243 Commits

Author SHA1 Message Date
ChengLong GU
524f60494f
fix(scheduler): scrub credentials in IM notice text (#8250)
* fix(scheduler): scrub credentials in IM notice text

URL user info and Authorization/Cookie header values carried no secret-like key, so the egress scrubber forwarded them verbatim to third-party IM platforms. Redact the credential itself, keeping the scheme and surrounding sentence readable.

* docs(changelog): record the IM notice credential scrub

* fix(scheduler): redact quoted and multi-pair header credentials

A canonical Cookie header carries one name=value pair per segment, so stopping at the first semicolon left the session cookie in the notice; a quoted Authorization value hid the scheme behind the quote, so only the word Bearer was replaced. The Cookie value is now redacted through the end of the line, and the Authorization pattern accepts an optional quote pair around the scheme and value.

* fix(scheduler): redact signature fields and comma-joined tokens

A SigV4 Authorization value carries its HMAC as a Signature= field after the scheme token, and a comma-joined bearer list stopped at the comma, so both reached the notice. Signature joins the keyword list, and the header value now runs through commas.

* fix(scheduler): redact digest credentials and scrub blocks first

* docs(scheduler): describe end-of-line credential redaction
2026-11-18 14:17:52 +08:00
ChengLong GU
35d33bea75
fix(frontend): treat invalid cron fields as non-scheduled (#8020)
* fix(frontend): keep invalid cron schedules as custom

* test(frontend): cover inclusive cron bounds

* docs(scheduled-tasks): note cron preset bounds

The form keeps an out-of-range cron as custom; the guide now says which
numeric ranges a preset covers and that saving such an expression returns
422. CHANGELOG entries cover the fix.

* docs(scheduler): clarify invalid cron save validation

---------

Co-authored-by: Nan Gao <thunderggnn@gmail.com>
2026-11-14 16:36:25 +08:00
ChengLong GU
c263b887b5
fix(scheduler):修复单个定时任务派发异常中断整批执行 (#8047)
* fix(scheduler): isolate queued run drain failures

* fix(scheduler): isolate queue timeout rows

* fix(scheduler): enforce queue timeout at launch claim

Keep expired queued occurrences ineligible to start when the timeout sweep fails. Cover per-row and whole-scan cleanup failures with SQLite service tests that also verify healthy queued and due work still launches.

* fix(scheduler): exclude expired rows from queue selection

Filter rows past the queue deadline before owner ranking and the fair batch limit so failed timeout cleanup cannot starve healthy waiting work. Keep the atomic claim cutoff as the final launch guard.

---------

Co-authored-by: AochenShen99 <sac1063467113@hotmail.com>
Co-authored-by: Nan Gao <thunderggnn@gmail.com>
2026-11-13 18:46:11 +08:00
Wang guanyu
b16e197618
fix(models): close Codex async HTTP requests on cancellation (#8053)
* fix(models): close Codex async HTTP requests on cancellation

* test(models): isolate loopback cancellation checks from proxies

* docs: record Codex cancellation fix in changelog

* docs: translate Codex cancellation changelog entry

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Claude Code <noreply@anthropic.com>
2026-11-12 21:55:08 +08:00
Hyeonsang Cho
8853e68638
fix(gateway): keep server-owned checkpoint keys out of client thread metadata (#8019)
* fix(gateway): keep LangGraph checkpoint keys out of client thread metadata

POST /api/threads spread client metadata over the root checkpoint's
step/source/writes/parents. A non-mapping parents broke every history
read and a non-integer step broke every later turn, leaving deletion as
the only way out. Server values now come after the client's.

* docs(changelog): reference #8019 for thread-create checkpoint metadata

* fix(gateway): keep server-owned checkpoint keys out of client thread metadata

The root checkpoint still copied client keys the server reads back as
trusted. A non-mapping counters_since_delta_snapshot failed every state
update and turn in both checkpoint modes, and deerflow_agent_name was
copied into the next state rewrite as the server-authored agent binding.
Drop a named set of checkpoint-owned keys before the spread so the fix no
longer relies on dict ordering alone.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-12 20:53:04 +08:00
kongxin
53c5195e5d
fix(gateway): name the agent problem when run admission rejects agent_name (#8087)
* fix(gateway): name the agent problem when run admission rejects agent_name

Since #5238, run admission loads the named custom agent's config for
every run, with or without a knowledge scope, and folded every failure
into "knowledge_scope assistant configuration could not be resolved".
Messaging a chat whose custom agent was deleted, or passing a malformed
agent_name, pointed callers at the knowledge base instead of the agent.

The 422 status is unchanged; the detail now says which problem it is:
- Agent '<name>' not found
- Invalid agent_name '<value>': must contain only letters, digits, and
  hyphens after normalization. (shared with custom_agent_name(), which
  gains a field= argument; existing callers keep the default)
- Invalid agent_name: expected a string, got <type>.
- Agent '<name>' configuration could not be loaded

* docs(changelog): reference #8087 for the run admission agent_name detail

* fix(gateway): bound the agent name echoed in run admission errors

Address review on #8087: admission now echoes the caller's raw
agent_name, which start_run merges from config/context without a size
check, so an oversized value was reflected verbatim into the 422 detail
and any log line that records it. Cap the echoed name at 200 characters
in the invalid-name message (shared with assistant_id validation) and in
the not-found / unreadable-config messages.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-12 19:34:10 +08:00
coder-abu
7d45fea17e
fix(models): keep the OAuth betas when a Claude request sends its own betas (#8061)
* fix(models): keep the OAuth betas when a Claude request sends its own betas

ClaudeChatModel put the Claude Code OAuth betas (oauth-2025-04-20, ...)
only in the client's default anthropic-beta header. A request whose
payload carries betas is sent through beta.messages.create, and the
Anthropic SDK turns that list into a per-request anthropic-beta header
that replaces the default. So a configured betas list (even []),
per-call betas, or a server tool for which langchain-anthropic appends a
beta sent the request without oauth-2025-04-20, and Anthropic rejects
the Bearer token.

_get_request_payload now puts the OAuth betas first in any request betas
list before the thinking budget resolves the header. Requests without
betas keep the default header, and API-key models are unchanged. The
list is rebuilt because the payload's betas can be self.betas.

Fixes #8060

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* docs(changelog): link the Claude OAuth betas fix to #8061

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(models): keep the OAuth betas in a caller's anthropic-beta extra header

The Anthropic SDK lets a request's extra_headers override both the
client default and the header built from betas. An anthropic-beta in
extra_headers, from model_kwargs or passed per call, therefore still
dropped the OAuth betas and Anthropic rejected the Bearer token.

_apply_oauth_betas now gives that header the same merge as betas: the
OAuth betas go first and the caller's betas follow without repeats.
The headers dict is copied because it can be the one in model_kwargs.
API-key models are unchanged.

Refs #8060

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: AochenShen99 <sac1063467113@hotmail.com>
2026-11-12 18:29:48 +08:00
Zeren Wang
95514245e2
chore(checkpoint): require fixed DeltaChannel replay backends (#8139)
* chore(checkpoint): require fixed DeltaChannel replay backends

* fix(checkpoint): correct Postgres floor and refresh docs

* test(checkpoint): update Postgres dependency floor assertion

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-12 17:49:41 +08:00
mosifu
51cc489c8f
fix(wecom): raise the image upload cap to the platform's 10 MB (#8174)
* fix(wecom): raise the image upload cap to the platform's 10 MB

`send_file` capped images at 2 MB and files at 20 MB. 2 MB is the *voice*
limit in WeCom's aibot media-upload protocol; images are allowed up to 10 MB
(developer.work.weixin.qq.com/document/path/101917). Every 2-10 MB image was
therefore dropped before upload, and the turn arrived without its chart.

Raise the image cap to 10 MB. The 512 KiB chunk size keeps a 10 MB upload at
20 chunks, well under the protocol's 100-chunk limit.

* docs(changelog): record the WeCom image-cap fix

Adds the Unreleased -> Fixed -> channels entry for #8174 to CHANGELOG.md and
CHANGELOG_zh.md.
2026-11-12 17:16:42 +08:00
mosifu
041d9e375e
fix(wecom): treat "@bot /new" in group chats as a command (#8118)
WeCom leaves the bot mention in group message text, so `_publish_ws_inbound`
handed "@RobotA /new" to `is_known_channel_command`, which requires a bare
leading slash. The turn was classified as chat and the command never ran.

Strip leading mentions for the command lookup only, mirroring Feishu (#4229)
and DingTalk (#4724): ordinary chat keeps its mentions, and the stripped form
is what reaches ChannelManager so it parses `/new`. The comment spells out that
this drops any leading mention, not only the bot's -- WeCom text mentions carry
display names, so `aibotid` cannot be matched against them.

Recorded in CHANGELOG.md / CHANGELOG_zh.md under Unreleased -> Fixed.

Fixes #8099

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-12 08:01:39 +08:00
Wenchao An
3d826c6d95
feat(approvals): add Ask, Auto and Full tool permission modes (#8033)
* feat(hitl): add human-in-the-loop approval for high-risk tool calls

* fix(hitl): address approval review findings

* docs(hitl): keep agent guidance under size limit

* fix(hitl): guard approval pause recovery

* docs(hitl): shrink inherited guidance

* fix(hitl): harden approval admission and recovery

* fix(approvals): address review safety and reconciliation gaps

* ci: retry approval checks after runner timeout

---------

Co-authored-by: wangzeren <1004695029@qq.com>
2026-11-11 20:59:05 +08:00
Hyeonsang Cho
c8d5c108f3
fix(frontend): copy share links on the current origin (#8126)
* fix(frontend): copy share links on the current origin

The sidebar Share action rewrote the origin to the hosted demo
(https://deer-flow-v2.vercel.app) whenever the page ran on localhost or
127.0.0.1, which are the default make dev and Docker entry points. The
copied link never opened the thread, because the thread only exists on
the local deployment, and opening it sent the thread id (and a custom
agent name) to a host the operator does not control.

Always build the link from window.location.origin and pathOfThread().

* docs(changelog): reference #8126 for the share link origin fix
2026-11-11 13:06:19 +08:00
Hyeonsang Cho
8850f8eb7e
fix(runtime): keep assembly evidence from reviving a run a peer reclaimed (#8046)
* fix(runtime): keep assembly evidence from reviving a run a peer reclaimed

In heartbeat mode every run-row write is conditional on this worker's
live lease except assembly evidence, which went through RunStore.put().
That upsert rewrote status, owner, lease, error and stop_reason from the
local record. When a peer had already reclaimed the run, it put the row
back to running and erased the takeover error. If the owner's local lease
was still live, its renewal then succeeded, the peer never reclaimed it
again, and the run finished as success after the peer had published its
terminal recovery event. If the write landed late, the row came back with
an expired lease and was reclaimed a second time.

Add RunStore.merge_owned_metadata(), which merges metadata keys only for
the owner holding a live lease on a pending/running row and writes no
other field. SQL follows the existing clock -> row lock -> conditional
UPDATE order; MemoryRunStore mirrors it. With heartbeat enabled,
record_assembly_evidence() uses it, refuses a locally fenced run before
any write, fences the run when the store rejects the merge, and fails
closed on stores without the method instead of falling back to put().
Single-worker mode keeps the full snapshot.

* docs(changelog): reference #8046 for the assembly evidence takeover fix

* test(runtime): scope the simulated lease expiry to the run's thread

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-11 07:56:53 +08:00
kongxin
f17e0504d0
fix(feedback): return 409 instead of 500 when feedback is POSTed twice (#8064)
* fix(feedback): return 409 instead of 500 when feedback is POSTed twice

POST /api/threads/{id}/runs/{rid}/feedback did a plain INSERT. A second
POST by the same user for the same run (a retry, or feedback on another
message of that run) hit uq_feedback_thread_run_user and the uncaught
IntegrityError surfaced as HTTP 500.

FeedbackRepository.create now rolls back and raises
FeedbackAlreadyExistsError on that collision, and the route maps it to
409 pointing callers at PUT, which already upserts.

* fix(feedback): only map the run/user unique key to 409; cover concurrent POSTs

Address review on #8064:
- create() now re-reads the (thread, run, user) row after an
  IntegrityError and raises FeedbackAlreadyExistsError only when it
  exists; any other violation (e.g. a feedback_id collision) propagates.
- Add a commit-barrier test where two first POSTs race: one 200, one
  409, and the winner's row is kept.
- Add CHANGELOG.md / CHANGELOG_zh.md Fixed entries.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-10 07:47:01 +08:00
ZephyrWang
f746da3a4c
fix(agents): count model calls independently of reused message IDs (#8050)
* fix(agents): count model calls independently of reused message IDs

* docs(agents): clarify budget accounting and changelog

* docs: avoid concurrent changelog insertion conflicts

* docs(agents): condense TokenBudgetMiddleware guidance to fit chain budget
2026-11-10 07:31:47 +08:00
yetuge
0dc423605a
fix(browserless): resolve the token through the shared credential rule (#8043)
* fix(browserless): resolve the token through the shared credential rule

Browserless read BROWSERLESS_TOKEN and the configured token raw, so a value
from a file kept its trailing newline and became the auth query parameter;
every request then failed authentication. A whitespace-only value was sent as
a token instead of counting as unset. Use provider_credentials.resolve_api_key
like the other search and fetch providers, with the blank-config fallback to
the environment.

* fix(browserless): keep an explicit blank token opt-out

An explicitly configured token ("" or null) is authoritative: a self-hosted
capture endpoint uses it to opt out of authentication, and falling back to
BROWSERLESS_TOKEN sent the cloud credential to that endpoint. Only an omitted
token key falls back to the environment. Regression tests cover the client
token and the outgoing capture query.

* docs(changelog): record the browserless token normalization

Match the sibling #7981 entry in both locales; the fix closes out the
credential-rule family for the bundled search and fetch providers.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-10 05:59:16 +08:00
Hyeonsang Cho
7bb92cea10
fix(threads): keep the owner row when deleting checkpoints fails (#7992)
* fix(threads): keep the owner row when deleting checkpoints fails

DELETE /api/threads/{id} treated the checkpoint delete as best-effort: a
failure was logged at DEBUG, the threads_meta row was removed anyway and
the request returned success. Read routes allow a thread without a meta
row as an untracked legacy thread, so the surviving checkpoints (title,
messages, goal) became readable by every signed-in user through
GET /threads/{id}, /state, /history and /goal, and the owner could not
retry because DELETE requires the row.

A failed checkpoint delete now logs the exception and returns a generic
500 before the meta row is touched, so the thread stays owned and the
owner can retry. The remaining cleanup steps stay best-effort; their
reads are owner-scoped.

* docs(changelog): reference #7992 for the thread delete checkpoint fix

* fix(threads): require checkpoint deletion before dropping ownership

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-09 11:53:56 +08:00
Zeren Wang
0d04322d41
feat(hitl): add human-in-the-loop approval for high-risk tool calls (#7979)
* feat(hitl): add human-in-the-loop approval for high-risk tool calls

* fix(hitl): address approval review findings

* docs(hitl): keep agent guidance under size limit

* fix(hitl): guard approval pause recovery

* docs(hitl): shrink inherited guidance

* fix(hitl): harden approval admission and recovery
2026-11-09 09:52:35 +08:00
Hyeonsang Cho
955524a510
fix(middleware): scan PII emails in linear time (#8006)
* fix(middleware): scan PII emails in linear time

The email detector's pattern restarts at every position inside a
whitespace-free run and consumes the rest of the run before failing to
find '@', so a scan is quadratic in the run length. PiiRedactionMiddleware
re-redacts every user message on every model call, on the event loop, so
one pasted 100 KB hex dump stalled the Gateway for ~6 s per model call.

Scan from run starts only (a local part must reach the end of its run),
and match anchored where the previous match ended so glued addresses
such as 'a@b.cc+c@d.org' keep both matches, exactly as before.

* docs(changelog): reference #8006 for the linear PII email scan

* fix(middleware): group the embedded email pattern and pin every detector's linearity

Wrap the pattern behind the run-start lookbehind in a group so a future
top-level alternative in _EMAIL_PATTERN cannot escape the lookbehind, and
add one whitespace-free payload per other detector to the linearity test
so the AGENTS.md rule is enforced for all of them.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-08 22:09:02 +08:00
Hyeonsang Cho
8924c5844a
fix(scheduler): pause a task whose schedule no longer computes (#7993)
* fix(scheduler): pause a task whose schedule no longer computes

Admission validates every schedule, but a stored one can stop computing
later: a zone the installed tz database no longer has, or a cron
expression a newer croniter rejects. The scheduler recomputes next_run_at
inside the shared poll, and that raise escaped:

- dispatch_task recomputed it in its except block after a successful
  launch, so run_once aborted the claimed batch and left the occurrence
  in "launching" with no last_error;
- once the launch lease expired, recover_expired_launch_claims found the
  durable run and raised again for every poll, before claim_due_tasks,
  so no other scheduled task was admitted for the rest of the process.

Runtime cursor writes (launch, launch repair, queue timeout, launch
failure, finalization) now use stored_next_run_at, which returns the
reason instead of raising. A live recurring task is paused with
"schedule can no longer be computed: ..." as its last_error and no next
run; a once task keeps its normal outcome. Resume re-validates the
schedule, so it reports the problem until the schedule is fixed.

run_once also isolates the lease-recovery pass, like the terminal-run
reconciliation next to it, so a failed pass no longer skips admission.

* docs(changelog): reference #7993 for the unschedulable task fix
2026-11-08 13:39:34 +08:00
Eilen Shin
2a8927c5e1
feat(models): add StepFun provider preset (#7988)
* feat(models): add StepFun provider preset

* fix(models): standardize the StepFun preset label

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-08 09:49:43 +08:00
Hyeonsang Cho
6c94ecc6cb
fix(community): strip provider API keys before they reach a header (#7981)
* fix(community): strip provider API keys before they reach a header

GroundRoute (from GROUNDROUTE_API_KEY), InfoQuest, Tavily, Exa, Jina,
Firecrawl, fastCRW and Crawl4AI put the configured or environment key into
an HTTP header as read. A key read from a file keeps its trailing newline
(a Kubernetes Secret created with --from-file and mounted through envFrom),
and the transport refuses it with an error that quotes the whole header:
h11's "Illegal header value b'Bearer <key>\n'" or requests' "... in header
value: '<key>\n'". The providers returned that message as the tool result,
so the key reached the model and the checkpointed conversation, and
GroundRoute, InfoQuest, Jina and Crawl4AI also wrote it to the error log.

Resolve each key through provider_credentials.resolve_api_key, as the other
bundled providers already strip theirs. Tavily, Exa and Firecrawl now read
their environment fallback themselves instead of leaving it to the SDK,
which would read the raw value again. A blank configured key now falls back
to the environment, as it already does for GroundRoute and the stripping
providers.

* docs(changelog): reference #7981 for the provider API key fix

* fix(community): keep fastCRW from sending the Firecrawl key

fastCRW builds the Firecrawl SDK client, and the SDK reads
FIRECRAWL_API_KEY whenever api_key is None. Once a blank configured key
resolved to None, a fastCRW config with api_key: "" and no CRW_API_KEY sent
the Firecrawl key to the fastCRW endpoint. With no api_key configured at
all, main already did the same.

Pass "" when fastCRW resolves no key of its own; the SDK falls back only on
None and sends no Authorization header for an empty key. A loopback test
pins the empty, blank and absent cases with FIRECRAWL_API_KEY set.

* fix(community): keep a blank environment key away from the SDKs

Tavily, Exa and Firecrawl resolved their environment fallback themselves,
but passed None when it was blank, and each SDK then re-read the same
variable unstripped. Tavily and Firecrawl now pass "", which the SDKs
treat as a missing key; Exa sends "" as is, so it fails before any
request instead.

The fastCRW comment records that only the Firecrawl SDK's v2 client
honours "", and the fastCRW regression test now covers web_fetch as well
as web_search, so a move to the v1 client would fail it.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-08 08:44:56 +08:00
Hyeonsang Cho
4e90f5d771
fix(docker): keep local config out of the image build context (#7958)
* fix(docker): keep local config out of the image build context

backend/Dockerfile copies the backend tree wholesale (COPY backend ./backend),
and frontend/Dockerfile does the same for frontend/. .dockerignore excluded
.env files and runtime data, but not the local configuration: config.yaml,
the config.yaml.bak that make config-upgrade writes beside it,
extensions_config.json and legacy mcp_config.json. The config resolvers still
read these from the legacy backend/ location, so on a checkout that keeps them
there every locally built gateway image (dev and prod) carried the model API
keys and MCP credentials in its layers, under the file Compose mounts over at
runtime. frontend/.env.local, the documented place for BETTER_AUTH_SECRET in
local development, was copied into the frontend image the same way, where
next build and next start also read it.

Exclude those files at the root and in backend/, and .env*.local at any depth.
None has tracked content; the build's file list is otherwise unchanged.

* docs(changelog): reference #7958 for the Docker build-context fix

* fix(docker): keep local HTTPS keys and snapshot credentials out of images

frontend/.gitignore also ignores *.pem, the mkcert key pair for local HTTPS,
and COPY frontend ./frontend shipped it into the dev and prod frontend images.
Exclude frontend/*.pem.

The trailing !backend/extensions/sources/** re-inclusion wins over every
earlier rule, so a hand-edited extension snapshot could still carry .env files
or keys into the gateway image. Exclude, after the re-inclusion, exactly the
files the extension manager already refuses to snapshot; a test pins that set
to the manager's own _SENSITIVE_FILENAMES and _SENSITIVE_SUFFIXES.

The test's matcher now translates patterns as Docker does (** across segments,
* within one, character classes, parent-directory matches), so it can model
the mid-path ** rules; its predictions agree with BuildKit on every test path.

The README and changelog now say that a locally built frontend image no longer
inlines NEXT_PUBLIC_* values from frontend/.env.local.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-08 07:56:27 +08:00
golemon
372baf762f
fix(agent): prevent todo reminders from resuming runs after hard stops (#7955)
* fix(agent): stop todo reminders after run hard limits

Respect loop_capped and token_capped before scheduling completion reminders, and include the behavior in the assembly policy fingerprint.

Cover sync and async agent graphs, blocked post-stop tools, preserved Todo state, and continuation from the same thread checkpoint. Validation: 316 targeted tests passed.

* docs(agent): explain todo behavior after hard stops

Document that loop and token hard stops suppress Todo completion reminders while retaining unfinished tasks for later runs.

* docs(changelog): record todo hard-stop fix

Add English and Chinese Unreleased entries referencing issue #7953.

* fix(agent): mark safety stops with partial responses

* fix(agent): honor provider stops before todo retries

* docs(agent): clarify todo behavior after provider stops

* test(agent): isolate todo safety-chain runtime dependencies

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Totoro <msy626836554@gmail.com>
2026-11-07 21:43:16 +08:00
Hyeonsang Cho
d658b13c79
fix(channels): keep Feishu cards within the card size limit (#7798)
* fix(channels): keep Feishu cards within the card size limit

Card text was unbounded and ASCII-escaped, so an answer of about 4,400 CJK
characters made the card request body exceed Feishu's 30 KB limit (230025).
The final patch and its reply fallback were both rejected, the answer was
lost and the running card stayed on its last streamed text.

Cards are now serialized without ASCII escapes and budgeted by the bytes
their text adds to the request body. A streamed update shows what fits; a
longer final answer continues in up to 10 cards replied to the same source
message, split at line breaks, and a retry resumes after the cards already
delivered.

* docs(changelog): reference #7798 for the Feishu card size fix

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-07 15:52:59 +08:00
Hyeonsang Cho
61d76d9a6a
fix(channels): key WeCom group conversations by chatid, not the sender (#7794)
* fix(channels): key WeCom group conversations by chatid, not the sender

Group messages used the sender's userid as chat_id and topic_id, the same
key as the sender's private chat. Wherever no group connection kept them
apart (auth-disabled mode, require_bound_identity: false, legacy group
bindings), a member's private chat and every group they wrote in ran in one
DeerFlow thread. Groups are now keyed by chatid with one thread per member.
A group-scoped connection carries its sender-keyed thread over once; a
legacy binding, which spans every group of the bot, does not.

* docs(changelog): reference #7794 for the WeCom group conversation fix

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-06 21:36:19 +08:00
Qiu
7f9e0bf611
fix(sandbox): defer fresh AIO skill-policy acquisition (#7782)
* fix(sandbox): defer fresh AIO skill-policy acquisition

Prepare the authorized thread skill view before the model runs without
acquiring an AIO container for a fresh lazy run. Keep existing sandbox
bindings and upload-based providers on the eager rebind/sync path.

Add sync/async regressions for first-tool authorization, strict rebinding,
filtered read-only AIO mounts, and policy-scoped warm reuse.

AI assistance: Codex; the account owner confirmed human review of the
complete seven-file patch and responsibility for the change.

* docs(sandbox): keep lazy-isolation guidance within inherited budget

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-05 15:37:13 +08:00
Totoro
593ba49458
feat(subagents): continue requested batch work and schedule explicit prerequisites (#7839)
* feat(subagents): continue native batches and honor item dependencies

* docs: link native batch follow-up changelog entries

* test(migrations): pin isolated history-seed upgrade to 0050

* fix(subagents): preserve follow-up scope, blockers and fair scheduling

* test(memory): freeze capacity evaluation time

* fix(subagents): guard follow-up admission and retain run controls

* fix(subagents): enforce runs:cancel on tool cancellation of follow-up batches

* style(tests): format test_batch_followup_host with ruff

* fix(subagents): drop the admission checkpoint check and keep SDK cancel compatible

The checkpoint check inside run admission waited on the checkpoint saver's
lock while holding the SQLite write lock, which could make another chat's
checkpoint write fail. Remove it; dispatch still checks the conversation
before admission.

A follow-up waiting for an unanswered question now keeps its claim until the
lease expires instead of rereading the conversation every poll. Cancel passes
the caller's run authority only to submitters that take it, so existing SDK
submitters keep the two-argument call. Document that retrying a prerequisite
by hand does not requeue its blocked items, and list 0052 as the migration head.

---------

Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-05 15:10:21 +08:00
golemon
5371343f69
fix(gateway): continue dispatching queued inputs after cancellation (#7746)
* fix(gateway): continue queued inputs after cancellation

* docs(runtime): clarify queued input cancellation handling

* fix(gateway): clarify cancelled-input error and log race-window skips

* docs(changelog): document queued input cancellation fix

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-04 10:39:20 +08:00
Nan Gao
1dd6d05627
fix(extensions): hand compaction observers the live task store and name the task in CompactionEvent (#7831)
* feat(extension-api): add task identity fields to CompactionEvent (0.2.10)

CompactionEvent carried the transform, its hashes and its counts, but
nothing that names the task, run or thread the compaction happened in.
An observer that wants to relate a compaction to the run that produced it
had to match hashes across sessions, which is unreliable.

Append three optional fields, task_id, run_id and thread_id (str | None,
default None). Existing keyword and positional construction is unchanged,
so already-released extensions keep working. The host fills them in the
next commit.

Bump deerflow-extension-api to 0.2.10 and the harness's exact pin with it.

* fix(extensions): hand compaction observers the live task store and its identity

The summarization middleware already recovers the live task store from
the runtime to observe its summary system call, and the registry
allocates that store precisely because a compaction observer is
registered. notify_context_compacted() then discarded it and handed every
observer a detached store, with a docstring claiming there was no live
task.

- The lead run worker and the subagent executor now seed every task store
  they allocate with the task's TaskInfo, not only when a lifecycle
  contributor is registered; the lifecycle notification reuses the seeded
  object. A subagent without a parent run_id still gets no TaskInfo.
- compact_state() and acompact_state() pass the store from
  task_store_from_runtime() to _record_compaction().
- notify_context_compacted() takes an optional task_store. A live store
  goes to the observers and fills the event's task_id/run_id/thread_id
  from its TaskInfo; without one (manual /compact runs outside any run)
  observers still receive a detached store and the ids stay None.

For a background subagent the store keeps its public scope id (the
provider tool_call_id) while TaskInfo.task_id stays the execution id, as
lifecycle contributors already see it; the event follows TaskInfo.

* docs(extensions): document compaction event identity and seeded TaskInfo

The extensions guide and the developer manual still said compaction
observers always receive a detached store because no task is live at the
call site. Describe what the host does now: lead runs and subagents with a
parent run seed every task store with TaskInfo, compaction observers get
the live store, and CompactionEvent's task_id/run_id/thread_id come from
it; only manual /compact falls back to a detached store with None ids.
Adds the 0.2.10 row to the contract version table (PR number pending).

* docs(changelog): note compaction observers receive the live task identity

* docs(extensions): list compaction observers among task-store triggers

* docs: reference #7831 for the compaction event identity change

* docs(extensions): backfill contract history rows 0.2.5 to 0.2.9

The version table jumped from 0.2.4 to 0.2.10 although 0.2.5-0.2.9
shipped. Add those rows, attributing names merged without a bump to
the first release that carried them (#5796 in 0.2.5, #6920 and #5645
in 0.2.8, #7729 in 0.2.10). The page intro now says it documents
0.2.4 plus the 0.2.10 CompactionEvent fields, and points to the
history for the rest.
2026-11-03 15:06:52 +08:00
Hyeonsang Cho
2c8892c810
fix(channels): deliver the DingTalk reply when an AI card request fails (#7781)
* fix(channels): deliver the DingTalk reply when an AI card request fails

dingtalk-stream's AICardReplier logs a failed card request and returns
as if it succeeded; its create call returns the card ID it generated
before the request. The channel stored that ID, so neither the running
reply's text fallback nor send()'s sampleMarkdown fallback could run,
every streamed update failed silently, and the final answer never
reached DingTalk.

Send createAndDeliver and the streaming update through the channel's
httpx client with its token, using the bodies the SDK sends, and raise
on HTTP and transport failures so both fallbacks run. The SDK replier,
its per-card map and the token shim it needed are removed.

* docs(changelog): reference #7781 for the DingTalk AI card fallback

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-02 10:34:03 +08:00
Hyeonsang Cho
7fd0c0cb3e
fix(harness): keep a cancelled batch cancelled when retrying a failed item (#7792)
* fix(harness): keep a cancelled batch cancelled when retrying a failed item

retry_item only kept a paused batch as it was, so retrying a failed item
of a cancelled batch reset the batch to queued and the worker claimed and
ran the item. A cancelled batch now rejects the retry (409), re-checked
under the write lock because SQLite ignores FOR UPDATE, and the workspace
no longer offers Retry there.

* docs(changelog): reference #7792 for the cancelled batch retry fix
2026-11-02 10:05:05 +08:00
Hyeonsang Cho
17b05718e0
fix(agents): store an explicit null description as empty (#7638)
* fix(agents): store an explicit null description as empty

PUT /api/agents/{name} accepted "description": null and wrote it into the
agent's config, but AgentConfig.description is a str. Every later load of
that agent failed validation: the PUT itself, GET and repair PUTs returned
500, the file backend dropped the agent from the list, and the db backend
failed the owner's whole list.

Store an explicit null as the empty default, and have parse_agent_config
read a stored null description (already written by this route, or a bare
YAML key) as empty so affected agents load again.

* docs(changelog): reference #7638 for the agent null description fix

* docs(agents): document that a null description resets it to empty

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-01 23:34:59 +08:00
Totoro
a17e5694cc
fix(sandbox): stop owned command processes when a run is cancelled (#7772)
* fix(sandbox): stop owned command processes when a run is cancelled

* fix(sandbox): handle incomplete AIO output responses

---------

Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-01 23:09:25 +08:00
Hyeonsang Cho
9a49fb2bb3
fix(clarification): keep each question when a provider reuses a call ID (#7762)
* fix(clarification): keep each question when a provider reuses a call ID

The clarification ToolMessage ID, which is also the human-input
request_id, was clarification:{tool_call_id}. Providers that number
calls per response reuse call_0 across turns, so a later question took
the earlier one's ID: add_messages replaced the earlier question in
place and left the new call without a result.

Add a digest of the issuing AIMessage ID. A retry of the same call comes
from the same AIMessage and keeps its ID; without that message in state
the ID keeps its previous form.

* docs(changelog): reference #7762 for the clarification call ID fix
2026-11-01 12:41:34 +08:00
Hyeonsang Cho
eb5d1e1880
fix(projects): keep referenced originals when the trash sweep walks a symlinked tree (#7732)
* fix(projects): keep referenced originals when the trash sweep walks a symlinked tree

The storage reconciliation protects each row's namespace by its resolved
path (project_document_path resolves symlinks) but walked the unresolved
documents directory. With a symlinked .deer-flow (no DEER_FLOW_HOME),
users/, users/{id}/ or projects/, no walked directory matched a protected
namespace, so the startup sweep and the lazy trash-listing sweep unlinked
live document originals older than 24 hours as orphans.

Walk each project's resolved documents directory so both sides compare
the same paths.

* docs(changelog): reference #7732 for the trash sweep symlink fix

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-31 19:16:50 +08:00
Totoro
44e372dd7f
feat(runtime): support Queue and Steer during active Web runs (#7729)
* feat(runtime): add Queue and Steer for active Web runs

* style(frontend): format Queue and Steer controls

* fix(runtime): retain user Steer controls and order active inputs

* docs: add Chinese changelog entry for Queue and Steer

---------

Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-31 11:35:36 +08:00
Dragon ze
5d2749b05b
fix(gateway): read the live config off the loop for thread token usage (#7727)
* fix(gateway): read the live config off the loop for thread token usage

build_context_usage resolves the model capacity through deps.get_config,
which revalidates config.yaml and extensions_config.json on every call, so
each /threads/{id}/token-usage request paid that file IO on the shared
Gateway loop.

* docs(changelog): record the thread token-usage config read move

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-31 08:28:01 +08:00
Hyeonsang Cho
8062d4ba12
fix(scripts): include nginx logs in dev_multi_instance.sh logs all (#7723)
* fix(scripts): include nginx logs in dev_multi_instance.sh logs all

`logs all` selected only the two Gateway logs, the same as running
`logs` with no argument, so nginx's error and access logs never showed
up although the help lists all next to nginx. `all` now adds the nginx
logs, and the nginx selection also covers nginx.log, where the start
command's own output goes and which no option printed before.

* docs(changelog): reference #7723 for the dev_multi_instance logs fix

* test(scripts): pin dev_multi_instance logs when nginx never started

Cover the layout start_nginx leaves behind when it bails on a missing
binary or a busy port: only gateway-*.log exists, so `logs all` prints
the two Gateway files and `logs nginx` prints nothing, both exiting 0.
2026-10-30 21:48:31 +08:00
Hyeonsang Cho
b4b2a68ee5
fix(memory): mask backend secrets in the memory config responses (#7665)
* fix(memory): mask backend secrets in the memory config responses

GET /api/memory/config and /api/memory/status returned
memory.backend_config as loaded. Config loading has already resolved
$VAR references by then, so a DeerMem extraction model api_key or a
Honcho api_key reached every caller with memory:read in plaintext,
which with authorization disabled (the default) is every signed-in
user.

MemoryConfigResponse now masks credential-named values (api_key,
*_token, password, authorization, ...) at any depth as "***". The
key is matched on its end, so knobs such as token_counting and
guaranteed_token_budget and the api_key_env variable name stay
readable, and unset values stay null or empty. The loaded config the
backend uses is not changed.

* docs(changelog): reference #7665 for the memory config secret masking fix

* refactor(gateway): share config secret masking between MCP and memory

The memory config masking forked the MCP router's key normalization
and recursive masker. Both now use app/gateway/secret_masking.py, and
each router keeps its own key rule: MCP matches credential terms
anywhere in the key, memory matches them at the end and keeps unset
values. MCP masking is unchanged.

The memory rule now also covers plural and cookie keys (api_keys,
secrets, passwords, cookies). Plural tokens stays out because
max_injection_tokens is a DeerMem knob. A secret-named container is
still masked whole, since its keys can be arbitrary names; the helper
docstring and a test now say so.

* docs(changelog): move the #7665 entry to Unreleased
2026-10-30 14:53:33 +08:00
lihongyuan99
9e7448cabd
fix(changelog): define the missing [#7022] reference link (#7710)
Both change logs mention [#7022] in the workflow-turn-cap entry but neither
defines it, so the released page renders the literal text "[#7022]" next to a
working link for the fixing PR. #7022 is an issue, not a pull request, so the
definition targets issues/7022.

Add an offline guard for the whole class: every [#n] reference token needs a
definition, and every definition must aim at the same number in this repository
(commit permalinks, as used for deleted PRs, stay allowed).
2026-10-30 08:40:00 +08:00
Willem Jiang
b3f23326a5
Moved to the 2.2.3 developement (#7697) 2026-10-29 22:02:49 +08:00
leom1919
dedb154e4c
docs(changelog): replace links to deleted PRs with permalinks to their commits (#7689)
* docs(changelog): replace links to deleted PRs with permalinks to their commits

* docs(changelog): fix remaining deleted #6304 reference

---------

Co-authored-by: leom1919 <leom1919@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-29 21:55:52 +08:00
Willem Jiang
b537d9c16c
chore(changelog): sync the change log information of 2.2.0 (#7663)
* chore(changelog): Sync the change log information of 2.2.0

* chore(changelog): update the change log information of 2.2.0

* chore(changelog): sync the change log information of 2.2.0

* Add entry for pull request #7585 in CHANGELOG_zh.md
2026-10-29 11:44:50 +08:00
Tsai Yuan
966aa9496a
fix(benchmark): validate sandbox timing options (#7651)
* fix(benchmark): validate sandbox timing options

* fix(benchmark): guard infinite idle reaping

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-28 20:47:59 +08:00
Hyeonsang Cho
f6a8f076ed
fix(tui): show picker labels as written instead of parsing markup (#7631)
* fix(tui): show picker labels as written instead of parsing markup

SelectScreen passed thread titles and model display names to Textual as
plain str, which Textual parses as content markup. A thread title such as
'Fix [/bold] in parser' raised MarkupError and exited the app whenever
/threads opened, and '[a]' vanished from the list. Wrap the title and
option labels in Rich Text so they render literally.

* docs(changelog): reference #7631 for the TUI picker markup fix

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-28 20:23:31 +08:00
Hyeonsang Cho
48949482c5
fix(channels): give DingTalk AI cards the channel token, not the SDK fetch (#7597)
* fix(channels): give DingTalk AI cards the channel token, not the SDK fetch

AICardReplier's async card calls read dingtalk_client.get_access_token()
inline, and dingtalk-stream refreshes it with requests.post and no
timeout. Card creation and card streaming both run on the Gateway loop,
so the first card and every SDK refresh after it (about every two hours)
blocked the loop for the whole token request, without bound if DingTalk
stalled.

Hand the replier a _CardTokenClient that serves the channel's own
httpx token (10s timeout), set before card creation and before every
streamed update. A token failure while streaming now raises into send's
existing sampleMarkdown fallback instead of being skipped silently.

Pin it with a strict blocking-I/O anchor over a real DingTalkStreamClient
and AICardReplier, a gate meta-check, and unit tests for token rotation
and failure. LocalHttpServer also records each request's method, path
and headers.

* docs(changelog): reference #7597 for the DingTalk AI card token fetch

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-28 10:50:30 +08:00
Tsai Yuan
54a09c467e
fix(readability): cache unavailable Node extraction (#7617)
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-28 07:33:41 +08:00
Hyeonsang Cho
fb553747d1
fix(scripts): read the checkout .env as data in serve.sh (#7606)
* fix(scripts): read the checkout .env as data in serve.sh

serve.sh sourced the root .env under set -a, so bash ran it as a script:
$$ became the shell's PID, backticks and $(...) ran commands, and an
unquoted value with a space ran its second word as a command (exit 127
under set -e, stopping make dev). The exports also beat the Gateway's
own load_dotenv(override=False), so e.g. a $$ in AUTH_JWT_SECRET changed
the signing secret on every launch.

Parse .env with a stdlib-only scripts/dotenv_exports.py on the host
Python and eval its shell-quoted export lines. It tokenizes like
python-dotenv, so values match what the Gateway reads, and keeps the
launcher's precedence over inherited variables and its $NAME /
${NAME:-x} / leading-~ expansion that support_bundle.py mirrors. $$ is
now one token in both. Unparseable lines and invalid names are skipped
with warnings that never echo values; a non-UTF-8 file stops the
launcher.

Tests run serve.sh's real .env block: no execution, parity with
python-dotenv, precedence, warnings, the non-UTF-8 stop and a stdlib-only
run; the support-bundle launcher cases now exercise the parser.

* docs(changelog): reference #7606 for serve.sh reading .env as data

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-27 22:19:33 +08:00
Hyeonsang Cho
77d0fc9d69
fix(channels): resolve reply artifacts off the event loop (#7594)
* fix(channels): resolve reply artifacts off the event loop

_handle_chat_on_thread and _handle_streaming_chat called
_prepare_artifact_delivery inline. For every presented file it resolves
the virtual path (realpath), resolves the outputs root, and checks the
file with is_file and stat, all on the Gateway loop that also serves
every other channel and request.

Run it through asyncio.to_thread on both reply paths, and anchor both
through the real manager under the strict blocking-I/O gate.

* docs(changelog): reference #7594 for the off-loop reply artifact resolution

* docs(changelog): drop the duplicate #7580 link definition in the zh changelog

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-27 14:55:19 +08:00