mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-09-11 22:48:38 +00:00
110 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Jun
|
3a6e681dee
|
fix(view-image): read active sandbox images from sandbox (#5306)
* fix(view-image): read remote sandbox images from sandbox * docs(tools): clarify view_image sandbox behavior * fix(view-image): address sandbox lifecycle review * fix(view-image): preserve image provenance across sandbox replacement * fix(view-image): address provider recovery review * fix(view-image): drain cancelled tool reads |
||
|
Wenchao An
|
0b3dadbc9b
|
feat(subagents): add acceptance checks to durable batch items (#5289)
* feat(subagents): check and persist durable batch acceptance Carry optional per-item criteria into native subagents, reuse the deterministic checker, and expose separate verdicts through item queries and exports. Preserve execution and retry semantics, renew leases during checks, and migrate existing batch rows with nullable acceptance fields. * fix(subagents): align batch acceptance normalization and sandbox admission * test(auth): include project permissions in the full-stack contract |
||
|
Wenchao An
|
ca23703ef0
|
fix(subagents): preserve actionable acceptance gaps after compaction (#5287)
* fix: preserve actionable subagent acceptance gaps Distinguish completed execution from acceptance in delegation guidance. Retain bounded unmet and unverified criteria after compaction and guide the lead to address remaining work within its budget. * docs: keep acceptance guidance within instruction budget |
||
|
Yusuf Gürdoğan
|
23bd76046a
|
feat(community): add Sofya web search provider (#5239)
* feat(community): add Sofya web search provider Add a community provider backed by Sofya (https://sofya.co). Its search endpoint returns the content of the result pages, not only their snippets, and its fetch endpoint returns a page as markdown. Both are plain JSON over HTTP, so this needs no extra Python package (uses httpx, already a dependency). Changes: - backend/packages/harness/deerflow/community/sofya/__init__.py - backend/packages/harness/deerflow/community/sofya/tools.py Implements web_search_tool and web_fetch_tool using httpx. API key is read from the config.yaml `api_key` field or the SOFYA_API_KEY env var. Follows the same interface and output shape as the existing ddg_search and serper providers, including the max_results parameter with config override and the structured "No results found" error. - backend/tests/test_sofya_tools.py Unit tests covering API key resolution, config overrides, result mapping, time range, HTTP errors, empty results, and fetch failures. - config.example.yaml: add commented-out Sofya web_search and web_fetch examples alongside the other providers - .env.example: add SOFYA_API_KEY placeholder - backend/docs/CONFIGURATION.md: list Sofya under web_search, web_fetch and the environment variables * fix(sofya): honor caller max_results, validate search_depth, join time_range contract test - Caller-supplied max_results now wins; config is used only when the argument is omitted, matching GroundRoute. - search_depth is clamped to basic/snippets; an unsupported value logs a warning and falls back to basic. - Sofya added to the shared time_range schema contract test. * fix(sofya): cap per-result content so a search stays inline An unbounded search payload (up to 20 read pages) crossed the tool output budget middleware's externalize_min_chars threshold, which replaces the result list with a file reference. Cap each result's content at contents_max_characters (default 2000, 0 disables), matching Exa's config key. Five capped results stay under the 12000 char threshold. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016TZhyPNCX2GYyBPkvTgJV5 * fix(sofya): list Sofya in the recency contract, coerce non-string content _clip subscripted its input, so a non-string content or description from the API raised TypeError instead of degrading. Coerce to text first, the way _sofya_post and _response_results guard the shapes around it. Also add Sofya to the Web Search Recency section in backend/AGENTS.md. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016TZhyPNCX2GYyBPkvTgJV5 * fix(sofya): coerce web_fetch content, list sofya in the tools guide, add changelog web_fetch sliced its content the same way web_search did before the last push: a truthy non-string from the API passed the falsiness guard and then raised TypeError. Reuse _clip, keeping the `or ""` so empty content still reports "No content found". Also add sofya to the community provider inventory in packages/harness/deerflow/tools/AGENTS.md and an [Unreleased] changelog entry. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016TZhyPNCX2GYyBPkvTgJV5 * docs(zh): add the missing InfoQuest and Firecrawl web_fetch tabs The ZH web_fetch tab list named five providers where EN names seven. Both tabs mirror their EN counterparts, so the two locales list the same web_fetch providers again. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016TZhyPNCX2GYyBPkvTgJV5 --------- Co-authored-by: Claude Opus 5 <noreply@anthropic.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com> |
||
|
PeaceMaker-best
|
3c36217a51
|
feat(observability): persist deferred tool promotions (#5183)
* feat(observability): persist deferred tool promotions Signed-off-by: PeaceMaker-best <221849497+PeaceMaker-best@users.noreply.github.com> * fix(ci): trim agent guidance chain Signed-off-by: PeaceMaker-best <221849497+PeaceMaker-best@users.noreply.github.com> --------- Signed-off-by: PeaceMaker-best <221849497+PeaceMaker-best@users.noreply.github.com> Co-authored-by: PeaceMaker-best <221849497+PeaceMaker-best@users.noreply.github.com> |
||
|
哈基米
|
dbe11dc798
|
fix(mcp): keep ToolRuntime injection for sync-wrapped MCP tools (#5164)
* fix(mcp): keep ToolRuntime injection for sync-wrapped MCP tools make_sync_tool_wrapper attached an annotation-less wrapper to tool.func, which made LangGraph's ToolNode stop detecting the coroutine's "runtime" parameter (_get_all_injected_args falls back to func first and its type hints are empty). Every MCP tool in a sync agent caller then ran with runtime=None: resolve_runtime_user_id fell through to the default user, and the background-submit wrapper lost run_id/tool_call_id on the TaskSubmitRequest, so completion notifications launched under the default lead agent instead of the thread's agent. Wrap the generator and both sync_wrapper variants with functools.wraps so get_type_hints still sees the original annotations. Adds a regression test that drives a func-patched pooled MCP tool through a real ToolNode and asserts the ToolRuntime is injected with the thread's user context. It fails on main (runtime=None) and passes with the fix. * docs(mcp): record sync-wrapper annotation contract; extend regression coverage Address review feedback on #5164: - Expand the Notes block in make_sync_tool_wrapper to state the functools.wraps contract (copies __name__/__qualname__/__doc__/__annotations__/__dict__ and sets __wrapped__) and why that is what keeps get_type_hints resolving string annotations from callers like mcp/tools.py and skill_manage_tool.py. Drop the no-op wraps on the inner run_coroutine so the wrap surface stays minimal. - Rename the regression test to test_func_patched_mcp_tool_keeps_toolnode_runtime_injection. - Add test_sync_wrapped_builtin_tools_still_resolve_runtime to pin that the built-in tools (which carry runtime as a pydantic schema field) keep resolving runtime after their func is wrapped by make_sync_tool_wrapper, so a future wrapper refactor cannot silently regress per-user resolution for them. |
||
|
PeaceMaker-best
|
fb28ed0122
|
feat(subagents): enable historical upload discovery (#5170)
Signed-off-by: PeaceMaker-best <221849497+PeaceMaker-best@users.noreply.github.com> Co-authored-by: PeaceMaker-best <221849497+PeaceMaker-best@users.noreply.github.com> |
||
|
AoHanBei
|
9b32b5d841
|
feat(observability): persist loop detection events (#5127)
* feat(observability): persist loop detection events * fix(observability): persist subagent loop events * fix(observability): narrow subagent loop event bridge * fix(observability): attribute subagent loop events * fix(tests): isolate subagent executor imports |
||
|
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> |
||
|
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) |
||
|
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 |
||
|
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. |
||
|
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. |
||
|
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. |
||
|
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. |
||
|
yong
|
846c716523
|
feat(search): add Tencent Cloud WSA provider (#5057)
* feat(search): add Tencent Cloud WSA provider * docs: restore README to upstream * docs: remove README changes from WSA provider PR * fix(doctor): validate Tencent WSA API key |
||
|
Aari
|
ff0a6768c2
|
feat(subagents): add unified capacity and durable batch execution (#4998)
* feat(subagents): add capacity controls and durable batches * fix(helm): sync subagent config schema version * fix(subagents): preserve batch history without worker * fix(subagents): support explicit factory runtimes * fix: address durable batch review findings |
||
|
ChaseMoon
|
cff8b74ec3
|
fix(harness): offload ACP workspace creation from event loop (#4965)
* fix(harness): offload ACP workspace creation from event loop * fix(harness): complete ACP event-loop offload |
||
|
Aari
|
1aa813ddb3
|
feat: add managed subagents and delegation scopes (#4887)
* feat: manage and scope subagents * fix: address subagent review feedback * fix: address managed subagent review feedback * fix: harden subagent settings semantics * fix: harden managed subagent cache invalidation * fix: reuse assembled lead agent inputs * fix: migrate managed subagent definitions --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com> |
||
|
simon
|
ea9b70148e
|
fix(clarification): drop sibling tool calls before interrupt (#4908)
* fix(clarification): drop sibling tool calls before interrupt - Rewrite the AIMessage in ClarificationMiddleware.after_model so a parallel bash/write_file cannot run before the user answers - langchain return_direct only inspects the last ToolMessage; siblings both execute and can keep the agent loop alive - Skip the rewrite when disable_clarification is set - Prompt and tool docs: do not call other tools in the same turn Fixes #4906 Co-authored-by: Cursor <cursoragent@cursor.com> * fix(clarification): enhance sibling tool call handling in ClarificationMiddleware - Update ClarificationMiddleware to ensure sibling tool calls are dropped when `ask_clarification` is invoked, preventing unintended execution before user input. - Modify documentation to clarify that the `return_direct` router now inspects all client-side tool calls of the last AIMessage, ensuring proper routing behavior. - Introduce a new integration test to validate that sibling tools do not execute when `ask_clarification` is present in the same turn. This change addresses potential issues with tool execution order and improves the overall reliability of the middleware. Fixes #4906 * fix(clarification): enhance tool call filtering in ClarificationMiddleware - Update _filter_content_tool_use to handle Gemini-style function_call blocks by matching on name when no id is present, ensuring proper filtering of tool calls. - Modify ClarificationMiddleware to maintain sibling tool call integrity by dropping unnecessary blocks, improving the clarity of the AIMessage content. - Add a new test to validate the correct stripping of idless function call content blocks, ensuring that sibling tool calls do not execute prematurely. This change improves the robustness of the middleware and addresses potential execution order issues. Fixes #4906 * fix(clarification): drop siblings when ask_clarification is malformed LangChain parks invalid args on invalid_tool_calls independently, so a valid sibling would otherwise still execute before the user answers. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com> |
||
|
Nan Gao
|
13f0a7f263
|
feat(extensions): let an out-of-tree extension observe what the agent did (#4863)
* feat(extensions): let an out-of-tree extension observe what the agent did
DeerFlow's extension system can contribute middleware, services and routes,
but an extension cannot answer basic questions about a run without reaching
into host internals. Several of the facts it would need are destroyed by the
operations that produce them:
* The middleware chain injects and rewrites a lot of context — date
reminders, recalled memory, compaction summaries, durable-context data,
image payloads, activated skill bodies. Downstream, none of it is
attributable: at the model-call boundary an injected HumanMessage is
indistinguishable from the user's own, and anything wanting to tell them
apart has to pattern-match prompt wording, which breaks on the next copy
edit.
* Two runs of "the same agent" are only comparable if the chain enforced the
same limits, prompts and thresholds. Recovering that from outside means
reading private attributes and guessing which of them change behaviour — a
guess that rots silently as middlewares gain fields.
* The lead-agent factory resolves a model after runtime overrides, renders a
prompt, filters tools through authorization and composes a stack, all
inside one synchronous call, and none of it survives: a middleware sees its
neighbours but not the prompt, the run worker sees a graph but not what
went into it.
* Summarization is destructive by design. N messages leave the context and
one summary enters it; afterwards only the summary exists, so "which
messages became this?" is not reconstructible.
This adds seven neutral facilities so those facts are recorded where they are
still true, and releases the contract package as 0.2.0.
Message provenance
Producers stamp `deerflow_content_kind` / `deerflow_producer_kind` onto the
messages they inject or rewrite. Stamping is unconditional — a fact whose
presence depends on whether an observer is installed is not a fact — and the
keys are server-owned, so provenance cannot be forged from a request.
Middleware self-description
Twelve middlewares declare their own behaviour-affecting parameters through
a duck-typed `release_policy_parameters()`. Long text is hashed rather than
embedded: a declaration is an identity, not a copy of the prompt.
Agent assembly descriptor
`assemble_lead_agent()` returns the graph plus a descriptor whose fingerprint
answers "did anything about this agent change between these two runs?".
`make_lead_agent()` keeps its graph-only signature — it is the LangGraph
Server ABI declared in langgraph.json. Tools and skills are sorted before
hashing because their assembly order is incidental; middlewares are not,
because stack order decides what wraps what. Host build identity is reported
but excluded from the fingerprint, so a redeploy does not invalidate every
agent's identity.
Context compaction observation
Summarization emits the content hashes of the messages it is about to remove
joined to the summary that replaced them. Content is the only identity
available at that seam: the summary does not become a message, and what later
projects it into a request renders it bounded and escaped rather than
verbatim.
Neutral policy, transform and MCP-source facts
Guardrail decisions are published to runtime context under a `__`-prefixed
key; result-rewriting middlewares append a declared, ordered transform trail;
MCP tools carry their credential-free logical origin.
Extension route identity
Contributed routes are session-authenticated and cannot opt out, but
"logged in" and "administrator" are different questions. Extensions get a
neutral projection of the caller rather than the host's auth context, and
`require_admin` fails closed when identity cannot be determined.
Extension-owned tables
An extension that persists data owns its own MetaData and migration chain, so
its tables are absent from Base.metadata and `alembic revision --autogenerate`
proposes dropping them. Extensions declare a table prefix, which is rejected
at registration if it would shadow a host table.
The contract package stays dependency-free and imports no host code; every new
Protocol method has a default so later additions remain additive. The loader's
pre-1.0 rule requires an exact major.minor match, so extensions written against
0.1 are now refused at startup with an actionable install hint rather than
loading into a host that implements a different surface.
uv.lock records the contract package's new version, so `uv sync --locked` still
resolves on a fresh checkout.
* fix(backend): sort gateway service imports
|
||
|
Nefelibata
|
f1f4af99bb
|
fix(tools): retain strong reference to deferred subagent cleanup tasks (#4928)
* fix(tools): retain strong reference to deferred subagent cleanup tasks * chore(tests): organize imports and format test_task_tool_core_logic.py |
||
|
Aari
|
5ffc2d3e27
|
feat(mcp): complete durable task notifications and chat UI (#4833)
* feat(mcp): add reliable task notifications and cancellation * feat(mcp): add background task chat UI * fix(mcp): hide and sanitize task notification prompts * fix(mcp): sanitize projected task names * fix(mcp): harden task notifications and details * fix(mcp): harden task lifecycle recovery * fix(mcp): gate task UI and isolate cancellations * test: scope plain-text response locator * fix(mcp): align task notification boundaries * fix(mcp): bound task delivery retries * fix background task notification races |
||
|
DanielWalnut
|
062ba9ddfc
|
feat: integrate MiniMax Code as a native ACP agent (#4846)
* feat: integrate MiniMax Code as an ACP agent * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@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> |
||
|
Ryker_Feng
|
ccff5f5ce7
|
docs: govern agent guidance size (#4799)
* docs: govern agent guidance size * refactor: split agent guidance by code scope * Clarify virtual path handling in AGENTS.md Updated the translation section to clarify the role of `LocalSandboxProvider` and the handling of virtual paths in the tool layer. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com> |
||
|
ChiHaYa
|
88252e9b31
|
fix(subagents): isolate background tasks from reused tool call IDs (#4758)
* fix(subagents): isolate background execution IDs * fix(subagents): preserve correlation scope and isolate usage * fix(subagents): make usage attribution idempotent |
||
|
Xinmin Zeng
|
74692fec12
|
fix(tools): resolve presented files with runtime user (#4677) | ||
|
Nan Gao
|
1f792d0f4b
|
feat(extensions): add middleware plugin foundation (#4636)
* feat(extensions): add middleware plugin foundation * fix(extensions): stop config resolution from masking extension loading `create_app()` resolved the configured plugin list inside the fail-open guard around `load_extensions()`. CI has no `config.yaml` (gitignored and never generated by the workflow), so `get_app_config()` raised `FileNotFoundError` there and was swallowed as an extension failure -- `load_extensions()` never ran at all, and the four `create_app()` tests in `test_extension_app_loading.py` passed locally but failed on every runner. Resolve the plugin list before the guard. Only an absent `config.yaml` is tolerated, mirroring `_resolve_trace_enabled_for_app_construction()`: `create_app()` runs at import time, and lifespan still performs strict config loading before serving. A `config.yaml` that exists but fails to parse or validate now propagates instead of being reported as an extension failure -- reporting it as the latter silently dropped a `required: true` extension rather than failing the boot. Make the tests config-independent with an autouse `stub_app_config` fixture, following the existing pattern in `test_gateway_lifespan_shutdown.py`, and cover both new branches of the config-resolution boundary. * fix(extensions): bind the run's extension snapshot through subagent delegation The lead-agent path resolves one immutable loaded-extension snapshot per run and binds it through task-store allocation and graph construction, but the subagent path re-read the process-wide singleton at execution time. In production both are the same object, yet a `set_loaded_extensions()` between the lead run's start and a subagent's execution (test teardown, a future hot-reload path) would let one run mix two extension generations — exactly what the documented invariant exists to prevent. The graph-build binding is a ContextVar scoped to synchronous construction, so it has already exited by the time a tool delegates; the snapshot has to travel through runtime context instead. The run worker publishes it under the host-internal `EXTENSION_SNAPSHOT_CONTEXT_KEY` (written after the caller merge, popped when the run has none, so a caller-supplied value is never authoritative), `task_tool` reads it back through the type-checking `resolve_run_extensions()`, and `SubagentExecutor` binds it at construction. Callers outside the Gateway run path — embedded `DeerFlowClient`, standalone LangGraph Server — install no snapshot and keep the existing `get_loaded_extensions()` fallback. * refactor(extensions): defer the ordering table by call, not by a lying tuple `CORE_ORDERING_CONSTRAINTS` was a `tuple` subclass that overrode only `__iter__` and resolved into a class-level `_resolved` side channel. A tuple cannot populate its own storage after construction, so the instance stayed the empty tuple it was built as: `len()` was 0, `bool()` was False, `in` was always False, indexing raised, slicing and `reversed()` came back empty, and it compared unequal to the plain tuples tests substitute for it — all while iteration yielded the real constraints. Only `assert_ordering` consumed it, and only by iterating, so the split went unnoticed. The sibling `_AnchorTable(dict)` uses the same idea soundly because dict is mutable: `self.update()` fills the real storage, making every inherited operation correct. That trick does not survive the port to an immutable type. Replace it with `core_ordering_constraints()`, matching how `stack.py` defers the same kind of table via `_anchors()`. The deferral is kept — it is about dependency direction, not just cycles: `extensions/` is the layer the middleware layer calls into, so a module-scope `agents.middlewares` import here points the dependency backwards and closes a cycle as soon as any middleware imports something under `extensions/` at module level. Resolution stays at `assert_ordering` time, which already runs inside the middleware builder. Tests pin both halves: the returned value is a plain tuple whose len/bool/ membership/indexing/reversal/equality agree with iteration, and a subprocess probe asserts importing `extensions.ordering` does not load the middleware layer while calling the function does. |
||
|
Xinmin Zeng
|
f2e832330e
|
fix(sandbox): enforce disabled skills in filesystem views (#4178)
* fix(sandbox): project enabled skills into sandbox views * fix(skills): keep projection mutations consistent * fix(skills): fail closed on projection errors * fix(skills): isolate per-scope failures during boot projection rebuild rebuild_all_skill_projections() propagated any exception from the public rebuild or from a single user's rebuild straight out of the gateway lifespan startup, uncaught. A single broken user directory (bad permissions, corrupted _skill_states.json, unreadable content) would therefore abort gateway boot for every user, not just that one - _rebuild_*_locked already fails closed internally (clears the view and re-raises), so the boot loop only needed to stop treating that re-raise as fatal. Each scope's rebuild now fails closed independently and boot continues; a scope left empty by a boot failure self-heals on the next sandbox acquire via ensure_skill_projections(). Also patches deerflow.skills.projection.rebuild_all_skill_projections in the memory-flush lifespan test fixture, matching the two sibling fixtures in the same file — this call is now on the lifespan startup path and the fixture's minimal SimpleNamespace config predates it. * test(skills): update authz test for the projection-aware public toggle _persist_shared_skill_state (introduced earlier in this branch) reads the shared extensions_config.json fresh from disk under the projection lock instead of through the cached get_extensions_config() singleton - that's the whole point of the fix (stale worker caches must not clobber another worker's concurrent update). The name no longer exists on the skills router module, so the test's monkeypatch of it started raising AttributeError instead of exercising the endpoint. The mock storage in this test isn't a real LocalSkillStorage instance, so _persist_shared_skill_state's projection-mutation branch is already skipped (nullcontext) and it falls back to a fresh ExtensionsConfig() for the nonexistent tmp config_path - no replacement monkeypatch needed. * fix(sandbox): make skill projection ensure best-effort in acquire acquire() called _ensure_skills_projection() directly, outside any try/except, in both LocalSandboxProvider and AioSandboxProvider. Every other skill-mount setup path in these providers has always caught exceptions and logged a warning rather than failing sandbox acquire outright (e.g. when config.yaml can't be resolved) - these two new call sites broke that contract, so any projection failure (including simply not having a config.yaml, as in CI's test environment) now failed acquire() itself instead of just leaving skill mounts off. _ensure_skills_projection now catches its own exceptions and returns None; both providers' callers already tolerate that (a None projection skips the skill-specific mounts, matching the existing degrade path) after making _append_public_skill_mapping and the custom/legacy mount block in LocalSandboxProvider explicitly None-safe. Caught by running the full suite with config.yaml removed, matching CI's environment - not caught locally because a real config.yaml was present, masking the failure. * fix(sandbox): make E2B skill projection mounts best-effort _skill_projection_mounts called ensure_skill_projections with no guard, unlike Local/AIO's _ensure_skills_projection. A raise propagated out of _apply_mounts before the configured-mounts loop ran, so a skills projection failure dropped the operator's own configured mounts too - only caught by create()'s outer warning, with nothing applied at all. Swallow here and return an empty mount list on failure, matching the Local/AIO pattern: still fail-closed for skills, but no longer widens the blast radius to unrelated configured mounts. Review feedback from PR #4178. * docs(skills): document projection trade-offs flagged in review - _update_tree_digest: note the metadata-only (not content) hashing trade-off and why runtime writes through this codebase are still covered regardless (rebuild-under-lock + rename always changes inode). - LocalSandboxProvider.acquire: note the acquire-time self-heal cost (cheap on a fresh manifest, ~400ms rebuild under lock on stale/drift). - skill_projection_mutation: drop the no-op except-Exception-then-raise; a raise from the mutation already propagates past the yield with the view left cleared, no explicit re-raise needed. - provisioner README: spell out that hostPath skills volumes require the gateway and K8s node to share DEER_FLOW_HOST_BASE_DIR (single-node or shared storage), and that the custom/legacy volumes' hostPath type Directory (not DirectoryOrCreate) makes a violation of that assumption a visible Pod-creation failure instead of a silent empty mount. Review feedback from PR #4178. * fix(skills): lazily repair user projections * fix(skills): close projection review gaps * fix(skills): refresh user projection enable state * fix(skills): close projection review follow-ups * fix(skills): preserve state across projection writes --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com> |
||
|
Eilen Shin
|
9d915ca8ca
|
fix(agent): route subagents by net benefit (#4384)
* fix(agent): route subagents by net benefit * fix(agent): refine subagent routing boundaries * fix(agent): clarify routing limits and batches * fix(agent): handle single-subagent routing |
||
|
阿泽
|
1baa8ad696
|
feat(clarification): structured form fields for human-input cards (#4400 Phase 1) (#4406)
* feat(clarification): structured form fields for human-input cards Add a request-side v2 `form` mode to the ask_clarification protocol so business flows (e.g. expense reimbursement) can collect several values in one card instead of sequential free-text questions: - `ask_clarification` gains a restricted `fields` parameter (text / textarea / number / select / multi_select / checkbox / date) - ClarificationMiddleware validates and normalizes fields explicitly (whitelisted types, unknown -> text, select-likes without options -> text, duplicate/invalid entries dropped, all-invalid falls back to the legacy modes) since the middleware short-circuits before tool execution; the plain-text fallback lists fields for IM channels - Form payloads carry `version: 2` so older frontends degrade to the text fallback; replies stay on the v1 response protocol — the card submits a readable summary as `response_kind: "text"`, so journal persistence and answered-card recovery are unchanged - Frontend renders typed field controls with required-field validation and compact multi-select chips Part of #4400 (scope narrowed per maintainer feedback: request-side only, no new response kinds, no top-level multi_choice). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(clarification): harden form protocol per review feedback Address the five review points on #4406: - Reject field names colliding with JS Object.prototype members on both sides; frontend reads form values via own-property access only, so `constructor`/`toString`-style names can no longer leak inherited members into required validation or the submitted summary - Close open requests answered through the legacy text fallback: a visible plain human reply (no response metadata) now marks every previously-opened request as answered, so upgrading to a v2-aware frontend cannot leave the composer locked on an already-answered card - Give checkbox fields deterministic boolean semantics: values are seeded to an explicit false ("no" in the summary) and `required` means must-agree/consent; documented in the tool schema - Make middleware field validation atomic: structurally broken entries (bad/duplicate/reserved names, over-cap field/option counts or text lengths) degrade the whole form instead of silently dropping fields; options are trimmed/deduped with blanks removed so the backend never emits payloads the frontend parser rejects - Associate form labels/controls (htmlFor/id), aria-required, aria-invalid, and error descriptions for accessibility Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * refactor(clarification): type the fields item schema via TypedDict Replace `fields: list[dict[str, Any]]` with `list[ClarificationFormField]` (a TypedDict with `name` required and the type whitelist as a Literal) so the provider-facing tool schema documents the item shape instead of an opaque object relying on the docstring. Runtime validation is unchanged and stays in ClarificationMiddleware, which intercepts the call before tool execution. Addresses the non-blocking review suggestion on #4406. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(frontend): drop unsupported aria-invalid from multi-select group jsx-a11y: role=group does not support aria-invalid; the error linkage stays via aria-describedby. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(clarification): coerce numeric required flags and normalize fields once - `_normalize_bool` now coerces 1/0 (some providers serialize booleans as integers), so `required: 1` no longer silently flips to optional - `_handle_clarification` normalizes `fields` once and passes the result to both the text fallback and the payload builder Addresses the non-blocking review nits on #4406. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(clarification): harden form protocol per contract review round 2 Backend: - Guard unhashable JSON in the intercept path: `type: []`/`{}` degrades the field to text and `clarification_type: []` coerces to str instead of raising TypeError (which, with return_direct, ended the turn with an error and no card or fallback) - Add a total budget over the serialized normalized fields (16KB UTF-8 bytes): per-item caps alone admitted forms whose IM text fallback exceeded channel delivery limits (Slack 40k chars, Feishu ~30KB card), silently truncating trailing fields; a boundary test proves any accepted form's fallback stays deliverable Frontend: - Submission value now appends a JSON block keyed by stable field names (readable summary alone is delimiter-ambiguous), with a collision regression test - Parser boundary tightened to match backend constraints: empty option values (Radix SelectItem crash), duplicate option ids/values, duplicate field names, and the form<->version-2 binding are rejected - Keep the error node mounted while any field is still invalid so aria-describedby never points at a removed element (happy-dom interaction test) - Required semantics are now accessible: native checkbox control (no HTML required attribute — it would intercept the custom submit path), visually-hidden localized "required" markers next to the aria-hidden asterisks - Legacy-fallback closure narrowed to the latest unanswered request: nothing guarantees a single outstanding clarification across runs, and closing all would silently swallow older decisions; an older request left open becomes the active card again Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * fix(frontend): keep clarification selects controlled --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com> |
||
|
Ryker_Feng
|
cd9432bcc1
|
feat(tools): support GIF images in view_image (#4438)
Add GIF to the view_image allowlist: map the .gif extension to image/gif and detect the GIF87a/GIF89a magic bytes so the existing extension/content cross-check accepts GIFs instead of rejecting them as an unsupported format. Covered by a new success test. |
||
|
Huixin615
|
4a2ecd430e
|
fix(streaming): expose custom events to astream_events (#4403)
* fix(streaming): expose custom events to astream_events * test(streaming): validate real custom event emitters --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com> |
||
|
Aari
|
7b330101d2
|
fix(tools): exclude injected runtime from list_uploaded_files schema (#4375) (#4376)
Declaring the injected runtime arg as `Annotated[Runtime, InjectedToolArg] | None` made the top-level annotation a Union, so LangChain no longer treated it as injected. It leaked into the model-facing schema and pydantic raised PydanticInvalidForJsonSchema on the ToolRuntime dataclass the moment the tool was bound to a model. The tool is bound by default for the lead agent, so any default run on an OpenAI-compatible provider failed at tool-bind time. Declare runtime as a bare Runtime first param, matching every other built-in tool (present_files, view_image, task, ...), which LangChain auto-injects and auto-excludes from the schema. Add a schema regression test that binds the tool. |
||
|
Aari
|
0d4d0cb17d
|
feat(agents): database-backed storage for custom agent definitions (#4359)
* feat(agents): database-backed storage for custom agent definitions Add an agent_storage.backend switch (default file, behaviour-unchanged) with a db backend that stores each custom agent as a row in the shared SQL persistence layer, so a multi-instance deployment sees the same agents on every node (#4331, #4357). Introduces an AgentStore interface routing all read/write surfaces, an agents table + migration 0006, startup validation, and a file->db importer. Follows the thread_meta store / run_events backend-switch / 0003_scheduled_tasks migration patterns; no new dependency. * fix(agents): make db storage path production-ready (review round 1) Addresses review feedback on the db/sync agent-storage path: - sql.py: mirror the async engine's per-connection SQLite PRAGMAs on the sync engine (busy_timeout=30000, synchronous=NORMAL, foreign_keys=ON, WAL) so both engines behave identically against the shared DB; guard the engine cache with a lock (double-checked) so concurrent first-touch cannot build duplicate engines or register the connect listener twice. - routers/agents.py + routers/assistants_compat.py: offload the sync-store reads that ran on the event loop (list/get/check, update's pre-read + legacy guard + refresh, and assistants_compat's four list routes) via asyncio.to_thread — on db+postgres each was a network round trip stalling the loop. Writes were already offloaded. - file.py: translate the create() mkdir(exist_ok=False) race FileExistsError into AgentExistsError (router 409, matching SqlAgentStore's IntegrityError path); correct the _write docstring — per-file atomic replace, two commits sequential not transactional. Tests: sync-engine PRAGMA + engine-cache reuse assertions; file create-race -> AgentExistsError; strict Blockbuster anchor over the read endpoints so a regression back onto the loop fails CI. * fix(agents): address round-2 review on the db store path - update_agent tool: align the docstring/inline comment with FileAgentStore._write. Cross-field write atomicity is db-only; the file backend commits config then soul via two sequential os.replace (a crash between them can leave a fresh config.yaml beside a stale SOUL.md). The dropped partial-write *reporting* is an intentional tradeoff — the stage-then-replace safety is preserved (test_update_agent_soul_failure_does_not_replace_config still holds). - SqlAgentStore.update(): true upsert. Catch IntegrityError on the insert-on-missing branch, re-fetch and apply, so two concurrent first-time writes (e.g. two setup_agent handshakes) converge instead of surfacing a raw UNIQUE(user_id, name) violation as a 500. Symmetric with create(). - get_agent_store(): document the graph-subprocess config-resolution invariant (the except->file fallback is a genuine no-config path, not a mask for a misconfigured graph process) and pin it with two tests driving the real get_app_config() file resolution: db resolves from an on-disk config.yaml, file fallback when config is unresolvable. * test(agents): cover SqlAgentStore.update() write-race upsert recovery Mandatory-TDD test for the round-2 fix in 0680340a: two concurrent first-time update()s where the loser's insert hits UNIQUE(user_id, name). Deterministically forces the IntegrityError recovery path by making the first _row probe miss the committed winner, and asserts last-writer-wins instead of a surfaced 500. |
||
|
Daoyuan Li
|
09d9cf53d2
|
fix(harness): add timeout to invoke_acp_agent to prevent indefinite hangs (#4238)
invoke_acp_agent had no timeout anywhere in its call path, and ACPAgentConfig had no timeout field. If the ACP agent subprocess answers initialize/new_session correctly but then hangs inside prompt(), the tool call - and therefore the whole agent turn - blocks indefinitely, with the child process left running. MCP stdio servers already guard against this class of hang via tool_call_timeout; ACP agent invocations had no equivalent. Add ACPAgentConfig.timeout_seconds (default 1800, ge=1), mirroring the shape/default of subagents.timeout_seconds, and wrap the conn.prompt() call in asyncio.wait_for(). On TimeoutError, return a clear error instead of hanging; exiting the spawn_agent_process context block triggers the ACP library's own graceful-then-forceful subprocess cleanup, so the hung process is actually terminated. |
||
|
Lee minjing
|
e225ad57d7
|
feat(uploads): lazy-load historical files via list_uploaded_files tool (#4174)
* feat(uploads): lazy-load historical files via list_uploaded_files tool
Replace per-turn injection of all historical upload metadata with on-demand
discovery via a new `list_uploaded_files` built-in tool, following the same
deferred-discovery pattern used by skills.
- Rename <uploaded_files> block to <current_uploads> (current-run files only)
- Add list_uploaded_files tool with include_outline: bool|list[str]
- Extract outline helpers to shared deerflow/utils/file_outline.py
- Update system prompt to reflect lazy-loading behaviour
- Historical file scan removed from UploadsMiddleware.before_agent()
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(uploads): clear uploaded_files state when no new files in current turn
When before_agent() returns None on empty turns, the LastValue
uploaded_files field retains the previous turn's filenames.
list_uploaded_files then incorrectly excludes those files as
"current-run" files, making them invisible until the next upload.
Fix: return {"uploaded_files": []} instead of None to explicitly
clear state. Add two-turn regression test covering the exact
scenario from review feedback.
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: resolve CI lint errors and stale test assertion from merge
- Split long prompt line to fit 240-char limit
- Add missing `Any` import in list_uploaded_files_tool
- Remove unused `re` import in file_conversion (outline code moved)
- Remove unused `os` import in middleware test
- Fix test assertion: <uploaded_files> → <current_uploads> after main merge
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: resolve CI lint errors and stale test assertion from merge
- Split long prompt line to fit 240-char limit
- Add missing `Any` import in list_uploaded_files_tool
- Remove unused `re` import in file_conversion (outline code moved)
- Remove unused `os` import in middleware test
- Fix test assertion: <uploaded_files> → <current_uploads> after main merge
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: add current_uploads to input sanitization exempt tags
The lazy-loading PR renamed <uploaded_files> to <current_uploads>.
The anti-drift guard scans all framework XML blocks and requires each
to be either blocked or explicitly exempted. current_uploads wraps
trusted server-generated file metadata, not user input, so it belongs
in the exempt set.
Co-Authored-By: Claude <noreply@anthropic.com>
* test: regenerate replay golden after uploaded_files state change
before_agent now returns {"uploaded_files": []} instead of None,
adding uploaded_files to SSE values events. Regenerated via
DEERFLOW_WRITE_GOLDEN=1.
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: review feedback — memory pipeline, stale tags, state clearing, nits
- Match both tags in memory stripping pipeline (uploaded_files|current_uploads)
- Remove stale uploaded_files from _BLOCKED_TAG_NAMES
- Clear uploaded_files on all before_agent early-return paths
- Fix ponytail: stray word in file_conversion re-export comment
- Remove dead total_omitted branch in _format_omitted_summary
- ruff format fixes
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: block current_uploads, sanitize only original user content
Per review feedback: instead of exempting <current_uploads> (which
allows user forgery), move it to _BLOCKED_TAG_NAMES and change
InputSanitizationMiddleware._process_request to scan only the
original user content (ORIGINAL_USER_CONTENT_KEY) when available.
Server-injected trusted blocks are no longer checked against the
blocked-tag denylist.
Co-Authored-By: Claude <noreply@anthropic.com>
* docs: clarify fallback reason in input sanitization comment
Co-Authored-By: Claude <noreply@anthropic.com>
* @
fix: third-round review feedback — state visibility, sanitization, regex, nits
- list_uploaded_files_tool: logger.warning instead of silent try/except
on runtime.state read failure (High)
- input_sanitization_middleware: _extract_text_from_content skips empty
text blocks to match message_content_to_text behaviour; rfind fallback
path logs warning for observability (Medium)
- memory pipeline regexes: backreference (?P<tag>)(?P=tag) in
message_processing.py and prompt.py (Low)
- file_conversion.py: re-export moved to top of file (Low)
- Tests: middleware→tool state bridge test; integrated forged-tag +
multimodal sanitization tests
PR #4174 — Follow-up issues: #4212, #4213, #4214
Co-Authored-By: Claude <noreply@anthropic.com>
@
* @
fix: 4th-round review — denylist, sanitization, scandir, nits
- Add "uploaded_files" back to _BLOCKED_TAG_NAMES (old tag still processed by
deermem; user forgery must be escaped) (consistency)
- Fix inaccurate rfind-fallback comment: UploadsMiddleware keeps string as
string, fallback is unreachable for strings (doc fix)
- Distinguish "empty string key" (upload without text) from "non-string key"
(caller forgery) so empty-text uploads never escape the server block (edge)
- Merge dual os.scandir(uploads_dir) calls into one list re-use (minor)
- Add comment on .md sibling skip known limitation: user-uploaded .md files
whose stem collides with a converted doc are hidden (boundary, no code change)
Co-Authored-By: Claude <noreply@anthropic.com>
@
* @
fix: tighten rfind-failure fallback — distinguish server blocks from user blocks
When _extract_text_from_content and message_content_to_text disagree on
multimodal list content and rfind fails, use content[0] (server-injected
<current_uploads> block) vs content[1:] (user blocks) to sanitize only
user blocks. Raw strings and non-standard dict blocks that
_extract_text_from_content misses are now also sanitized.
Non-distinguishable paths (< 2 text blocks, non-list content) still
degrade to full sanitization (safe — server block may be escaped but
user forgery never leaks). All fallback paths log via logger.warning.
Decision 18 / willem-bd 4th-round comment #3
Co-Authored-By: Claude <noreply@anthropic.com>
@
* @
fix: correct comments referencing text_blocks → content in rfind fallback
Co-Authored-By: Claude <noreply@anthropic.com>
@
* fix: 5th-round review — dead code, subagent gating, integration test, perf, consistency
- Delete unreachable ORIGINAL_USER_CONTENT_KEY guard in rfind fallback
branch (original_user_content guaranteed non-empty str at that point)
- Remove list_uploaded_files from BUILTIN_TOOLS; add include_upload_tool
param to get_available_tools(), default True; task_tool.py passes False
so subagents no longer receive a tool whose state exclusion is broken
- Add integration test exercising real create_agent graph (not mocked
runtime.state) to verify LangGraph propagates before_agent state writes
into ToolRuntime.state during same-turn tool calls
- Cache DirEntry.stat() st_size in candidates tuple to avoid second
per-file syscall in the rendering loop
- Make the upload-tag pre-check case-insensitive (content_str.lower())
to match _UPLOAD_BLOCK_RE re.IGNORECASE
PR #4174 — willem-bd 5th-round review items #1-#5
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(channels): pass files metadata through _human_input_message() for IM uploads
_human_input_message() was not passing additional_kwargs.files to the
downstream message. UploadsMiddleware read no files, wrote
uploaded_files=[], and list_uploaded_files reported same-run IM
attachments as historical files (fancyboi999 repro).
Fix: add files parameter to _human_input_message(), call site passes
files=uploaded. Regression test locks the contract.
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(channels): remove legacy <uploaded_files> manual prepend to fix double-injection regression
Commit 8d86dbf6 added files= pass-through to UploadsMiddleware but
left the manual _format_uploaded_files_block() prepend in place.
Every IM attachment reached the model twice — once via the legacy
<uploaded_files> block and once via <current_uploads>.
This commit removes the manual prepend and the now-dead
_format_uploaded_files_block() function. UploadsMiddleware is the
sole upload-context producer for both IM and web paths.
Reported-by: fancyboi999 (PR review)
Co-Authored-By: Claude <noreply@anthropic.com>
* docs: update #4212 issue body to reflect completed fixes and narrowed remaining scope
* chore: remove temporary scratch file
* fix(middleware): neutralize user-derived values inside <current_uploads> block
Upload-derived filenames, paths, outline titles, and preview text are
interpolated verbatim inside the trusted <current_uploads> wrapper,
which InputSanitizationMiddleware exempts from sanitization. A crafted
filename or document heading containing blocked authority tags would
bypass the guardrail and enter model context as trusted framework data.
Fix: call neutralize_untrusted_tags() on all four user-derived values
inside _format_file_entry(), preserving the outer <current_uploads>
wrapper untouched.
Reported-by: fancyboi999 (P1 security review)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(middleware): neutralize extension labels in omitted-file summary
Files exceeding the 10-item context cap bypass _format_file_entry().
Their extensions, derived from user-controlled filenames via
_extension_label(), were interpolated verbatim into the trusted
<current_uploads> wrapper — another path for blocked authority tags
to escape the guardrail.
Fix: neutralize extension values inside _extension_label(), the
single extraction point for all extension labels.
Reported-by: fancyboi999 (P1 security review)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(tools): neutralize user-derived values in list_uploaded_files tool result
Apply neutralize_untrusted_tags() to every model-visible user-derived value
returned by list_uploaded_files: filename, virtual path, extension, outline
titles, outline preview lines, and omitted-file extension summary.
This closes the last remaining injection bypass in the upload lazy-loading
path - the <current_uploads> block and its omitted summary were already
neutralized (previous commits), but the list_uploaded_files tool produced
a second exit for the same attacker-controlled metadata that
ToolResultSanitizationMiddleware did not cover.
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(tests): add missing include_upload_tool=False to task_tool mock assertions
PR #4174 added include_upload_tool parameter to get_available_tools().
task_tool.py correctly passes include_upload_tool=False for subagents
but 5 existing tests' assert_called_once_with expectations were not
updated, causing CI failures.
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
|
||
|
Ryker_Feng
|
20debf9cc7
|
feat(agents): per-agent model and generation settings (#4347)
* feat(agents): per-agent model and generation settings Let each custom agent choose its own model and sampling settings (temperature, max_tokens) plus thinking / reasoning_effort defaults, so agents sharing a model profile are no longer stuck with one shared temperature and output length (#4336). AgentConfig gains optional model_settings / thinking_enabled / reasoning_effort (None = inherit). create_chat_model applies per-caller model_overrides on top of the profile before the thinking/Codex transforms; the lead agent resolves each knob with precedence request > agent config > profile/default. The /api/agents create/update routes persist the fields and reject an unknown model. The default lead agent path is unchanged (no agent config -> overrides None). The agent chat composer also stops force-overriding an agent's configured default model with models[0]. * fix(agents): tri-state thinking control and default-model capability gating The model-settings dialog seeded the thinking switch to false, so opening it to tweak temperature and saving silently disabled thinking (the runtime default is on) with no way back to inherit. It also hid the thinking / reasoning controls whenever the agent inherited the global default model, since `__default__` never resolved through `models.find`. Give thinking an explicit Inherit / On / Off tri-state so an untouched save is a no-op, and resolve `__default__` to the effective default (models[0]) for the capability check. Logic lives in the tested helpers module. |
||
|
Aari
|
cd34a1a504
|
fix(skills): don't attach model tracing to the in-graph skill security scan (#4252)
* fix(skills): don't attach model tracing to the in-graph skill security scan * fix(skills): pass attach_tracing explicitly from the in-graph scan call site Follow the tracing INVARIANT's own convention rather than detecting the call context: scan_skill_content takes an attach_tracing flag, and _scan_or_raise -- the single in-graph choke point -- passes False. Standalone callers (Gateway skill routes, installer) keep the default True. The INVARIANT list named four sites and asks that new in-graph calls be added to it; record this fifth one so a future audit of that list finds it. --------- Co-authored-by: Willem Jiang <willem.jiang@gmail.com> |
||
|
hataa
|
10890e10a8
|
feat(authz): propagate trusted authorization principal context (#4203) | ||
|
Huixin615
|
f9340c1f08
|
test(mcp): cover passive skill tool visibility (#4247)
* test(mcp): cover passive skill tool visibility * test(mcp): tighten deferred discovery coverage |
||
|
Aari
|
7df44f586c
|
fix(agents): refuse empty SOUL.md updates in update_agent (#4219)
* fix(agents): refuse empty SOUL.md updates in update_agent setup_agent already rejects empty/whitespace soul (#3553). update_agent is the sibling write path and previously reported success while wiping a working SOUL.md. Mirror the same guard before staging. * fix(agents): guide the retry in the empty-SOUL update rejection Append "Omit the soul field if you do not want to change it." to the empty-soul error so the model self-corrects in one step instead of retrying with another null-like value, matching the "No fields provided" sibling message's helpfulness. Both regression tests assert the guidance. |
||
|
Huixin615
|
65afc9b1d2
|
fix(skills): apply allowed-tools only to active skills (#4098)
* fix(skills): scope allowed-tools to active skills * fix(skills): tolerate stale active skill paths * chore: retrigger CI * fix(skills): document policy activation limits * perf(skills): reuse per-step tool policy decisions * fix(skills): harden runtime tool policy contracts * fix(skills): redact cached policy decisions * fix(skills): make slash tool policy authoritative * fix(skills): preserve policy-safe discovery tools * test(skills): cover explicit task delegation policy |
||
|
Daoyuan Li
|
0dd90ccfde
|
fix(agents): require config.yaml in update_agent's legacy-agent guard (#4166)
update_agent (the harness tool) and PUT /api/agents/{name} (the same
operation over HTTP) share an identical guard meant to block updates to
an agent that only exists in the legacy shared layout. The guard checked
bare directory existence:
if not agent_dir.exists() and paths.agent_dir(name).exists():
When memory is enabled, the first time a user chats with a legacy shared
agent, the memory writer creates a per-user directory containing only
memory.json (no config.yaml). agent_dir.exists() is then true, so the
guard never fires: the tool falls through to load_agent_config, which
resolves through to the legacy shared config via the already-hardened
resolve_agent_dir, and silently writes a brand-new config.yaml/SOUL.md
into the memory-only directory. That forks the agent for just this user;
every other user keeps reading the original shared config forever, with
no error or warning.
resolve_agent_dir itself was already hardened against exactly this
failure mode: it requires config.yaml to exist, not just the directory.
Mirror that condition at both call sites here.
|
||
|
qin-chenghan
|
713ee544b7
|
fix(agents): stop persisting base64 image data in checkpoint state (#4140)
* fix(agents): stop persisting base64 image data in checkpoint state (#4138) The viewed_images state field stored full base64-encoded image data, which was duplicated across every subsequent checkpoint (O(n * steps) growth). A single 1MB image viewed early in a conversation would be re-stored in every checkpoint for the rest of the session. Changes: - ViewedImageData: replace base64 field with lightweight metadata (mime_type, size, actual_path) - view_image_tool: store only metadata in state, no base64 encoding - ViewImageMiddleware: read image files from disk on-demand in before_model and encode base64 temporarily for the model call - Update all tests to use the new metadata-only format This is the first step of #4138. The base64 data is no longer in persistent state, but the injected HumanMessage (with base64 content) still appears in the checkpoint for the step where it was injected. Checkpoint retention policies and large tool result dedup are separate follow-up items. * fix(agents): address review feedback on #4140 - view_image_tool: remove stale 'convert to base64' comment, replace with 'validate contents'; drop redundant image_size reassignment and add a TOCTOU guard that rejects files changed between stat() and read(). - view_image_middleware: extract _read_image_as_data_url helper that re-checks size against the recorded value AND the absolute cap (_MAX_IMAGE_BYTES). Document the trust assumption for actual_path (server-set, not client-settable) in the helper docstring. - view_image_middleware: abefore_model now runs the blocking read+encode via asyncio.to_thread to avoid stalling the event loop on up to 20MB images. - tests: add coverage for OSError during read, file-changed-since-view (TOCTOU), and size-exceeds-cap branches. |
||
|
Aari
|
79cdd99fca
|
fix(mcp): validate MCP tool names at load so deferred prompts stay inert (#4154)
* fix(tools): escape MCP tool names rendered into deferred prompts get_deferred_tools_prompt_section and get_mcp_routing_hints_prompt_section list MCP tool names into the <available-deferred-tools> and <mcp_routing_hints> system-prompt blocks without escaping, while the mirror get_skill_index_prompt_section (per its docstring) does escape. An MCP name is taken verbatim from an external server, so a crafted name could close the block and forge a framework tag. Escape names (and routing keywords) at render, mirroring the skill-index section. * fix(mcp): validate tool names at the load boundary Escaping at render only neutralizes < > &, so a tool name with newlines or markdown still injects free-form text into the deferred-tools prompt block. Deferred (tool_search) tools are never bound, so the provider's function-name check never runs on them. Drop any MCP tool whose name is not a valid identifier (^[A-Za-z0-9_-]+$) in get_mcp_tools() — the same charset the provider enforces at bind time — before it can enter the catalog or the prompt. Render-time html.escape stays as defense-in-depth. Mirrors the load-time skill-name validation in skills/storage/skill_storage.py. |
||
|
Aari
|
1ebf59fe24
|
fix(tools): stop capping tool_search's select: at MAX_RESULTS (#4054)
`select:` names its targets explicitly, so capping it silently drops schemas the
model asked for by name -- and picks the survivors by catalog order, not request
order. The model is told the tool it wanted was not returned by nothing at all;
it then tries to call a tool that is still deferred.
The rule is already stated three times in the repo, and this is the one place
that breaks it:
- backend/AGENTS.md:447 -- "select: returns all requested skills without a
result cap; other modes cap at MAX_RESULTS=5"
- skills/catalog.py:71 -- SkillCatalog.search returns select: uncapped; the
ranked modes slice. DeferredToolCatalog shares its query grammar and its
MAX_RESULTS = 5, and is capped.
- tool_search's own docstring -- "select:Read,Edit -- fetch these exact tools
by name" versus "notebook jupyter -- keyword search, up to max_results best
matches". Only the ranked form promises a cap.
The cap is applied twice: once inside `DeferredToolCatalog.search` and again in
the tool closure. `search` already caps the ranked branches internally, so the
closure's slice is redundant for them and is the only thing capping `select:`
once the first is removed -- fixing one site alone changes nothing the model can
observe. Its sibling closure, `skills/describe.py::describe_skill`, calls
`catalog.search(name)` with no slice.
Both slices are removed. The ranked modes keep their cap.
|
||
|
Ryker_Feng
|
41658c5ff4
|
feat(skills): add skill review quality gate (#4037)
* feat(skills): add skill review quality gate * fix(skills): skip review eval fixtures in CI * fix(skills): ignore review eval fixtures in bundled scans * fix(skill-review): harden review gate boundaries * fix(skills): address skill review gate feedback |
||
|
Nan Gao
|
aafd5077b2
|
feat(subagents): show effective model and token usage on task cards (#4049)
* feat(subagents): show runtime metadata on task cards * fix(subagents): stop task-card render loop and dedupe model fetches Address code review on the runtime-metadata cards: - P1 render loop: the terminal ToolMessage is re-parsed on every MessageList render and always carries modelName/usage, so the presence-based setTasks condition fired a fresh state object each render -> "Maximum update depth exceeded". computeNextSubtask now returns a value-compared `changed` flag and a pure subtaskNotification() routes terminal transitions through the deferred after-render path while skipping no-op re-parses. - Per-card useModels refetch: add staleTime: Infinity to the ["models"] query so every subtask card shares one /api/models fetch instead of refetching on each mount. * make format * refactor(subagents): dedupe token-usage validators + tidy event narrowing Address PR review follow-ups: - DRY: extract one shared token-usage validator per side. Backend status_contract.normalize_token_usage() now backs both the terminal ToolMessage metadata and the subagent.step/.end run events (step_events.py), and frontend messages/usage.normalizeTokenUsage() backs both the live task_running event (lifecycle.ts) and the terminal ToolMessage metadata (subtask-result.ts). Prevents the input/output/ total_tokens validation from drifting across the four former copies. - Nit: onCustomEvent narrows event.type once instead of re-checking the object shape per branch; the redundant task_started early-return (already validated by taskEventToSubtaskUpdate) is dropped. |
||
|
Ryker_Feng
|
ebc09ce130
|
feat(mcp): auto-promote deferred MCP tools from routing hints (#4019)
* feat(mcp): auto-promote deferred MCP tools from routing hints
When tool_search.enabled=true defers MCP tool schemas, PR1 routing hints
still require the model to spend a tool_search discovery round trip before
it can call the tool the routing metadata already points at. This adds a
McpRoutingMiddleware that matches the latest user message against PR1
routing keywords and promotes the matching deferred schemas before the
model call, removing that round trip.
Design (soft routing, opt-in, additive):
- Matches only the latest real HumanMessage (shared is_real_user_message
helper, reused by SkillActivationMiddleware so the two cannot drift);
case-insensitive substring match, no tokenizer dependency.
- Ordering: priority desc, then tool name asc; capped by the new global
tool_search.auto_promote_top_k (default 3, clamped 1..5). Does not add or
consume a per-tool auto_promote_top_k (PR1 schema unchanged); a per-tool
value is ignored with a DEBUG note.
- Returns a plain {"promoted": ...} state update (not a Command) and relies
on ThreadState.merge_promoted for union/dedupe, so auto-promote and a
model-triggered tool_search converge on the same catalog hash.
- Installed before DeferredToolFilterMiddleware on every deferred-tool path
(lead agent, subagent, embedded client, webhook via shared builders);
a construction-time assert rejects the reversed order. catalog_hash is
None / no routing index is a complete no-op, so bootstrap and ACP skip it.
- Privacy: never executes tools, never promotes policy-filtered tools, adds
no routing keywords or matched tool names to trace metadata or INFO/WARN
logs.
No behavior change when tool_search.enabled=false.
Tests: index construction, matching semantics, middleware state updates,
same-cycle deferred-filter interaction, lead/subagent/embedded-client
builder wiring + order invariant, config clamping, config.example.yaml
parseability, and privacy assertions.
* refactor(mcp): address auto-promote review nits
- executor: access app_config.tool_search.auto_promote_top_k directly to match
the lead-agent and embedded-client paths (drop the over-defensive getattr that
masked missing config); update the subagent test mock to carry tool_search.
- tool_search / mcp_routing_middleware: cross-reference the duplicated routing
priority/keyword normalization between the builder and the middleware's
defensive _normalize_index so they cannot silently drift.
- MCP_SERVER.md: document that auto-promote keyword matching is a case-insensitive
substring test (not word-boundary), advising distinctive keywords.
|