explicit-cancel) so a future observer wiring thinks twice before reusing it — the one-caller- away variant of the observer-disconnect P1. * docs(changelog): correct the PAT entry's digest and route-policy description The entry said HMAC digests (the implementation stores SHA-256 digests, as documented in API.md and pinned by the repository tests) and claimed the route policy admits 'implemented stateless endpoints' (it admits the thread/run lifecycle routes, narrowing further by scopes). Also notes the cancel-capability gate now covering action and multitask strategies. * fix(auth): enumerate the PAT runs route policy per implemented subroute The runs subtree rule was a GET|POST /runs(/.*)? wildcard — it pre-authorized every current and future subroute under /runs, including methods the router never implemented (e.g. GET /runs/stream), which is the same latent default-deny weakening the threads collection rule was tightened for: a future route added under /runs would become PAT-reachable without an explicit policy change. The wildcard is replaced with six segment-precise rules covering exactly the 14 implemented method+path combinations; the {run_id} slot necessarily matches any single segment, so the POST-only collection names (stream, wait, regenerate, edit-regenerate) are excluded from the GET run-id rule via negative lookahead — no dead method stays pre-authorized. Behavior for implemented routes is unchanged. test_pat_runs_policy_admits_exactly_the_mounted_routes derives the expected set from the mounted thread_runs router instead of a hand-maintained list: every implemented GET/POST route under /runs must be admitted, routes in this router outside the subtree stay denied, and representative unimplemented neighbors are denied — so adding a route under /runs now fails CI until it is explicitly allowlisted, and a removed route leaves a dead rule visible. API.md's PAT constraints list the enumerated routes and drops a feedback mention that belonged to the stateless /api/runs axis. * docs(migration): add the 0017 renumbering coordination note to 0017 The PR's migration-coordination comment states each migration file carries the note; the file did not. Adds it: numbering was generated against main head 0016 alongside #5078 and #4843; whoever merges first keeps the slot, the others renumber on rebase (revision/down_revision plus the bootstrap head assertions). * fix(auth): pad base62 tokens to a fixed 43-char width int.from_bytes discards leading zero bytes, so the unpadded encoder returned a variable-length body — empty for all-zero input, and shorter than 40 characters for any draw below 62**39 (~1 in 14.5M), leaving test_generate_pat_token_format probabilistically flaky and the token body without stable width (review round 6, P3). _base62 now left-pads with "0" to _base62_width(len(data)) — the exact integer digit count (62^43 > 2^256 > 62^42, so 43 for 32 bytes). The format test asserts the exact fixed width instead of a probabilistic floor, and a new unit test pins the all-zero, leading-zero-byte, and max-value edges deterministically.	2026-08-29 23:50:45 +08:00
Nefelibata	c6f6a01f56	fix(runtime): prevent IndexError in MemoryStreamBridge._make_gap on empty events buffer (#5047) ... * fix(runtime): prevent IndexError in MemoryStreamBridge._make_gap on empty events buffer * fix(runtime): handle empty stream replay gap bounds across backend and frontend - Clamp MemoryStreamBridge queue_maxsize at 1 and validate StreamBridgeConfig.queue_maxsize >= 1 - Update StreamGap docstring to clarify None retained bounds - Allow StreamReplayGapData and parseStreamReplayGap in frontend to accept string | null bounds, safely resuming when bounds are null - Add backend and frontend regression unit tests for queue clamping and null bounds replay gap * docs(stream-bridge): bump config_version and document empty buffer replay gap behavior * docs: document nullable gap bounds and sync helm config_version to 37	2026-08-29 17:21:29 +08:00
Zeren Wang	3b592c2053	feat(harness): subagent receipt citation verification (#5076) ... * feat(harness): subagent receipt citation verification - add receipt citation verification core - harvest subagent tool receipts at terminal status - transport subagent receipts and citation verdict via status contract - verify subagent report citations at task write-back - render citation verdicts in the delegation ledger * fix(gateway): strip forged receipt verdicts from the delegations channel normalize_input() and the checkpoint-state mutation sanitizer only stripped server-owned metadata from message-shaped values, so an external caller could submit a delegation entry carrying a forged receipt_verdict that render_delegation_ledger would present as runtime-owned execution evidence. Strip receipt_verdict from caller-supplied delegation entries on both the run-creation and thread-state mutation paths, with regression coverage for each. * fix(harness): close silent-pass gaps in the zero-citation heuristic The action-claim detector missed the most common completion verbs (fixed/added/tested/changed/...) and had no CJK coverage at all, so reports like 'I fixed the bug and added tests.' or '我已经创建了文件并运行了测试。' were treated as claim-free: citation_resolved=True with no ledger warning. Broaden the verb lists and add a language-independent safety net: when the run harvested receipts and a nontrivial (>=240 char) report cites none of them, flag it UNVERIFIED. Short claim-free confirmations remain a vacuous pass.	2026-08-29 16:56:56 +08:00
早上肚子疼	b41354d75f	fix(scripts): invoke repo shell scripts through an explicit interpreter (#5031) ... Recipes and scripts ran sibling shell scripts bare (./scripts/x.sh), so any checkout that lost the executable bit -- zip/tarball download, core.fileMode=false, non-POSIX filesystem -- failed with: make: ./scripts/docker.sh: Permission denied make: *** [Makefile:181: docker-start] Error 127 The tracked modes are already 100755, so chmod cannot fix it. Name the interpreter instead: the POSIX branch of RUN_SHELL_SCRIPT (renamed from RUN_WITH_GIT_BASH) now expands to $(BASH) rather than nothing, and the five script-to-script call sites are prefixed with bash. Fixes #2903 Co-authored-by: zaoshangduziteng <309590849+zaoshangduziteng@users.noreply.github.com>	2026-08-29 14:54:02 +08:00
qingbo1011	2eba65449f	eval(memory): add a reproducible hybrid eviction evaluation (#4810) ... * eval(memory): scaffold reproducible eviction evaluation * refactor(eval): align with benchmark layout * eval(memory): add deterministic QA grading Implement the disclosed deterministic-overlap-v1 grader as a pure offline module. Grading is blind by construction: grade_answer() accepts only the prediction and reference strings, never a policy identity. The undisclosed stopword list is committed as a fixed part of this grader version; yes/no/not are deliberately excluded because negation can be the entire answer. Before freezing, the grader locally reproduced all 90 historical (prediction, grade) pairs disclosed in #4789 with zero mismatches and no post-hoc tuning. validate-contracts now rejects a config whose qa.grader_version does not match the committed grader. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * eval(memory): add environment-configured QA runner Add the exact answer-prompt renderer (retained facts sorted by ID, CURRENT DATE line omitted when absent), an OpenAI-compatible provider adapter configured only through the environment variable names pinned in the config, and a resumable run-qa command that calls both policies with identical versioned settings. Each row persists as its own file on success, so a partial paid run resumes without repeating completed calls; qa_run.json binds an output directory to one config identity. Row files and errors carry predictions and non-secret metadata only -- never questions, references, memory text, credentials, or response headers. All tests are offline via mocked transports; run-qa fails fast before touching the dataset when the provider environment is missing. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * eval(memory): add blind QA grading report and paired statistics Add grade-qa: it recomputes the deterministic selector output, rejects any answer row whose kept facts, capacity, or policy disagree with it, grades every prediction through the policy-blind grade_answer(prediction, reference) call, and only then joins grades back through stable row IDs. Published artifacts are qa.rows.jsonl (graded rows with non-secret metadata), qa.summary.json (accuracy by source/scenario/policy; official and synthetic suites never folded together), and qa.stats.json (exact paired McNemar and seeded paired bootstrap difference for the official, synthetic, and overall suites using the pinned statistics parameters). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * eval(memory): pin the official DeepSeek model ID The historical protocol recorded the answer model with an aggregator-style namespace (deepseek/deepseek-v4-flash). The live run calls the same underlying model (DeepSeek-V4-Flash-0731, released before the historical run) directly through DeepSeek's official OpenAI-compatible API, whose canonical ID is deepseek-v4-flash. The served model is recorded from the provider response in every answer row. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * eval(memory): publish paired eviction QA results Publish the equal-budget live QA artifacts for pr4789-reproduction-v1: provenance, 90 graded rows, per-scenario summary, and paired statistics. At capacity 7 with identical settings, confidence answers 24/45 and hybrid-v1 40/45 (official 23/40 vs 35/40, exact McNemar p=0.0042; overall p=0.0004). The noisy-signal control is the one scenario where hybrid-v1 scored below the baseline (10/10 vs 8/10) and is reported separately. The offline suite now verifies the published statistics are recomputable from the published rows and that the artifacts carry no dataset text or credentials. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * docs(eval): decompose the noisy-signal QA cell Both policies retained the support fact in all ten noisy-signal cases, so the two rows hybrid-v1 lost are grader phrasing boundaries (verbose numeric answers rejected by the numeric-conflict rule), not eviction failures. Documented from the published rows; the grader stays frozen. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * eval(memory): address review hardening findings - ignore the responses/ directory the runner actually writes instead of the stale provider-responses/ entry - cover the official selection-rule recomputation with direct synthetic tests: matching manifests pass, rule-breaking IDs and missing eligible rows fail, and every published exclusion is load-bearing - align the report docstring and README with the statistics contract: the summary never folds sources; the explicitly labeled overall suite is reported alongside the separate official and synthetic suites - recompute the published bootstrap intervals (not only McNemar) in the published-results test - wire required_policy_version to the production EVICTION_POLICY_HYBRID_V1 constant so validate-contracts rejects policy drift Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * eval(memory): restore historical evidence rendering and harden resume identity Address both blocking findings from the #4789 artifact cross-check. The evidence renderer now emits the historical SESSION {id} AT {date} line instead of the divergent bracket format. The byte representation is protocol-critical: the witness record 35a27287 renders at 697 characters again, stays inside the 700-character distractor-bank bound, and 60d45044 leaves the bank, restoring row-level pool reproduction. Deterministic capacity-7 retention is unchanged at 27/45 vs 45/45. qa_run.json now binds a run directory to the SHA-256 of all five protocol inputs (config, both manifests, answer prompt, dataset) and names the changed artifact when it refuses to resume. Stored rows are reused only when row identity, policy, capacity, kept facts, and the request fingerprint recomputed from the current task all match; the disclosed probe (changed message under the same config) is now a regression test. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * eval(memory): republish QA results under the historical protocol Replace the published artifacts with the fresh equal-budget run executed at 497ff3d0 under the restored historical evidence rendering; the earlier run under the divergent rendering is discarded entirely. At capacity 7 with identical settings, confidence answers 24/45 and hybrid-v1 38/45 (official 23/40 vs 33/40, exact McNemar p=0.0129; overall p=0.0013). The confidence control is the one scenario below baseline for hybrid-v1 (8/10 vs 6/10); both lost rows retained the support fact and are grader phrasing/abstention boundaries, documented from the published rows. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * eval(memory): adopt the historical fact IDs and prompt serialization Pool facts now carry the historical protocol IDs (gold_{case} for the support fact, d_{case}_{index}_{source} for distractors in bank-draw order), and the rendered STORED MEMORY joins fact blocks with a blank line. Sorting by these IDs reproduces the historical selection tie-break: witness case 41698283 at capacity 7 again keeps the 58bf7951 distractor and evicts 001be529 under both policies. Deterministic capacity-7 retention is unchanged at 27/45 vs 45/45. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * eval(memory): republish QA results under the historical serialization Replace the published artifacts with the fresh equal-budget run executed at 01f99d61 under the historical fact IDs and prompt serialization; earlier runs under divergent serializations are discarded entirely. At capacity 7 with identical settings, confidence answers 24/45 and hybrid-v1 40/45 (official 23/40 vs 35/40, exact McNemar p=0.0018; overall p=0.0001). The single row below baseline (1cea1afa, confidence-control) retained its support fact; the model abstained. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * eval(memory): self-certify the publish path and pin offset coverage grade-qa now verifies (read-only) that the run marker's five protocol artifact hashes match the current inputs, rebuilds every answer task, and rejects any stored row whose request fingerprint does not match the task recomputed from the current protocol — the staleness class that previously required an out-of-band cross-check to detect. Verified end-to-end against the published run: all 90 rows pass and regrade to byte-identical artifacts, while a tampered fingerprint is refused by row ID. The distractor offset derivation and wraparound selection are now pinned by unit tests with hardcoded indices, including a wrapping offset, so a digest-slice or modulus regression can no longer stay green offline. Closes both non-blocking suggestions from the re-review. * fix(bench): bind persisted answer rows to their expected case identity Grading derived the reference case from the stored row's embedded case_id, so reassigning a valid row to another valid case passed every integrity check while silently changing the published grade. The resume path had the same gap: _row_matches_task() never compared case_id, source, or scenario. The recomputed task is now authoritative in both paths: grade_answer_rows() resolves the reference case from the expected PolicyResult and rejects any mismatch in the persisted row_id/case_id/source/scenario, and _row_matches_task() checks the same identity fields so a reassigned row is re-run instead of reused. Regressions tamper each field individually and exercise both paths. * docs(bench): document where to download the pinned LongMemEval file The README named the dataset but never said it lives on Hugging Face or how to fetch the pinned revision, so a reviewer could not run the offline commands. Add the direct download URL, the expected SHA-256, and the mirror and huggingface-cli alternatives; the CLI still never downloads anything. --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>	2026-08-29 14:36:38 +08:00
Nan Gao	73e3699347	feat(frontend): render markdown artifacts in the "open in new window" view (#5056) ... * feat(frontend): render markdown artifacts in the new window The artifacts panel's "open in new window" action handed the browser the raw Gateway response. For markdown that is a `text/markdown` body the browser can only show as source, so the new window was a text dump rather than a reader. Route markdown artifacts to a new `/artifacts/view` page that renders them with the same components the panel uses (SafeStreamdown + the artifact rehype chain + citation links/panel), including the truncated-preview banner and its "load full file" action. Everything else keeps the raw Gateway URL — notably HTML/SVG, which the Gateway deliberately serves as a download so active content never executes in the application origin. - `core/artifacts/viewer.ts` centralizes which stored artifacts are markdown (`.skill` archives included, since they hold a SKILL.md), so the panel and the viewer route cannot drift. - `ArtifactFilePreview` and its siblings move out of `artifact-file-detail.tsx` into `artifact-file-preview.tsx`; otherwise the standalone route would pull the CodeMirror editor into its bundle. - The window title comes from the route's `generateMetadata`, not `document.title`, which the App Router overwrites after hydration. - The viewer reads content through `useStandaloneArtifactContent`, which shares `useArtifactContent`'s query key but not its `useThread` dependency, since a detached window has no thread context. Claude-Session: https://claude.ai/code/session_013AiCrC5SBc3HdFYNxsp1EC * fix(frontend): keep the artifact target across re-authentication Review found the standalone viewer unrecoverable from an expired session. The window's target lives entirely in `?path=...&thread_id=...`, and both auth paths dropped it: - The layout guard redirected to `/login` with no `next` at all. A layout cannot read `searchParams`, so the guard moves into the page, which can — and rebuilds the full viewer address for `next`. The layout loses its AuthProvider along the way: nothing under this route reads `useAuth`, and the guard now makes a single `getServerSideUser` call per request. - The shared fetch wrapper built `next` from `window.location.pathname`, which silently truncated the query string. It now carries `search` too, so any route holding state in the query survives a 401, not just this one. `validateAuthNextPath` already accepts a query string. `buildArtifactViewerURL` is split out of `resolveArtifactOpenURL`: the guard needs the route itself, never the Gateway fallback that the latter takes for non-markdown targets. Tests: the login round trip (unit — the rebuilt URL survives `validateAuthNextPath` and parses back to the same target), the fetch wrapper preserving the query on 401 (unit), and the expired-session window reaching `/login` with the artifact intact (E2E). The E2E asserts on the popup's navigation *requests*, since `(auth)/layout` answers `/login` with a server redirect under DEER_FLOW_AUTH_DISABLED and no navigation commits. `tests/unit/core/models/api.test.ts` stubbed `window.location` without `search`; a real Location always has it. Claude-Session: https://claude.ai/code/session_013AiCrC5SBc3HdFYNxsp1EC * fix(frontend): keep public showcase artifacts out of the auth gate Review found that the viewer's access check regressed `/showcase`. Those pages render with `isMock`, their artifacts are served by the unauthenticated demo route, and the raw artifact URL this window replaced stayed public — so gating the window unconditionally bounced every logged-out showcase visitor to /login for a document that is already public. `requiresAuthenticatedViewer` exempts a mock target only when `resolveStaticDemoArtifact` would actually serve it. The allowlist is the authority rather than the flag: `mock=true` is caller-supplied, so a target the demo route answers with 404 — a non-allowlisted path, or a thread that is not a demo thread — still needs a session. Covered in `tests/e2e-auth/`, since the default E2E config disables auth and cannot see this: a public showcase artifact renders without a session, while a non-allowlisted path and a missing mock flag both land on /login. Verified the positive case goes red without the exemption. Claude-Session: https://claude.ai/code/session_013AiCrC5SBc3HdFYNxsp1EC	2026-08-29 11:07:16 +08:00
nonoge	0cb356858b	fix(frontend): truncate selected model names (#5050) ... * fix(frontend): truncate selected model names * test(frontend): scope model selector overflow guard	2026-08-29 08:03:29 +08:00
cui fliter	adfc307677	fix(channels): synchronize ChannelStore reads (#5083) ... Signed-off-by: cuishuang <imcusg@gmail.com>	2026-08-29 08:01:38 +08:00
Syt3s	6e5a41fd9a	feat(frontend): add conversation outline navigation for long chats (#5025) ... * feat(frontend): add conversation outline navigation for long chats * fix(frontend): escape bottom lock before outline navigation	2026-08-29 08:00:55 +08:00
Nan Gao	bf3e792a6a	feat(models): add GLM-5.3-Flash thinking workaround (#5074)	2026-08-28 22:24:10 +08:00
zhang	23d8e4b3a3	feat(scripts): support skipping frontend build on make start (#5053) ... * feat(scripts): support skipping frontend build on make start * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * fix(scripts): validate skip-frontend-build before stop_all and format test --------- Co-authored-by: PoetryLin <PoetryLin@users.noreply.github.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com> Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>	2026-08-28 10:44:30 +08:00
Jholly	2d0568a14f	fix(frontend): format structured upload error details (#5071) ... * fix(frontend): format structured upload error details * fix(frontend): preserve generic message error details	2026-08-28 10:40:29 +08:00
ChaseMoon	9c1dd11160	fix(mcp): preserve pooled stdio sessions after task timeouts (#5027)	2026-08-28 10:37:01 +08:00
Serply	4dbfe37ff3	feat(community): add Serply web search tool (#5023) ... Add deerflow.community.serply.tools:web_search_tool, a Google SERP provider for the web_search slot that also covers Google News and Google Scholar through an optional `vertical` config option. Reads the key from api_key in config.yaml or SERPLY_API_KEY, clamps max_results to Serply's 1-100 range, and returns the same structured JSON errors as the Serper and Brave tools. Register the provider in config.example.yaml, scripts/doctor.py, scripts/wizard/providers.py, .env.example, backend/docs/CONFIGURATION.md, the en/zh tools.mdx provider tabs, and tools/AGENTS.md. Tests mock httpx.	2026-08-28 10:30:30 +08:00
Terminator666666	e09b2d48df	fix(uploads): keep deduplicated filenames within the 255-byte limit (#5059) ... normalize_filename accepts names up to 255 UTF-8 bytes, but claim_unique_filename appended _N to the stem without re-checking the budget. A duplicate at maximum length therefore produced a 257-byte name, and the write path (open_upload_file_no_symlink -> normalize_filename) rejected it with ValueError. In the Gateway upload route that error falls into the generic handler: the whole request fails with a 500 and files already written in the same batch are rolled back — including unrelated ones. The same helper backs the Feishu and DingTalk channel downloads and client-side attachment staging. Truncate the stem on a UTF-8 code-point boundary when appending the dedupe tag would exceed 255 bytes, so the result always round-trips through normalize_filename. Names short enough to fit keep the exact dedupe shape they had before. Tests: red on main, green here — - unit: max-length dedupe stays within the limit and round-trips; repeated collisions stay unique; multibyte stems truncate on a code-point boundary; short names keep the historical _N shape - router: a batch with a max-length duplicate now succeeds and keeps every file instead of failing with a 500 Co-authored-by: Terminator666666 <Terminator666666@users.noreply.github.com>	2026-08-28 09:16:51 +08:00
georgelichen	24001e80b7	fix(skills): safely tokenize portable allowed-tools patterns (#4984) ... * fix(skills): accept portable frontmatter forms * fix(skills): normalize portable tool names * Safely preserve parenthesized portable skill tool patterns Portable Agent Skills declarations such as Bash(tvly *) contain spaces inside a command pattern. Keep those patterns as single literal entries while preserving exact names from the existing YAML-list form, so skill loading no longer fragments valid metadata or rewrites mixed-case MCP tools. Constraint: DeerFlow's current skill policy matches exact tool names and does not inspect Bash arguments Constraint: Agent Skills scalar syntax uses whitespace-separated entries with parenthesized command patterns Rejected: raw.split() | fragments Bash(tvly *) into unrelated tool names Rejected: normalize YAML-list entries | breaks case-sensitive MCP/runtime tool names Rejected: map Bash(...) to bash | broadens command-scoped declarations into unrestricted shell access Confidence: high Scope-risk: narrow Reversibility: clean Directive: Keep Bash(...) entries literal and inactive until DeerFlow has an explicit command-pattern authorization model Tested: 175 focused parser, validation, installer, review, loader, and tool-policy tests; Ruff check and format; compileall; git diff --check Not-tested: Full backend suite stopped at pre-existing Windows mode assertion test_runtime_config_store_file_is_owner_only Related: #4912 * Preserve exact custom tool names in portable skill parsing Portable scalar frontmatter needs alias normalization for known DeerFlow-compatible names, but generic case conversion corrupts MCP and custom tool identifiers. The tokenizer also treated quoted or escaped parentheses as structural delimiters, rejecting valid command patterns. Preserve unknown names and parse quoted or escaped patterns without broadening Bash(...) into bash. Constraint: Runtime skill policy uses exact tool-name matching Constraint: Parenthesized patterns remain literal because argument-level authorization is not implemented Rejected: Generic CamelCase-to-snake_case for every scalar | rewrites custom/MCP names Rejected: Map Bash(...) to bash | broadens command-scoped declarations into unrestricted shell access Confidence: high Scope-risk: narrow Reversibility: clean Directive: Add an explicit alias before supporting another portable tool name; keep command-pattern authorization separate Tested: 225 skills tests passed, 1 skipped; Ruff check; Ruff format --check; compileall; git diff --check Not-tested: Full backend suite remains affected by unrelated Windows permissions/path and missing Lark CLI tests Related: #4984; #4912 * Preserve case-sensitive exact tool authorities Case-folding a scalar declaration before alias lookup can turn literal write into write_file, substituting a different runtime authority. Keep exact portable spellings as aliases and preserve lowercase, custom, and MCP names; strengthen activation coverage for spaced Bash patterns and command fragments. Constraint: Runtime skill policy uses exact tool-name matching Constraint: Bash(...) remains literal and inactive because command-pattern authorization is not implemented Rejected: Case-insensitive alias lookup | maps lowercase runtime tools onto built-in authorities Rejected: Broaden the parser into command-pattern authorization | outside this PR's scope Confidence: high Scope-risk: narrow Reversibility: clean Directive: Add aliases only for documented portable spellings; preserve all other scalar names verbatim Tested: 226 skills tests passed, 1 skipped; Ruff check; Ruff format --check; compileall; git diff --check Not-tested: Full backend suite remains affected by unrelated Windows permissions/path and missing Lark CLI tests; GitNexus index refresh remains stale Related: #4984; #5016297602 * Support portable Glob and Grep skill aliases Portable Agent Skills commonly declare Glob and Grep, but DeerFlow exposes the runtime tools as glob and grep. Add explicit exact-spelling aliases and activation coverage so imported skills retain search-tool access without broad normalization. Constraint: Runtime skill policy uses exact tool-name matching Constraint: Alias conversion is limited to documented portable spellings Rejected: Case-fold all scalar names | can substitute custom or MCP authorities Rejected: Map arbitrary names by convention | breaks exact runtime compatibility Confidence: high Scope-risk: narrow Reversibility: clean Directive: Keep the alias table explicit and preserve unknown scalar names verbatim Tested: 228 skills tests passed, 1 skipped; Ruff check; Ruff format --check; compileall; git diff --check Not-tested: Full backend suite has unrelated environment failures on Windows; GitNexus index reports stale line mappings Related: #4984; #5026257899 --------- Co-authored-by: kriptoburak <kriptoburak@users.noreply.github.com>	2026-08-28 08:58:59 +08:00
早上肚子疼	0d97fdc770	docs(zh): sync missing security subsections into README_zh (#5029) ... The English Security Notice has four subsections; the Chinese one had two. Translate the two that were missing: - Gateway Admin Is Equivalent to Code Execution - Deployment Defaults Both describe deployment-time security behavior, so a stale translation leaves Chinese-speaking operators without the loopback-default and first-run-setup guidance that English readers get. Verified against the code rather than translated blind: - stdio MCP allowlist defaults to {npx, uvx} and is extended via DEER_FLOW_MCP_STDIO_COMMAND_ALLOWLIST (backend/app/gateway/routers/mcp.py) - entry port publishes as ${BIND_HOST:-127.0.0.1}:${PORT:-2026} (docker/docker-compose.yaml) - /setup exists as the first-run admin creation route (frontend/src/app/(auth)/setup/page.tsx) Co-authored-by: zaoshangduziteng <309590849+zaoshangduziteng@users.noreply.github.com>	2026-08-27 22:56:57 +08:00