Queue comments received while a run is active, then submit one deduplicated follow-up after it finishes. Failed drains are requeued and watcher tasks stop cleanly with the channel manager.
Sync the harness docs with the #3875 subagent middleware changes:
- subagents.mdx (en/zh): fix built-in max_turns defaults (general-purpose
160->150, bash 80->60) to match code and config.example.yaml; document the
new config (global + per-agent override) and add a
'Runaway guards' section covering the LoopDetection / TokenBudget /
Summarization middlewares now mirrored on the subagent chain.
- middlewares.mdx (en/zh): note that loop-detection, token-budget, and
summarization guards are shared with the subagent chain (#3875), instead of
implying they are Lead-Agent-only.
Code, contracts/subagent_status_contract.json (v2), and config.example.yaml
already reflect #3875; only the docs were lagging.
* fix(skills): offload blocking filesystem IO in get_custom_skill_history
The GET /api/skills/custom/{name}/history handler ran its storage probes and the
per-skill .history read directly on the asyncio event loop:
get_or_new_skill_storage(), custom_skill_exists(), get_skill_history_file().exists()
and read_history() are all blocking filesystem IO. make detect-blocking-io flagged
the existence probe (routers/skills.py:224) as DIRECT_ASYNC.
Move the whole read into a nested sync function run via asyncio.to_thread; a None
return signals 404 (distinct from an empty history list). Behavior is unchanged.
Per the blocking-io-guard SOP:
- Candidate: get_custom_skill_history (FILE_METADATA, DIRECT_ASYNC) -> FIX+ANCHOR.
- Re-scan: the finding no longer appears for this handler.
- Anchor: tests/blocking_io/test_skills_router.py drives the real handler against a
real on-disk skill + history; teeth verified red (pre-fix) -> green (post-fix)
under make test-blocking-io.
Scoped to this self-contained read handler. rollback_custom_skill and update_skill
also touch blocking IO but interleave it with awaits (security scan / cache refresh)
and do a read-modify-write, so offloading them needs the asyncio.Lock serialization
treatment (cf. #3552) and is left as a separate fix unit.
* test: trim dead skills history setup
* fix(skills): use the user-scoped storage accessor in the offloaded history read
The merge with main left the offloaded reader calling get_or_new_skill_storage,
which is not defined in this module (ruff F821), so lint failed and the handler
would raise NameError at runtime. Use _get_user_skill_storage(config) — the same
accessor every other handler in this router uses.
Also update the regression test for the current route signature: the handler is
now admin-only and takes a Request, so the test supplies request.state.user
(mirroring tests/blocking_io/test_channel_runtime_config_store.py) and seeds the
history through the same user-scoped accessor.
---------
Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
* fix(subagents): align prompt and middleware subagent limit; allow min of 1
SubagentLimitMiddleware clamped max_concurrent to [2, 4] internally, but
agent.py and client.py fed the raw config value into the system prompt, so
a user-configured 1 (or 5) produced a prompt that disagreed with the
enforced middleware limit. Lower MIN_SUBAGENT_LIMIT to 1 and clamp the raw
config value with _clamp_subagent_limit() at both the agent factory and the
embedded client so the prompt and middleware see the same value.
* fix: remove unused imports MAX_CONCURRENT_SUBAGENT_CALLS, MIN_CONCURRENT_SUBAGENT_CALLS, clamp_subagent_concurrency
* fix: harmonize clamp range [1,4] across middleware, config, and prompt path; fix lint
- Changed MIN_CONCURRENT_SUBAGENT_CALLS from 2 to 1 so prompt.py's
clamp_subagent_concurrency and the middleware's _clamp_subagent_limit
both clamp to [1,4] — eliminating the divergence where the prompt told
the model 'max 2 task calls' but the middleware enforced 1.
- Applied _clamp_subagent_limit at build_middlewares (agent.py:360) so
all 3 construction sites (agent.py:360, agent.py:450, client.py:259)
consistently clamp the config-resolved limit.
- Derived MIN_SUBAGENT_LIMIT / MAX_SUBAGENT_LIMIT from
MIN_CONCURRENT_SUBAGENT_CALLS / MAX_CONCURRENT_SUBAGENT_CALLS so the
two module-level definitions stay in sync.
- Added TestConfigParity.test_prompt_path_and_middleware_clamp_agree
regression test.
- Fixed lint.
* fix(lint): add missing imports for MIN_CONCURRENT_SUBAGENT_CALLS and MAX_CONCURRENT_SUBAGENT_CALLS
* docs+test: update AGENTS.md clamp range to 1-4; add prompt/middleware parity regression test
- backend/AGENTS.md still documented the old [2,4] clamp in two places;
updated to [1,4] to match MIN_CONCURRENT_SUBAGENT_CALLS = 1.
- Added test_apply_prompt_template_single_subagent_limit_matches_middleware:
renders the real system prompt with max_concurrent_subagents=1 and asserts
the advertised HARD LIMITS value equals SubagentLimitMiddleware's enforced
max_concurrent — the end-to-end check that would have caught the [1,4] vs
[2,4] prompt-path divergence flagged in review.
* refactor: simplify per review — restore clamp delegation, drop redundant call-site clamps
Per willem-bd's review, reduce the PR to the one behavioral change plus
docs/tests:
- _clamp_subagent_limit delegates to clamp_subagent_concurrency again
instead of inlining a byte-identical copy; with a single source of
truth the TestConfigParity sync-check class is unnecessary — dropped.
- Revert the call-site clamps in agent.py (build_middlewares,
_make_lead_agent) and client.py (_ensure_agent) to main: both
downstream consumers (SubagentLimitMiddleware.__init__ and the prompt
path) already clamp internally, and the cross-module private import
of _clamp_subagent_limit goes away with them.
- Keep MIN_CONCURRENT_SUBAGENT_CALLS = 1 (the fix), the [1, 4]
docstring updates, the AGENTS.md range corrections, and the
end-to-end prompt/middleware parity test for single-subagent mode
(docstring reworded: on main a configured 1 was bumped to 2 by both
paths — there was no divergence to fix, just a silently raised floor).
* test: fix stale comment referencing reverted agent.py/client.py call-site clamps
---------
Co-authored-by: nankingjing <nankingjing@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Enforce one queued or running scheduled-task run per task with a partial unique index. The migration resolves legacy duplicates before creating the index, and losing inserts use the existing conflict or skip outcomes.
Normalize YAML frontmatter keys in the shared parser so validation and review report malformed fields instead of failing while sorting mixed key types.
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.
* fix(runtime): stop subgraph stream frames impersonating root frames
The web frontend always requested stream_subgraphs, and since delegated
subagent graphs inherit the parent checkpoint namespace (#4215), their
values snapshots and token chunks ride the parent stream. The worker's
_unpack_stream_item dropped the namespace and published every subgraph
frame under a bare event name, so a subagent's values snapshot replaced
the whole thread view in SDK clients (#4399), its token chunks flooded
the parent message stream, and a subagent's LLM error fallback could be
mistaken for the parent run's.
Publish subgraph frames under namespace-qualified SSE event names
(mode|ns1|ns2, LangGraph Platform style) and keep root-only consumers
(file-tool chunk batcher, subagent event persistence, error-fallback
detection) on root frames only. Drop streamSubgraphs from the frontend
submit paths: subtask progress arrives via root-namespace task_* custom
events, so the flag only exposed the leak.
* test(runtime): add production-shaped subgraph stream regression tests
Address review: the namespace tests validated the publishing helpers
with hand-fed namespaces, while the #4399 regression lived in the
integration between LangGraph's delegation routing and the worker's
stream loop. Add TestWorkerSubgraphStreamIntegration: a real parent
graph delegates through the real SubagentExecutor and streams through
run_agent into a real MemoryStreamBridge, locking both stream_subgraphs
modes -- delegated frames arrive namespaced (never bare), a delegated
error fallback cannot mark the parent run as errored, and without the
flag delegated frames stay out while task_* custom events remain.
* fix(frontend): strip and parse the <current_uploads> upload context tag
#4174 renamed the upload context block that UploadsMiddleware prepends to
the user message from <uploaded_files> to <current_uploads>, but the
frontend tag vocabulary was not updated, so the raw block (file list plus
usage guidance) rendered inside the user's chat bubble and the file-chip
content fallback stopped matching. Add the new tag to
stripUploadedFilesTag, INTERNAL_MARKER_TAGS (covers export and streamdown
preprocessing), parseUploadedFiles, and the chip fallback detection.
<uploaded_files> stays supported for history and IM-channel messages.
* fix(frontend): parse upload-context sizes to bytes for the file chip
parseUploadedFiles stored the raw leading number of the human-readable
size (e.g. parseInt("177.6 KB") -> 177) into FileInMessage.size, which
is documented as bytes. On the content-fallback chip path (history/IM
messages without additional_kwargs.files) formatBytes then rendered a
177.6 KB file as "0.2 KB".
Convert the backend's "<n> KB" / "<n> MB" form back to bytes so the chip
re-renders at the original magnitude; update the parse tests to assert
byte values.
* fix(frontend): keep leading orphan tool messages visible
#3880 stopped dropping orphan tool messages that arrive after a terminal
group, but left the leading-orphan branch dropping the message with a
console.error on every render. The case is reachable: history pagination
cuts by event seq, not turn boundaries, so the first loaded page can
begin mid-turn with tool results whose AI tool-call message sits on an
unloaded older page — in dev mode the diagnostic surfaces as a
full-screen Next.js error overlay (#4399). Open a processing group for
the leading orphan instead; loading the older page re-groups it under
its real turn.
* test(frontend): lock leading-orphan accumulation invariant; clarify self-heal comment
Address review on #4408:
- The self-heal note only holds for the pagination path. The
hidden-only-precedent case and a truly orphaned tool have no older page to
load, so the processing group persists and renders as an empty
ChainOfThought shell (convertToSteps emits steps only for type === ai).
Document that as an accepted degradation instead of implying it always
self-heals.
- Add a test locking the accumulation invariant: a leading orphan followed by
a real tool-call turn folds into one processing group, not a stranded empty
group beside the real turn.
An empty assistant message from a provider safety filter (content_filter with
no content, no tool calls) was persisted into thread history and replayed to
strict OpenAI-compatible providers, which reject it with HTTP 400 ("message ...
with role 'assistant' must not be empty") — breaking every later turn until a
new chat is started.
SafetyFinishReasonMiddleware only handled the tool-call case (#3028) and
TerminalResponseMiddleware only the post-tool case (#4027), so a plain empty
content-filter response fell through both. Extend the safety middleware to
backfill a user-facing explanation when a safety-terminated message is
otherwise blank, so the persisted turn is non-empty (and the user sees why it
was blocked).
Fixes#4393
PR #4289 corrected the false claim that GitHub auto-retries 5xx webhook
deliveries, but its replacement wording overcorrected: it described a
mistaken 200 response as dropping the webhook "forever with no way to
recover it" / "permanently" - implying manual recovery is impossible,
not just unprompted. fancyboi999 flagged this in a CHANGES_REQUESTED
review on #4289 (submitted 23:21:23Z, referencing
github_webhooks.py:190-197,325-335 and
test_github_webhooks.py:548-559) that went unaddressed before the PR
was approved and merged roughly 40 minutes later.
Verified directly against GitHub's documentation before changing
anything: the manual "Redeliver" button and the REST/App redelivery
endpoints place no failed-status precondition on the delivery id - any
past delivery, success or failure, can be redelivered within GitHub's
~3-day window
(https://docs.github.com/en/webhooks/testing-and-troubleshooting-webhooks/redelivering-webhooks,
https://docs.github.com/en/rest/repos/webhooks#redeliver-a-delivery-for-a-repository-webhook).
The real problem with swallowing a transient failure into 200 is
discoverability, not recoverability: the delivery never shows up as
failed in Recent Deliveries, and GitHub's own recommended
scripted-recovery pattern filters on non-OK status by convention, not
because the platform blocks redelivering a success. A 200'd delivery
can still be redelivered by hand if an operator happens to look - they
just get no signal telling them to, unlike the 503 path, which stays
correctly flagged as failed and so is actually found.
- github_webhooks.py: reworded the route docstring and the inline
fan-out comment to describe the 200-vs-503 difference as
discoverability, not raw recoverability, and added the redelivery
docs link alongside the existing failed-deliveries link.
- test_github_webhooks.py: reworded
test_dispatch_failure_returns_503_not_200's docstring the same way.
No assertions changed.
All 44 tests in test_github_webhooks.py pass, plus
test_github_dispatcher.py / test_github_channel.py /
test_github_registry.py / test_channels.py (322 total). ruff check and
ruff format --check are clean on both touched files.
* fix(gateway): seed branch run-events so inherited history survives (#4380)
The thread feed (GET /messages, /messages/page) reads the run-event store,
but branch creation only wrote checkpoint state - a fresh branch had no
message rows, so the parent history vanished from the UI as soon as the
branch's first run refreshed the feed. Seed the branch's run_events from
the same checkpoint snapshot the branch was created from, mirroring
RunJournal's message-event contract (event types, hidden-message rules,
original-user-text restoration). Best-effort: a seeding failure degrades
to the old behavior and is reported as history_seed_mode=failed.
* docs(gateway): correct branch-seed docstring on RunJournal divergences
The "consumers cannot tell a seeded row from a journaled one" claim was
overstated for AI rows: seeded rows omit run-scoped enrichment (usage /
latency_ms / llm_call_index) and stamp caller=lead_agent rather than the
message's original caller, neither recoverable from a checkpoint message.
Rewrite the docstring to state these divergences explicitly and note they
are display-invisible today (no consumer indexes those keys; per-message
caller drives no attribution). Also add a code comment marking the
hide_from_ui filter as intentionally stricter than the live paths.
* fix(gateway): seed dict-shaped checkpoint messages + persist hidden AI/tool rows
Two review-driven fixes to build_branch_history_seed_events:
1. Checkpoint messages can arrive as model_dump()-shaped dicts (the
branch-matching helpers in threads.py already handle both BaseMessage
and dict). The seed only handled BaseMessage, so a dict-backed
checkpoint seeded nothing and the branch reported skipped_empty while
history existed. Coerce dicts back to BaseMessage via messages_from_dict
(faithful: tool_calls / tool_call_id / additional_kwargs survive);
unparseable dicts are dropped best-effort.
2. RunJournal.on_llm_end and _persist_tool_result_message persist
hide_from_ui AI/tool rows unconditionally (the frontend hides them
client-side); the hide check only gates the reconciliation pass. The
seed dropped them, so a hidden turn vanished from a forked feed and
seeded rows diverged from journaled ones. Match RunJournal and write
them, restoring true row-level parity.
Adds tests for dict deserialization, the unparseable-dict drop, and the
hidden AI/tool persistence contract.
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.
* 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.
The reasoning-effort selector trigger only appended a value for the four
explicit efforts; when reasoning_effort was unset it rendered
"Reasoning Effort:" with an empty value. The dropdown already treats an
unset effort as medium (highlighted and checked), so the trigger and the
menu disagreed on the default. Show "Medium" in the trigger when unset to
match the dropdown's existing default.
* fix(mcp): use threading.Lock for OAuth token refresh to avoid cross-thread deadlock
OAuthTokenManager created one asyncio.Lock per server for the process
lifetime. The embedded/TUI sync tool-call path (DeerFlowClient.stream()
-> LangGraph's ToolNode._func -> a ThreadPoolExecutor ->
make_sync_tool_wrapper's per-call asyncio.run()) invokes
get_authorization_header from a fresh event loop on a fresh OS thread
for every concurrent tool call. asyncio.Lock binds to whichever loop
first contends on it; when a caller on a different loop later releases
or wakes a waiter, it does so without call_soon_threadsafe, so the
waiting loop's selector is never woken and that caller hangs forever
with no exception. A third concurrent caller instead raises a
synchronous RuntimeError ("bound to a different event loop"). Either
way, two concurrent OAuth-protected tool calls (including the very
first cold-start token fetch) can freeze the entire agent turn.
Gateway's async path (ToolNode._afunc) is unaffected.
Replace the asyncio.Lock with a plain threading.Lock, acquired via
asyncio.to_thread so the blocking wait never blocks the event loop,
and released synchronously in a finally block. This keeps the
single-fetch de-duplication the lock provided while making it safe
across however many event loops/threads call into the same server's
lock.
Adds a regression test that runs three threads, each with its own
event loop, calling get_authorization_header concurrently for the same
server, and asserts (with a bounded join timeout so a regression fails
fast instead of hanging the suite) that none hang or raise, and that
only one real token fetch happens.
* fix(mcp): make OAuth lock acquisition cancellation-safe
get_authorization_header acquired the per-server threading.Lock via a
bare `await asyncio.to_thread(lock.acquire)`, with the try/finally that
guarantees release only starting after that await returned. Once the
executor thread had actually started running lock.acquire(), cancelling
the awaiting caller only stopped the caller -- Python cannot interrupt a
running OS thread. CancelledError was still delivered to the caller
immediately, but the thread kept blocking until the current holder
released, then silently acquired the lock with nobody left to call
release() for it. The lock stayed locked forever and every later OAuth
token refresh for that server blocked permanently at the same line --
the exact cross-thread deadlock this lock was introduced to prevent,
reintroduced via a different path under cancellation (e.g. a caller
wrapped in asyncio.wait_for/asyncio.timeout, or task-group cancellation).
Run the acquisition as an explicit asyncio.create_task, awaited via
asyncio.shield() so cancelling the caller no longer cancels the
underlying acquisition task. If the caller is cancelled, keep
(re-)waiting on the still-shielded acquisition task -- tolerating
further cancellation during this cleanup by simply retrying -- until it
actually finishes, release the lock immediately, and only then
re-raise. This guarantees the lock is released regardless of when or
how many times the caller is cancelled: before the acquisition is even
scheduled, while queued, or after it has already been silently granted.
Adds a regression test that holds the per-server lock, starts a second
caller that has to wait for it, cancels that caller while it is
genuinely blocked in its executor thread, releases the original holder,
and asserts a third caller completes within a bounded asyncio.wait_for
and still performs exactly one token fetch. Every potentially-hanging
await is bounded so a regression fails the test quickly instead of
hanging the suite.
* fix(feishu): check response.success() on card/reaction SDK calls
_reply_card, _create_card, _update_card, and _add_reaction call the
lark-oapi SDK and only used the response on the happy path, never
checking response.success(). lark-oapi signals a business-level
failure (invalid/expired card, permission error, etc.) by returning a
response with success()=False rather than raising, so these calls
looked identical to callers whether Feishu accepted them or not.
This file's own _upload_image/_upload_file/_receive_single_file
already guard against exactly this by checking response.success()
before trusting the response; the card/reaction helpers just didn't
follow that established pattern.
The gap is most exposed on _update_card: Feishu supports streaming, so
a single conversation issues many _update_card patches, each one a
chance to silently drop an update. _send_card_message already has a
try/except around _update_card that retries (via _send_with_retry) on
non-final failures and falls back to a brand-new card on final ones -
but that logic was unreachable because _update_card could never raise
on a business failure.
Adds response.success() checks to all four methods, raising for
_reply_card/_create_card/_update_card (mirroring the upload helpers,
and making the existing retry/fallback logic in _send_card_message
reachable) and logging a warning for _add_reaction (mirroring
_receive_single_file, since a failed reaction is fire-and-forget and
must not trigger a redundant resend of the whole card).
Adds regression coverage in TestFeishuCardSuccessChecks: a
business-failure mock response for each of the four methods, plus two
tests driving _send_card_message end to end to confirm the retry and
fallback-to-new-card paths actually engage now.
* fix(feishu): include log_id in card SDK failure errors + cover create_card retry path
willem-bd's review on this PR suggested two non-blocking follow-ups:
- _reply_card/_create_card/_update_card's RuntimeError on a business-level
failure omitted the Feishu log_id, unlike _add_reaction and
_receive_single_file in this same file, which already include it in their
warning logs. Adding it gives a Feishu support-traceable id once retries
exhaust and the error reaches the caller.
- _create_card's failure on the no-thread_ts path (the tail of
_send_card_message) only had direct unit coverage
(test_create_card_raises_on_business_failure_response), unlike
_update_card's failure path, which also has an end-to-end test through
send() confirming _send_with_retry engages
(test_send_retries_after_update_card_business_failure_then_succeeds).
Adds the mirrored end-to-end test for the _create_card path.
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.
* refactor(memory): pluggable MemoryManager interface for backend onboarding
Optimize the MemoryManager interface layer so new backends (mem0/openviking)
onboard with less code and the contract stays stable as capabilities are
added. A minimal backend now implements only from_config + add + get_context
(verified by test_memory_manager_interface.py::_MinimalBackend onboarding via
the factory); the factory no longer knows a backend's private hooks.
- MemoryManager: ABC -> pydantic BaseModel; three-tier methods (tier-1
add/get_context abstract; tier-2 management defaults; tier-3 optional hooks
warm/reload/fact + on_pre_compress/on_turn_start). Dropped 3 self-serving
hooks. 6 hasattr probe sites -> direct call + try/except NotImplementedError.
- from_config classmethod: factory thins to resolve + inject storage_path +
collect host hooks + call from_config; DeerMem-specific hook consumption
moved from factory to DeerMem.from_config.
- Invariants: @model_validator (mode='tool' requires search via supports_search
ClassVar); DeerMemConfig storage_path-is-file check moved here from factory.
- Async: aadd/aget_context/asearch default to the sync path (speculative).
- Callbacks: MemoryCallbacks + LangfuseMemoryCallbacks; on_memory_llm_call
subsumes tracing_callback (same signature/timing/mutation); deleted the
tracing_callback field. DeerMem decoupled from langfuse (portability).
- noop keeps read-op empty overrides (avoids router 500s on the
disable-memory-via-noop path); only delete/export inherit the base raise.
Behavior preserved: 661 passed / 13 skipped. Docs: backends/README.md rewritten
(three-tier + from_config + callbacks); samples README updated; removed stale
private doc paths.
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(memory): 501 on unsupported read/manage endpoints + accurate warm log
Review follow-up on the three-tier MemoryManager refactor.
- Read/manage endpoints (GET /memory, /memory/export, /memory/status,
DELETE /memory, POST /memory/import) and the /memory/reload fallback now
catch NotImplementedError -> 501, matching the fact-CRUD endpoints. The
hasattr->try/except migration had skipped these: they were @abstractmethod
before (every backend implemented them, so they never raised), so once they
became tier-2 default-raise a minimal backend (only add + get_context) hit a
raw 500 -- there is no global NotImplementedError handler. get_memory is
shared via _get_memory_or_501 (covers /memory, export, status, reload
fallback). noop is unchanged: its read-op empty overrides never raise.
- warm() base default returns None (tri-state: True=warmed, False=failed,
None=nothing to warm) so the Gateway lifespan logs "skipping" for a
non-DeerMem backend (e.g. noop) instead of the inaccurate "warmed
successfully" it never earned. DeerMem.warm keeps True/False.
- Tests: 6 router 501 tests (read/manage + reload fallback) + 2 lifespan
warm-log tests (None->skipping, False->warning); conformance/pluggable
assert warm() is None.
705 passed / 13 skipped; lint clean.
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(memory): review follow-ups - search-flag consistency, client reload, backend_config purity
Address review feedback on the three-tier MemoryManager refactor:
- [Medium] supports_search/search drift: the invariant now requires the
supports_search ClassVar flag to MATCH whether search() is actually
overridden (type(self).search is not MemoryManager.search), so the flag
can't drift from the impl. Catches both directions at instantiation: a
backend that overrides search() but forgets supports_search=True (was a
misleading tool-mode rejection), and one that sets the flag without
overriding (was a runtime NotImplementedError on the first memory_search).
noop sets supports_search=True to match its search() override. Conformance
adds drift + consistent-backend tests.
- [Low] client.reload_memory fallback: wrap the get_memory fallback so a
minimal backend (only add + get_context) surfaces a clean NotImplementedError
("implements neither reload_memory nor get_memory") instead of an uncaught
propagation -- mirrors the router's 501. Test added.
- [Low] backend_config purity: DeerMem.from_config restores backend_config to
the pure data the host passed after model_post_init parses the injected hooks
into DeerMemConfig (self._config, PrivateAttr); the field stays serializable
(no callables/LLM) and matches the README ("host hooks NOT in backend_config").
Test asserts purity + hooks wired.
- [Low] CHANGELOG: breaking-change note that mode='tool' + non-search backend
now fails fast at startup (was silently empty) so operators recognize it on
upgrade.
- [Nit] .gitignore: drop the env-specific .tmp-pytest/ entry (--basetemp is
local-only, not make test/CI).
709 passed / 13 skipped; lint clean.
Co-Authored-By: Claude <noreply@anthropic.com>
* docs(changelog): correct memory tool-mode fail-fast note
The CHANGELOG entry said mode='tool' + a non-search backend "(e.g. noop)"
fails fast at startup, but noop overrides search() (returns []) and sets
supports_search=True (required by the consistency invariant), so noop IS
search-capable and noop+tool does NOT fail fast. The fail-fast only affects a
custom backend that onboards without overriding search(). Reworded to drop the
misleading noop example and state both shipping backends implement search().
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* fix(sandbox): bound E2B output synchronization resources
E2B release-time output sync pulled every changed file back from the
remote VM with only a per-file size cap and no aggregate bound, so a
pathological outputs tree (thousands of files, or many sub-cap files
summing to gigabytes, or a slow VM) could make release download
unboundedly on a hot path that runs at every agent turn end.
Add three aggregate ceilings on top of the per-file cap — total bytes,
file count, and a wall-clock deadline — enforced in the sync loop. When
a ceiling is hit the pass stops early, logs what it dropped, and defers
the rest to the next release. A truncated pass skips stale-manifest
pruning so files it never reached are reconciled next time instead of
being forgotten and re-downloaded.
Closes#4340
* test(sandbox): pin multi-pass convergence of bounded output sync
The four truncation tests each exercise a single capped pass. Add a
two-pass test that locks in the invariant the design relies on for
correctness: already-synced files are skipped before the budget check,
so they never consume the cap and the deferred tail drains over
successive releases instead of the leading files being re-downloaded
every turn. A refactor that let a skipped file consume the cap would
pass the single-pass tests but fail this one.
* 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>
* fix(blocking-io): trace self/cls attribute chains and local aliases in the call graph
_record_call_ref only recorded a call-graph edge for bare-name calls and
literal self./cls. single-hop attribute calls (self.flush()). Any other
receiver shape fell through the "." not in call_name fallback and was
silently dropped from the graph -- including a deeper self./cls.
attribute chain (self.store.flush()), a local variable holding a
self./cls. attribute (store = self.store; store.flush()), or a
parameter used directly as a receiver. A real blocking call reachable
from async code only through one of those shapes never surfaced as a
finding, the opposite (and more dangerous) failure mode from the
duplicate-helper-name over-report this detector already documents.
Trace those shapes back to a self./cls. attribute or a parameter,
within the same function only, and resolve them through the same
bare-method-name fallback already used for receivers that cannot be
resolved to a name at all -- no new false-positive risk beyond what
that existing fallback already accepts.
* fix(blocking-io): narrow alias tracking to fix three scope-creep bugs
The alias/receiver tracking this detector added reused dotted_name(),
which intentionally unwraps ast.Call/ast.Subscript for blocking-call
pattern matching elsewhere in this module. Reusing it for alias
extraction let a Call or Subscript result inherit its base's
alias-worthiness, so factory().flush(), client = factory(); client.flush(),
and client = clients[0]; client.flush() were all incorrectly treated as
calls on a traced receiver. Add _simple_receiver_name(), a restricted
Name/Attribute-only extractor, and use it wherever a receiver/alias is
extracted instead of dotted_name().
Alias state also only ever grew: _record_local_receiver_alias_targets
never removed a name once traced, so a later reassignment to a
non-traceable value (client = NonBlockingClient()) left the name
aliased forever, still exposing unrelated same-named methods.
Reassigning now resolves traceability from scratch and kills the name
when the new value isn't traceable.
Separately, if/else branches had no isolation: with no visit_If
override, body and orelse shared one mutable alias set, so an alias
added in one leaked into the other and the result depended on which
branch was textually first. Add a visit_If override that snapshots
aliases before the branch, resets between body and orelse, and unions
their exit states afterwards -- a conservative, order-independent
may-alias join. Scoped to ast.If only; ast.Try/ast.Match keep the
previous unisolated traversal (different, more complex control-flow
semantics, out of scope here).
Finally, _visit_function pushed the new function's context before
visiting decorator_list/args/returns, but those expressions run at
definition time in the enclosing scope, not the function body. A
default value referencing an outer name that happens to match one of
the function's own parameter names (receiver = Store(); async def
route(receiver=receiver.flush())) was misattributed to route itself.
Visit decorators, parameter defaults/annotations, the return
annotation, and PEP 695 type-parameter bounds before pushing the new
function's context so they resolve against the enclosing scope.
Real-scanner output against the actual backend tree is unchanged
(41/41 findings, byte-identical JSON) -- these were latent
false-positive/negative risks in shapes the current codebase doesn't
happen to contain, not active miscounts.
* fix(blocking-io): fix three more alias-tracking and definition-time bugs
_record_local_receiver_alias_targets ran before the assignment's own
value was visited, so an assignment's RHS was analyzed against the
alias state *after* the target had already been updated/killed for
this same statement. Python evaluates the RHS before binding the
target: with `client = self.store` followed by
`client = client.flush()`, the second statement's target update killed
`client`'s alias before its own RHS (`client.flush()`) was visited, so
that call silently disappeared from the graph. visit_Assign and
visit_AnnAssign now visit the RHS first and only update the target's
alias afterward, matching Python's own evaluate-then-bind order.
_simple_receiver_name still returned the trailing attribute name
whenever its recursive parent lookup came back unsupported (a Call or
Subscript), instead of refusing the whole chain -- so `factory().client`
and `clients[0].client` both collapsed to plain "client", which, when
"client" was also a traced parameter or local alias, incorrectly linked
`factory().client.flush()` to an unrelated same-file `Store.flush`.
Return None instead of falling back to `node.attr`, so an unsupported
node anywhere in the chain makes the whole receiver unresolved rather
than a truncated suffix of it.
Finally, _visit_function's enclosing-scope walk of decorators,
defaults, annotations, and type_params recursed into every
subexpression uniformly, including ones that don't actually execute at
definition time: a lambda's body, a bare generator expression's
element/later-for clauses, annotations postponed by `from __future__
import annotations`, and PEP 695 type-parameter bounds (always
evaluated lazily, in their own hidden function, only if something like
T.__bound__ is ever accessed). Add visit_Lambda/visit_GeneratorExp
overrides that stop at exactly the eager subset (a lambda's own
parameter defaults; a generator's outermost iterable), skip parameter/
return annotations entirely once a `postponed_annotations` flag is set
by the future import, and drop the type_params walk instead of moving
it to the enclosing scope.
Real-scanner output against the actual backend tree is unchanged
(41/41 findings, byte-identical JSON) -- these were latent risks in
shapes the current codebase doesn't happen to contain, not active
miscounts.
* fix(blocking-io): preserve eager traversal for immediately invoked lambdas and consumed generators
visit_Lambda/visit_GeneratorExp (added last round to stop treating merely
created lambda/generator objects as executing at definition time) were
unconditional, so they also suppressed bodies that genuinely execute right
away: an immediately invoked lambda ((lambda: ...)()) and a generator
expression passed directly to an eager-consuming builtin (list/set/tuple/
frozenset/dict/sorted).
visit_Call now marks a Lambda used as its own func, or a GeneratorExp passed
as the sole argument to one of those builtins, by node identity before
generic_visit runs. visit_Lambda/visit_GeneratorExp check that marker and,
on a match, visit the node fully instead of applying the lazy walk. A
lambda/generator that is merely created, stored, passed as a callback, or
invoked later through a variable is unaffected and stays lazy.
* fix(blocking-io): scope lambda/generator laziness to definition-time expressions only
visit_Lambda/visit_GeneratorExp were unconditional overrides, so they
suppressed lambda bodies and generator elements everywhere the visitor
reached one, not only inside another function's definition-time
expressions (decorators, parameter defaults/annotations, return
annotation) where that suppression is actually needed. In ordinary
function-body code this caused real false negatives: a lambda stored in
a local and called through that name (callback = lambda: os.listdir(".");
callback()), a generator reduced by sum/any/all/min/max, a bare
lambda/generator that is merely created, and a generator wrapped in
another lazy iterator like map(...) all went unscanned, even though none
of them are definition-time expressions at all.
The previous fix for this (an id()-keyed marker set covering exactly two
eager shapes -- an immediately invoked lambda, and a generator passed
directly to a fixed list of eager-consuming builtins) narrowed the
suppression back down, but only for those two shapes, and the underlying
eager-consumer builtin set itself excluded true reducers (sum/any/all/
min/max) that consume their generator argument just as eagerly as list/
set/etc. Both are instances of the same problem: enumerating every shape
in which a lambda or generator happens to be invoked/consumed piecemeal
inside an AST visitor, which is unbounded in the general case.
Replace both mechanisms with a single boolean,
_in_definition_time_expression, set only while _visit_function walks
another function's own decorators/defaults/annotations/return
annotation. visit_Lambda/visit_GeneratorExp apply their lazy
(defaults-only/outermost-iterable-only) walk only while it is set;
everywhere else they fall through to a full generic_visit, scanning
lambda bodies and generator elements unconditionally -- the same
conservative, over-report-rather-than-infer stance this file already
takes for reachability elsewhere.
This removes EAGER_ITERABLE_CONSUMER_NAMES and the two identity-marker
sets entirely rather than growing them further. The one shape this
newly gives up on -- an immediately invoked lambda or eagerly consumed
generator used as another function's decorator/default/annotation value
-- is now an explicit, narrow, documented limitation (see
backend/AGENTS.md): definition-time expressions never scan a nested
lambda body or generator element, full stop, regardless of whether it
happens to be invoked right there.
Targeted suite (test_detect_blocking_io_static.py +
test_scan_changed_blocking_io.py + test_detector_repo_root.py +
blocking_io/test_gate_smoke.py): 65/66 pass, the one failure a
pre-existing Windows path-separator comparison unrelated to this file.
Full backend suite: identical 64 pre-existing failures on both the
pre-fix and post-fix commit, confirmed by diffing the two failure lists
directly -- zero regressions. Real scanner against the actual backend
tree: 41/41, byte-identical JSON before and after -- these were latent
risks in shapes the current codebase doesn't happen to contain, not
active miscounts.
* 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.
str_replace guards the replacement with `if old_str not in content`, which
cannot reject an empty old_str -- `"" in content` is always true. So an
empty old_str reached `str.replace("", new_str)`, which inserts new_str at
every character boundary, and the tool rewrote the file while still
returning "OK":
old_str='', new_str='# H\n' -> OK, file silently prepended
old_str='', new_str='X', replace_all -> OK, 'XdXeXfX XmXaXiXnX(X)X:X\nX...'
The empty-file branch above it already handles this case (`if not content:
if not old_str: return "OK"`), and the existing test states the intent
directly: "An empty old_str is a no-op edit and remains a benign OK". That
contract just never held once the file had content.
The tool is registered by default (config.example.yaml) and its schema
declares old_str as a plain string with no minLength, so a model can emit
"" legitimately; read-before-write only compares a hash and lets it past.
Check old_str first so the no-op holds whatever the file contains. The
empty-file case folds into the same not-found branch, which keeps its
message and behaviour.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
E2BSandbox.grep()'s glob handling reduced a directory-scoped pattern like
"src/*.js" down to just "*.js" before passing it to `grep --include=`,
dropping the directory-scoping prefix entirely. GNU grep's `--include`
matches by basename only, at any depth, so the search silently broadened
to every matching-extension file in the sandbox tree instead of just the
directory the caller asked for.
Keep the basename portion as a coarse `--include=` pre-filter (a superset
of the true match set) and post-filter grep's raw hits through
path_matches(), the same helper glob() already uses to enforce directory
scoping correctly, so grep and glob agree on what a directory-scoped
pattern means.
* feat(checkpoint): dual-mode checkpoint storage with LangGraph DeltaChannel
Add a restart-required database.checkpoint_channel_mode ("full" default,
"delta") that stores the messages channel via LangGraph 1.2 DeltaChannel,
cutting checkpoint storage from O(n^2) to O(n) for append-only history.
Existing full checkpoints seed delta state transparently; no data migration.
- config: mode schema + freeze-on-first-use with
CheckpointModeReconfigurationError; mode marker persisted in checkpoint
metadata; unsafe delta->full downgrade rejected fail-closed with
CheckpointModeMismatchError (run-level error, failed state read)
- state: delta message state schema; CheckpointStateAccessor centralizes
materialized reads for all consumers (threads API, branches,
regeneration, compaction, state updates, memory, goal workers)
- runtime: raw writers (run durations, interrupted title, thread goal)
parent their checkpoints to the checkpoint they derive from, preserving
delta ancestry; rollback forks the pre-run lineage through a state
mutation graph with Overwrite restores; InMemorySaver delta-history
override delegates to the base walk (fixes dropped first write after
migration, also present upstream)
- tests: conformance suite over {memory, sqlite, postgres} covering
migration replay, stable message IDs, storage shape and writer
preservation; conftest fixture isolates the frozen mode between tests;
stale config fakes refreshed
- ci: backend unit tests gain a postgres service
* fix(checkpoint): close materialization gaps in goal flow, guard public factory
- Route goal-continuation message reads through CheckpointStateAccessor:
raw channel_values reads see the delta sentinel in delta mode, which
disabled goal continuation (stand_down=no_durable_end_of_turn) after
durable assistant turns. Raw tuples remain for tuple-only metadata
(checkpoint id, pending_writes).
- Reject checkpoint_channel_mode='delta' + checkpointer in
create_deerflow_agent at construction: factory-built persisted graphs
bypass mode-marker injection and the fail-closed gate, reproducing
silent mixed-mode state loss. Delta without persistence stays allowed.
- Import the postgres saver lazily (pytest.importorskip in the fixture)
so the documented default install collects the suite; add a CI job
running pytest --collect-only on uv sync --group dev without extras.
- Fix test_checkpointer fallback test to patch get_app_config at its
use site (provider module), making it deterministic when a local
config.yaml selects a persistent backend.
* fix(gateway): preserve extension-owned channels in state mutations, bump config version
- build_state_mutation_graph / build_checkpoint_state_mutation_accessor
accept an explicit state_schema; branch and POST /state now compile the
mutation graph from the thread's effective schema
(graph_state_schema on the assistant graph). The base-ThreadState
fallback silently discarded channels contributed by custom
AgentMiddleware.state_schema on branch (data loss) and returned a
false-success 200 on POST /state.
- POST /state validates values keys against the mutation graph's
channels and rejects unknown fields with 422 instead of ignoring
them; reducer detection covers extension channels
(BinaryOperatorAggregate or DeltaChannel) so Overwrite replace
semantics work for middleware reducers in both modes.
- Endpoint regression: custom AgentMiddleware.state_schema value
survives branch, updates through POST /state, and an unknown field
receives 422.
- config_version 26 -> 27 for the new database.checkpoint_channel_mode
(example, Helm chart values + README, support-bundle fixture), so
existing installs get the outdated-config warning and
make config-upgrade merges the field; covered by a test driving the
real example file and the real config-upgrade script.
* fix(gateway): resolve assistant schema via one boundary, copy branch reducer values with Overwrite
GET /threads/{id}/state now resolves the thread's assistant_id through a
single reusable boundary (thread metadata -> assistant_id -> effective
graph), so channels contributed by a custom AgentMiddleware.state_schema
are materialized instead of dropped by the default lead schema. POST
/state uses the same boundary instead of resolving the schema ad hoc.
Branch writes wrap every copied reducer channel in Overwrite (derived
from the effective mutation graph: BinaryOperatorAggregate + DeltaChannel),
not just messages, so already-aggregated values are never re-merged.
Regression tests use a real AgentMiddleware.state_schema with a
non-identity reducer in both full and delta modes: GET /state returns the
extension value, POST /state replaces it, branch preserves it
byte-for-byte; the unknown-field 422 is a separate assertion.
* refactor(checkpoint): collapse read-path round-trips and ship dual-mode parity tests
Address review round 4 on PR #4292:
- Push ahistory/history limit through Pregel into checkpointer.alist
(SQL LIMIT) instead of materializing all rows and breaking in Python
- Fold the read-side mode-compat gate onto the returned snapshot's
metadata; only writes keep the pre-write tuple fetch (fail-closed)
- Cache factory-built accessor graphs per (assistant_id, mode) with
factory-identity revalidation; state reads no longer build a lead
agent per request
- get_thread: one snapshot fetch + one raw pending_writes fetch on the
resolved checkpoint (post-checkpoint __error__ writes never surface
in snapshot.tasks; verified empirically)
- DeerFlowClient.get_thread: single checkpointer.list walk collects
pending_writes per checkpoint instead of N get_tuple calls
- InMemorySaver delta-history patch: stand-down when the upstream
override disappears, try/except guard, validated-version warning,
guard tests
- make_lead_agent mode precedence: first freeze is owned by app_config
(client-supplied configurable key ignored); once frozen, injected
key/app_config must match or fail closed
- Rollback: lock in non-message channel restoration via fork
inheritance with a dedicated reducer-channel test
- Add tests/test_threads_checkpoint_mode.py and
tests/test_gateway_checkpoint_mode.py referenced by AGENTS.md and
the PR validation section: lifecycle parity (memory + sqlite),
per-step blob-count storage guard, gateway endpoint parity
Counted-saver tests pin checkpoint round-trips for aget/ahistory so
these regressions cannot silently return.
* fix(checkpoint): precise mode-mismatch HTTP mapping, gate E2E, and accessor resilience
- threads router: map CheckpointModeMismatchError to 409 (with cause and
thread id) and CheckpointModeReconfigurationError to 503 across all state
endpoints instead of swallowing both into a generic 500
- gate coverage: seed a real delta checkpoint into AsyncSqliteSaver and
assert aget/aupdate/ahistory fail closed; assert 409 at the HTTP boundary
through the real route stack
- rollback: compile the restore mutation graph with the thread's effective
state schema per the build_state_mutation_graph contract
- inheritance contract locks: rollback and manual compaction preserve
middleware-contributed channels via checkpoint fork cloning
- services: revalidate the accessor-graph cache against app_config identity
so config.yaml hot-reloads never serve a stale compiled graph
- services: degrade full-mode state reads to raw checkpointer reads when the
agent factory is unavailable (delta gate still applies; delta mode has no
fallback)
- deps: override websockets==16.0 (langgraph-sdk 0.4.2's <16 pin silently
downgraded 16.0 -> 15.0.1; pin is not grounded in any API incompatibility)
and bump the langchain lower bound to what the lockfile actually resolves
* fix(checkpoint): include anchor checkpoint in degraded history walk + cover get_thread
- _RawCheckpointReadAccessor.ahistory: alist(before=...) is exclusive while
pregel's get_state_history treats config.checkpoint_id as the inclusive
start; fetch the anchor explicitly so both read paths paginate identically
- extend the degraded-path gateway test: GET /thread returns raw values, and
POST /history with before starts at the anchor checkpoint
* fix(gateway): preserve degraded checkpoint timestamps
* fix(gateway): harden degraded checkpoint access
* fix(gateway): resolve assistants for checkpoint reads
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
The /help string was hardcoded and had drifted from BUILTIN_COMMANDS,
omitting six real commands (help, switch, resume, uploads, artifacts,
details) and ordering the rest differently from the picker. Generate the
command line from the registry so /help can never fall out of sync again,
and add parity tests that guard against future drift.
