116 Commits

Author SHA1 Message Date
yong
8547666a31
feat(search): add DeepSeek web search with configurable thinking (#8299)
* feat(search): add DeepSeek web search with configurable thinking

* fix(search): drain DeepSeek teardown and retain citation spans

Reuse the cancellation-safe context helper so repeated cancellation cannot interrupt HTTP transport cleanup. Preserve validated Unicode citation ranges on retained public sources so the agent can associate claims with their supporting pages. Add regressions for cancellation, timeout, normal completion, invalid ranges, URL screening, and result limits.

* fix(search): preserve DeepSeek citation excerpts through guardrails

* fix(search): share DeepSeek citation excerpts across sources

Group each validated answer range once and associate it with response-local source IDs after URL filtering and result limits. Preserve full-answer PII redaction and existing source-card fields, document the model-facing citation mapping, and repair live-test configuration for both thinking modes. Add HTTP transport, guardrail/budget, attribution, and browser reload regressions.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-18 21:19:41 +08:00
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
30bef100w
32dafbe2fe
feat(acp): add Pi coding agent configuration (#8293)
* feat(acp): add Pi coding agent configuration

* fix(acp): address Pi configuration review feedback

* docs(acp): document Pi prerequisites and isolation

* docs(acp): use Pi interactive login in setup examples

---------

Co-authored-by: 30bef100w <30bef100w@users.noreply.github.com>
Co-authored-by: 30bef100w <314075793+30bef100w@users.noreply.github.com>
2026-11-18 11:49:44 +08:00
yi-coding
c2b29f118d
fix(skills): preserve existing images on Gemini decode errors (#8256)
* fix(skills): preserve images on Gemini decode failures

* docs(skills): document legacy MiniMax output handling

---------

Co-authored-by: xiaoyi <xyi74976-del@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-17 16:43:05 +08:00
Wenchao An
c87e238ddd
feat(artifacts): quote and rewrite selected passages (#8212)
* feat(artifacts): quote and rewrite selected passages

* fix(artifacts): verify rewrite spans and clear discarded edits

* fix(artifacts): require explicit rewrite submission in side chat

* fix(artifacts): honor cleared rewrite references on all origins

* docs(artifacts): remove committed selection screenshots

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-17 16:41:29 +08:00
ordinary being
39788402ec
fix(scheduler): fence late launch bookkeeping by claim generation (#8268)
* fix(scheduler): fence late launch bookkeeping by claim generation

An expired launch claim can be requeued and immediately reclaimed by the same scheduler process. Because requeue_claimed_run and fail_launching_run only matched status == launching and the lease owner, the original attempt's late busy-thread requeue or launch failure could still clear the fresh claim's lease and release its global execution-budget slot. Another queued occurrence could then claim that slot while the fresh launch was still in flight.

attempt_count already increments on every claim. Capture it from claim_queued_run and pass it to both slot-releasing writes, which now match on the generation as well. The lease-owner check remains; a stale attempt becomes a no-op, while the current generation can still release its own claim. The fence is optional so legacy/custom repositories that do not expose attempt_count keep the previous behavior.

Tests: a SQLite/Postgres repository test recovers an expired claim, reclaims it with the same owner, then replays the stale requeue and failure and asserts the fresh row plus its global slot survive. Service tests pin that the claim attempt is passed on both the busy-thread and pre-launch-failure paths.

* fix(scheduler): log lost requeue claims after a newer generation wins

The busy-thread requeue path discarded requeue_claimed_run()'s boolean, so a generation-guard rejection was indistinguishable from a normal requeue in logs while the attempt no longer owned the occurrence. Capture the result and emit the same lost-launch-claim warning used by the failure path; add a regression test that simulates a newer claim winning.

* docs(scheduler): keep persistence guidance within its soft limit

Compress the generation-fence note so the shared persistence AGENTS.md chain stays below the soft size limit.

* fix(scheduler): omit generation kwarg for legacy claim repos

Both late-bookkeeping calls passed expected_attempt_count=None even when the claim had no generation. Custom repositories that still implement the pre-fence signatures reject that keyword with TypeError. Build the kwargs conditionally so the argument is only sent when the claim actually carries a generation; add a legacy repo regression for both the busy-requeue and pre-launch-failure paths.

---------

Co-authored-by: Tong-bit-art <Tong-bit-art@users.noreply.github.com>
2026-11-17 10:36:27 +08:00
MasterZRC
d59738649f
fix(frontend): isolate background task cancellation reads (#7903)
* fix(frontend): fence background task cancellation cache

Cancel the exact list and target-detail reads before publishing confirmed cancellation state. Forward AbortSignals and refresh only the list, preserving sibling detail loads.

Cover delayed reads after panel close, initial detail loads, cancellation failures, and request isolation with real QueryClient/HTTP regressions.

Fixes #7177

AI-assisted with OpenAI Codex.

* test(frontend): cover cancellation before initial task list loads

Address PR #7903 review by covering the uncached-list case through cancellation, stale-response settlement, and the next enabled refresh. Document the single-argument fetch contract and capitalize the polling guidance.

* chore: remove background task screenshots from PR
2026-11-17 10:10:29 +08:00
Aurora_
c5d072af91
feat(subagents): add optional SQLite checkpoint history (#8265)
* feat(subagents): add optional SQLite checkpoint history

* docs(subagents): clarify checkpoint history limits

* fix(subagents): resolve checkpoint factory at startup

---------

Co-authored-by: Nan Gao <thunderggnn@gmail.com>
2026-11-16 13:29:26 +08:00
yi-coding
f582b9a87b
fix(skills): read legacy XLS workbooks with an XLS-capable engine (#8215)
* fix(skills): read legacy XLS workbooks with an XLS-capable engine

* fix(skills): keep legacy XLS analysis independent of spatial

* fix(skills): skip unreadable legacy workbooks

* fix(skills): preserve mixed cell types in legacy XLS

---------

Co-authored-by: xiaoyi <xyi74976-del@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-14 22:04:58 +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
Wenchao An
4f3a8b790d
feat(sharing): add revocable read-only conversation snapshots (#8211)
* feat(sharing): add revocable read-only conversation snapshots

* fix(sharing): preserve fork idempotency and allow snapshot cleanup
2026-11-14 12:22:22 +08:00
Wenchao An
dba950443d
feat(search): find conversations and jump to matching messages (#8032)
* feat(search): find conversations and jump to matching messages

* test(extensions): align example registry with search contribution

* test(search): scope bookmark search to its extension

* fix(search): address review correctness and scaling gaps
2026-11-13 23:01:38 +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
Loveca
067c9736b6
feat(goal): add /goal from-chat for IM channels (#8200)
* feat(goal): add /goal from-chat for IM channels

First slice of #7050: add an explicit IM command that composes the active goal
from the recent conversation instead of taking the text literally.
Natural-language intent detection remains out of scope.

Gateway:
- POST /api/threads/{thread_id}/goal/from-chat synthesizes the objective
  from the thread summary and recent agreement turns (visible user/assistant
  text, clarification questions, and card answers), preserving agreed
  constraints and the stopping condition.
- Reject a busy thread before the model call; the save reuses the existing
  checkpoint-write reservation so a run that starts mid-synthesis still wins.
- Refuse to synthesize while a human-input request is unanswered, and return
  structured no_context/unclear/synthesis_failed outcomes without echoing
  model-generated reasons.

IM:
- /goal from-chat [hint] shows the saved objective, then starts exactly one
  run through the ordinary chat path; a longer read timeout covers synthesis.
- Map busy/pending/unclear/no-context/timeout outcomes to localized replies;
  a saved goal whose run cannot start is reported honestly.
- The TUI explains that from-chat is not supported yet; the web input box
  still treats it literally (documented follow-up).

Docs: README, CHANGELOG, IM channel guide, TUI guide, AGENTS, and the
acceptance plan/execution record. Tests: new route, synthesis and manager
suites, plus parser and TUI coverage.

* fix(goal): keep the from-chat confirmation visible on every channel

The saved-objective reply was published as a non-final progress update.
QQ and DingTalk card mode drop non-final outbounds before a stream exists,
and Feishu/Telegram fold the update into the run's stream, so the run
output overwrote the objective. Publish it as the turn's final message.

Redact PII on whole lines and the summary before the context budget can
split an identifier; the composed prompt is still redacted once more as
defense in depth, matching the goal evaluator's direct call.

Also correct the gateway/IM docs (from-chat never creates a checkpoint,
the busy pre-check is worker-local, and synthesis uses the deployment
default model), fix the route test clock patch, and add regression tests
for the final-outbound and truncation-boundary cases.

* fix(goal): align from-chat with the goal-route admission gates

Reject a from-chat save while a tool approval is pending, matching
PUT/DELETE /goal, and suppress subagent-batch continuations queued under
the previous goal after the save. Both invariants landed upstream while
this branch was in review; the new route now shares them.

Add route tests for both behaviors.

* docs(changelog): remove the from-chat entry to avoid conflicts

The maintainer asked to drop the changelog entry because the section conflicts with upstream changes. The feature remains documented in the goals guide and README.

* fix(goal): close three review gaps in /goal from-chat

- Enforce model-use authorization for the deployment default model before
  the synthesis call, matching the suggestions route, so a denied role
  never sends conversation context to the model.
- Save with expected_checkpoint_id pinned to the head the synthesis read;
  a write that landed during the model call is a 409 goal_changed instead
  of silently clobbering the newer goal.
- Re-check the conversation binding before starting the run: a /new during
  synthesis keeps the goal in the original thread and reports that the
  task did not start instead of running it in the switched conversation.

* fix(goal): preserve from-chat handoff and run status

Pin the saved thread through run preparation and reject a changed binding.
Read configuration and model authorization off the event loop, and report
rejected starts separately from requests whose response was lost.

Cover the handoff races and streaming/wait admission outcomes through the
real channel manager and SDK transport, plus file-backed config under the
strict blocking-I/O detector.

Co-authored-by: Loveca <44801706+Loveca@users.noreply.github.com>

* fix(goal): preserve reasoning tags in synthesis JSON

Use the existing JSON-aware reasoning stripper so literal tag text in
objective and reason values survives parsing. Cover complete and unclosed
tags while still removing model reasoning before the JSON payload.

Co-authored-by: Loveca <44801706+Loveca@users.noreply.github.com>

---------

Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
Co-authored-by: Totoro <msy626836554@gmail.com>
2026-11-13 14:22:58 +08:00
yi-coding
94447d12b6
fix(memory): preserve summaries when extraction returns invalid types (#8192)
Co-authored-by: xiaoyi <xyi74976-del@users.noreply.github.com>
2026-11-13 14:13:47 +08:00
Wistom Zhang
2ff88fbb29
feat(memory): opt-in reserved categories for DeerMem hybrid-v1 eviction (#8194)
* feat(memory): support category capacity reservation in DeerMem hybrid-v1 eviction

In long-running personal assistant interactions, core user profile facts
(such as health allergies, coding style, or identity constraints) can suffer
from capacity starvation as high-confidence conversational context accumulates.

This change introduces opt-in category capacity reservation for DeerMem:
- In DeerMemConfig and select_facts_for_capacity, support eviction_reserved_categories
  (defaulting to ['correction'] for historical compatibility) and
  eviction_decay_exempt_categories (defaulting to empty list).
- Wire MemoryUpdater to pass the configured categories to select_facts_for_capacity.
- Add deterministic offline unit tests in test_memory_personal_assistant_protection.py
  verifying root-cause reproduction, bidirectional lifecycle (clean explicit removal
  and contradiction replacement), and strict backward compatibility under defaults.

* fix(memory): preserve correction priority in reserved capacity

Co-authored-by: Wistom Zhang <77424093+Yakyou7@users.noreply.github.com>

---------

Co-authored-by: Totoro <msy626836554@gmail.com>
Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
2026-11-13 11:09:41 +08:00
Loveca
bce5dc3327
fix(feishu): receive post attachments from the top-level files array (#8190)
* fix(feishu): keep attachments sent with post messages

* fix(feishu): keep user-typed file placeholders and malformed files arrays from losing attachments

* test(feishu): pin mixed inline attachment behavior and consume the post file count

* fix(feishu): parse post commands before adding attachment placeholders

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Totoro <msy626836554@gmail.com>
2026-11-12 22:09:20 +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
Eilen Shin
81de0761ed
feat: improve file attachments and add Office artifact previews (#8009)
* feat(frontend): improve file attachment recovery and artifact presentation

* feat(extensions): add Office artifact previews with search and navigation

* fix: preserve public viewers and HTTP Office previews

* fix: address file preview and upload review findings

* fix: use typed upload errors and linear bookmark allocation

* fix(office-preview): isolate parsing and bound preview resources

* fix(ci): install Office preview fixture dependencies for E2E

* fix(ci): provision matching Playwright browsers before E2E tests

* fix(ci): isolate Python libraries and include Office documentation

* test(frontend): wait for download status to finish rendering
2026-11-12 20:30:17 +08:00
Evan
b4410f64d4
fix(agents): keep the delegation ledger exact across HITL approval and reused call ids (#8128)
* fix(agents): count each delegation once when a provider reuses its call id

Tool-call ids are unique per response, not per conversation. Some providers
number every response's calls from call_0, so two task calls in one run can
share an id.

The delegation ledger used (run_id, tool_call_id) as a delegation's identity:

- extract_delegations built one id -> entry map over the whole run, so a
  later call_0 replaced the earlier delegation's description and took its
  result while it was still running.
- merge_delegations replaced the same (run_id, id), keeping one entry.
- SubagentLimitMiddleware counted distinct ids, so the per-run cap
  (subagents.max_total_per_run) never advanced past the first call_0 and a
  run could launch any number of subagents one response at a time.

Each entry now also records dispatch_message_id, the AIMessage that issued the
call, and results pair through pair_tool_call_results, which answers a call
only from its own response. The reducer, DurableContext's change filter and
the cap use the extended identity. An entry without a dispatch id still
updates its run's entry for that call id, and a dispatch-scoped entry adopts a
ledger entry written before the field existed, so runs in flight across the
upgrade are not counted twice. The steer path names the dispatching AIMessage
from the tool request's state, so its delegation update and the graph's own
capture stay one entry.

* fix(agents): close an earlier run's dangling dispatch by its own response

_close_delegations_left_by_earlier_runs decided "answered" by
(run_id, tool_call_id). When a stopped run had dispatched call_0 twice,
the first reply kept the second, dangling entry in_progress, so the
lead kept hearing "already delegated" for work nothing would finish.

Entries that carry dispatch_message_id are now decided by pairing that
response's calls through pair_tool_call_results. Legacy entries and
dispatches no longer in history keep the id-based inference.

Also pin that two runs reusing call_0 stay two ledger entries, and
cross-reference the three delegation identity helpers.

* fix(agents): settle an approval-gated task delegation in the ledger

With `task` in `hitl_approval.tools`, the paused run records the dispatch
as in_progress and the resume run executes it. The resume run opens with
no HumanMessage, so its capture window starts after the pre-existing
messages and never contains the dispatching AIMessage: the result was
dropped and the entry stayed in_progress with no result_brief, forever.

DurableContext now pairs results the resumed window receives with the
last pre-existing dispatch and settles the issuing run's entry, keeping
its run_id instead of re-tagging it. HITL denials of `task` carry
`cancelled` subagent status, so a rejected or denied delegation settles
too.

* fix(agents): address review on the delegation ledger

- Steer path: hold each wait's dispatch AIMessage locally and pass it to
  the observer, so a later response reusing the call id while the first
  call is still observed cannot take over its args or dispatch id.
- New-turn close: a dispatch whose reply carries subagent status settles
  from that reply instead of staying in_progress, covering a crash
  between the tools checkpoint and the next capture.
- Reuse thread_state.delegation_key instead of a duplicate identity
  helper in DurableContext.
- CHANGELOG: reference #8128.

* docs(changelog): drop the #8128 entry per review
2026-11-12 19:46:58 +08:00
N
06634003a5
fix(subagents): apply tool policies to middleware-declared tools (#8136)
* fix(subagents): apply tool policies to middleware-declared tools

* fix(subagents): address tool-policy review feedback

Normalize declaration conversion errors with middleware context, document
generated discovery exemptions, and add the Unreleased changelog entry.
Audit final explicit and middleware tool sets before graph creation, with
identity-based exemptions for generated discovery helpers and regressions.

* fix(subagents): reuse tool name resolution and clarify policy errors
2026-11-12 19:12:02 +08:00
paer
2dc68b242f
fix(subagents): prevent concurrent file-backed creates from overwriting definitions (#8132)
* docs(subagents): describe create-only file publication

* fix(subagents): prevent concurrent create overwrites

* test(subagents): cover independent create races

* docs(persistence): record create-only publication

* docs(config): explain managed subagent file claims

* docs(persistence): retain create-only publication rule

* docs(subagents): retain shared file create semantics

* fix(gateway): probe managed subagent hard links on startup

* test(gateway): cover managed subagent volume probes

* test(gateway): keep volume probes off the event loop

* docs(config): describe startup hard-link warnings

* docs(changelog): reference managed subagent fix #8132

* docs(changelog): keep the fix entry clear of append conflicts
2026-11-12 14:39:25 +08:00
ZephyrWang
b80191fad3
fix(memory): reject duplicate fact IDs during import (#8151)
* fix(memory): reject duplicate fact IDs during import

* fix(memory): explain duplicate IDs in import response

* docs(changelog): link duplicate import fix PR

* fix(memory): keep duplicate validation portable

---------

Co-authored-by: AochenShen99 <sac1063467113@hotmail.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-12 11:42:55 +08:00
2SinceJuly
6eb4833598
fix(client): scope memory management to the named agent's bucket (#8146)
* fix(client): scope memory management to the named agent's bucket

A named DeerFlowClient stored and read its memory in that agent's bucket:
MemoryMiddleware and the memory tools both pass agent_name. The management
methods on the client did not, so create_memory_fact wrote the fact into the
user's default bucket while the agent's injected context came from its own
bucket — the fact was persisted but never recalled by the same client.

Pass the client's agent_name through get_memory, export_memory,
import_memory, reload_memory, clear_memory and the single-fact CRUD calls.
An unnamed client keeps the default bucket, and a backend that ignores the
scoping keyword keeps raising its own unsupported-operation error.

Fixes #8142

* fix(client): refuse named memory calls a backend cannot scope

DeerFlowClient forwarded the agent name to every memory management call, but
a backend that declares no agent-scoped storage ignores the keyword and
answers normally. A named client then reported success while the call read,
cleared or exported the user's default bucket, the same silent
wrong-bucket behaviour #8142 is about. Check the capability flag before
forwarding the scope and raise an unsupported-operation error, as the
Gateway already does with 501.

Resolve the scope in reload_memory before the get_memory fallback so an
unsupported scope is not mistaken for a backend without reload support and
retried as a user-wide read.

* chore: drop the CHANGELOG entry

The changelog is generated at release time, and the hand-written entry points
at #8146 without a link definition, which breaks
tests/test_changelog_reference_links.py. Removing it keeps the file released-
generated, per the reviewer's request.

* docs(memory): explain scoped noop client behavior

---------

Co-authored-by: 2SinceJuly <202121119+2SinceJuly@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-12 09:21:28 +08:00
Wenchao An
9699f04cdc
feat(projects): add visible project memory with extraction controls (#8117)
* feat(projects): add visible project memory with extraction controls

* fix(projects): avoid replaying committed memory extractions

* chore(ci): retrigger project memory checks

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-12 09:09:44 +08:00
SuKoYa07
fc7c7e012c
fix(frontend): restore handed-off artifacts from thread history (#8080)
* fix(frontend): restore handed-off artifacts from thread history

* fix(frontend): reject duplicate artifact handoff receipts

* docs(frontend): fit artifact guidance within budget

* fix(frontend): accept consistent retried artifact handoffs

---------

Co-authored-by: lovesky514514-cmd <273698517+lovesky514514-cmd@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-11 21:00:33 +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
zuiqiangxijiejin
c7bc8bab67
fix(docker): handle inline YAML comments in sandbox mode detection (#8103)
* fix(docker): honor inline comments on the sandbox section header

* fix(docker): match the sandbox provider value exactly

* test(docker): ignore nested provisioner URLs

* docs(docker): explain exact sandbox provider matching
2026-11-11 20:11:53 +08:00
Heo Hao
80cb6404b6
fix(browserless): reject timeouts httpx cannot use (#8025)
* fix(browserless): reject timeouts httpx cannot use

`_coerce_timeout` forwarded any int, float or numeric string to
`httpx.AsyncClient(timeout=...)` unchanged, so a configured `timeout_s: 0`
or a negative value failed every fetch and capture with `ConnectTimeout`
against a healthy backend, `nan` raised `ValueError: deadline must not be
NaN`, and `inf` left the request without a deadline so it never completed.
Each of those silently disabled the provider.

Fall back to the documented 30s default with a warning when the number is
not a usable deadline. This matches `crawl4ai._coerce_timeout` after #7481;
`jina_ai._coerce_timeout` still forwards non-positive values.

* fix(browserless): address timeout review and format tests

Explain how HTTPX handles NaN and positive infinity. Document that
Browserless accepts positive finite timeouts without an upper limit,
and pin that behavior with a 1e308 test case.

Crawl4AI and Jina timeout validation are tracked in #7481 and #7823.
Remove the Browserless docstring's claim that Crawl4AI shares its
coercion behavior. Format the test file for the backend lint check.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-11 19:43:53 +08:00
Wistom Zhang
218c64180e
feat(summarization): align built-in compaction prompt to preserve user requirements and approval conditions (#8114) (#8114)
In long-running agent workflows with repeated context compaction, empirical gateway ablations across 132 real sessions revealed that standard boundary compliance remains robust, while semantic drift can occur when model-generated summaries rephrase literal approval phrases and action conditions.

This change converges PR #8114 into a clean built-in summary prompt enhancement:
- Replaces regex extraction, tag elevation, and heuristic revocation with an extended built-in DeerFlow summary prompt (_DEERFLOW_SUMMARY_PROMPT).
- Instructs the summarizer to faithfully record active user requirements, literal approval phrases, permitted actions, and later explicit revisions without paraphrasing.
- Treats summary text strictly as historical data, fully preserving the security boundary and control/data plane separation of DurableContextMiddleware.
- Unifies automatic and manual compaction factory paths to select the built-in template when unconfigured, while preserving explicit summary_prompt precedence.
- Adds comprehensive sync/async unit tests covering built-in and custom templates.

Co-authored-by: Totoro <Totoro-qaq@users.noreply.github.com>
Co-authored-by: Totoro <msy626836554@gmail.com>
2026-11-11 19:36:32 +08:00
ZephyrWang
d9b2cb4bcb
fix(memory): require facts in replacement imports (#8131)
* fix(memory): require facts in replacement imports

* docs(memory): document import facts requirement

* docs(changelog): link memory import fix
2026-11-11 17:35:17 +08:00
Xinmin Zeng
2a97ec3e58
docs: turn README into an index and move reference detail to docs/guide (#8113)
* docs: turn README into an index and move reference detail to docs/guide

The README had grown to 393 KB because every change appended its notes there. The text moves verbatim into 18 topic guides under docs/guide/; only headings are re-leveled and relative links re-pointed. The README keeps the introduction, a quick start and a guide index. Contributor test notes move to CONTRIBUTING.md.

* docs: send user docs to topic guides and budget the root README

The rule 'update README.md for user-facing changes' is what grew the README. Guidance now points to docs/guide/, and check_agent_guidance.py fails when the root README exceeds 16 KiB (AG003).

* chore: remove unreferenced screenshots and finished plan notes

pr-build/ holds two PR screenshots (3 MB) from #1986. plans/ holds the plan for the merged #4049. docs/SKILL_NAME_CONFLICT_FIX.md is a February change note. Nothing references them.

* docs: route always-loaded AGENTS.md files to scoped guides

* docs(agents): cut scoped guides to scope, verify, traps, decisions

Each AGENTS.md keeps four kinds of content: the scope of the directory, the
verification commands, traps a local test run does not show, and decisions the
code cannot state. Values, field lists, function inventories, test names, issue
numbers and history are deleted, because the code, the tests and git state them.

Search and fetch providers share one community guide. Four guides with no
remaining content are removed. The size check now allows 6 KiB per file (hard
limit 8 KiB) and 24 KiB per chain (hard limit 32 KiB).

* style: format frontend guide table and guidance test imports

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-11 13:26:17 +08:00
Wenchao An
6fe87b65fa
feat(extensions): show package-owned usage in extension details (#8031)
* feat(extensions): show package-owned usage in extension details

* test(extensions): align bookmark checks with detail UI

* fix(extensions): reconcile package documentation and locale fallbacks

* fix(extensions): align discovery locale fallback

* fix(extensions): isolate malformed optional documentation

* docs: keep backend guidance within inherited budget
2026-11-10 18:41:27 +08:00
lilei
24884e8120
fix(task-continuity): count distinct archived search sources (#7956)
* fix(task-continuity): count distinct archived search sources

* docs(task-continuity): explain archive search ranking trade-off

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-09 09:07:20 +08:00
Wenchao An
b6ed47778d
feat(extensions): add versioned team file handoffs (#7817)
* feat(extensions): add versioned team file handoffs

* fix(extensions): fence team artifact execution and snapshots

* fix(agent-teams): retain resumed keys and bound artifact transfers

* ci: reclaim runner space before sandbox image smoke

* ci: budget sandbox image preparation separately

* fix(extensions): version artifact contracts and document snapshots
2026-11-05 14:50:09 +08:00
王一帆
d0ec8dcc5d
feat(knowledge): add optional ingestion and status center (#7518)
* feat(knowledge): add optional ingestion and status center

* docs(knowledge): record upstream CI budget fix and regression results

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-11-02 10:42:21 +08:00
Xuehao Xu
cfe2bec371
feat(workflows): add multi-Gateway coordination and session-authorized failover (#7138)
* feat(workflows): add leased multi-Gateway coordination and fenced dispatch

* test(workflows): validate deployed failover and canonicalize config revisions

* fix(workflows): share namespace across registration and lease fencing

* fix(workflows): recover interrupted cancellation without admission caps

* fix(workflows): retain execution lease through child cleanup

* docs: trim guidance padding to fit merged instruction budget

* fix(workflows): release rejected admission slots and normalize gateway routing

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-23 23:31:43 +08:00
trent87
0d73798beb
feature(skills): keep allowed-tools as compatibility metadata (#6935)
* refactor(skills): keep allowed-tools as compatibility metadata

* docs(skills): align current guides with agent tool authority

* test(skills): simplify authority regressions and sync Korean docs
2026-10-20 19:34:28 +08:00
Ryker_Feng
d1d0958bea
feat(skills): add guarded evolution host APIs (#5645)
* feat(skills): add guarded evolution host APIs

* docs(agents): avoid growing saturated guidance chains

* fix(skills): address mutation host review findings

* fix(skills): order name fence before projection lock

* fix(skills): preserve composite toggle lock order

* fix(skills): address catalog and pagination review feedback

* docs: keep subagent guidance within merged instruction budget

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-18 21:17:02 +08:00
Totoro
eae908c00d
fix(sandbox): make failed AIO teardown safely retryable (#7001)
* fix(sandbox): make failed AIO teardown safely retryable

* docs(sandbox): add sanitized teardown retry verification

* fix(sandbox): clear stale teardown fence on warm reclaim

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-18 09:57:12 +08:00
Xuehao Xu
169002a4c9
feat(workflows): add Phase 2 approvals, immutable artifacts and configuration evidence (#6920)
* feat(workflows): add versioned approvals and run configuration evidence

* docs: trim repeated setup guidance to respect inherited size limit

* docs: leave room in inherited agent guidance

* test(channels): align Buzz capability expectation with upstream registry

* fix(workflows): fence file consumers and preserve review access

* fix(runtime): reuse assembly evidence key at run admission
2026-10-17 09:41:15 +08:00
Totoro
517a8309a2
feat(extensions): allow ModelTool plugins to return structured artifacts (#6861)
* test(plugins): capture opt-in artifact RED (18 failed, 13 passed)

* feat(plugins): add typed opt-in artifacts (31 ToolNode tests pass)

* test(extensions): require API 0.2.6 (version RED verified)

* build(extensions): pin API 0.2.6 (installed wheel guards GREEN)

* test(examples): verify plugin artifacts through checkpoint restart

* test(extensions): reproduce artifact key coercion (8 RED cases)

* fix(extensions): reject non-string artifact keys (185 tests GREEN)

* fix(frontend): list bundled retrieval example in extension catalog

* test(mcp): reconcile recovered notification at stored due time

---------

Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
2026-10-14 17:24:32 +08:00
Totoro
5ae95e6a34
feat: add Feishu group notifications and fix mention caret placement (#6762)
* feat(feishu): deliver scheduled-task notifications to bound users

* feat: add Feishu group notifications and fix mention caret placement

* fix(frontend): preserve group targets while capabilities load

---------

Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
2026-10-13 07:17:56 +08:00
Yeager0204
782fed9135
feat(skills): show YAML load errors for owned custom skills (#6623)
* feat(skills): show YAML load errors for owned custom skills

* docs: capture skill diagnostics with real gateway validation

* fix(skills): clarify YAML diagnostic scope

* docs: remove PR evidence directory

---------

Co-authored-by: kwsYeager <331533331+kwsYegar@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-11 12:52:48 +08:00
ZJPex
7e0e3013d0
feat: return hit-centered history search excerpts with source offsets (#6008)
* feat: return history search excerpts near keyword matches

* docs: use English for history search guidance and comments

* docs: sync Chinese history search excerpt contract

* docs: clarify history excerpt fallback for oversized matches

* fix(history): skip oversized occurrences when selecting excerpts

Continue scanning casefolded substring matches until an occurrence fits the 600-character excerpt, including overlaps. Cover later fitting hits through synchronous and asynchronous active/archive search and read tools, and update the documented contract.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-10 21:24:21 +08:00
Hyeonsang Cho
f8b419ab38
fix(scripts): bind local make dev and make start to loopback (#6587)
* fix(scripts): bind local make dev and make start to loopback

serve.sh and backend/Makefile started the Gateway with --host 0.0.0.0,
nginx.local.conf listened on every interface, and Next.js kept its
all-interfaces default outside Windows, so a local stack on a LAN or VPN
exposed ports 2026, 8001 and 3000, including /setup before the first
admin existed. The Docker stack and the README already document a
loopback-only default.

Bind the Gateway and frontend to 127.0.0.1 and keep nginx on loopback
unless BIND_HOST is set, the variable the Docker stack already honors.
nginx-local-conf.sh renders a copy listening on BIND_HOST, and serve.sh
resolves it before stopping anything so an invalid value cannot tear
down a running stack.

* docs(changelog): reference #6587

* docs(changelog): separate the loopback entry from the next bullet

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-10 15:47:30 +08:00
Hyeonsang Cho
db9b0b4bf0
fix(release): reject a stale backend/uv.lock in the version gate (#6588)
* fix(release): reject a stale backend/uv.lock in the version gate

verify_versions.sh compared only Chart.yaml, pyproject.toml and
package.json, so bumping those three by hand passed the v* gate while
backend/uv.lock still recorded the previous root package version. The
backend image installs with uv sync --locked, so the chart and the other
images published while the backend image failed to build.

Run uv lock --check in backend/ as part of the gate, letting uv own the
PEP 440 normalization, and fail when uv is missing. The reusable
verify-versions workflow installs the uv version the backend image pins.

* docs(changelog): reference #6588

* fix(release): explain an unparsed lock version and stop blaming the lock for every uv failure

Print a fallback when the lock's root entry is not found, so the job log
does not show an empty field, and word the uv lock --check annotation so a
network error or uv crash is not reported as a stale lock.
2026-10-10 14:05:35 +08:00
hataa
3e5bd081db
feat(authz): construction-enforced async decision batches (ActivationDecisions) (#6508)
* feat(authz): construction-enforced async decision batches (ActivationDecisions)

The follow-up promised in the #4541 review threads. Four review rounds
traced four instances of one failure family: an async execution path
whose decision-map miss silently fell back to the synchronous
authorize() from a worker thread — the wrong API for loop-affine
providers, and under fail_closed:false a provider error there flips a
denial into an allow. The carrier was a plain dict|None held together by
caller discipline.

ActivationDecisions (deerflow/authz/activation_decisions.py) makes the
contract construction-enforced:
- a covered name returns the batched decision (unchanged semantics);
- a MISS resolves per the configured provider-error policy (fail-closed
  denies, fail-open allows) with a loud WARNING — a miss is a
  prepass/consumer divergence, a construction bug, not a policy
  question — and never touches a provider;
- None remains the sync-chain signal (synchronous authorize() is correct
  there);
- an empty candidate set still yields an empty BATCH, not None, so an
  unexpected consumer name fails per policy instead of silently taking
  the sync path;
- get_or_none lets publishers distinguish 'uncovered' from False;
- fail_closed travels with the batch from the resolved authorization
  context.

Both middlewares (_activation_allowed in SkillActivationMiddleware and
SkillToolPolicyMiddleware) migrate to the type; their collectors return
batches; the render-decision publisher adapts. Tests 65->70+5: type unit
tests (covered/miss both directions with loud-log assertions/
get_or_none/container), middleware-level miss semantics (fail-open
allows with provider.sync_calls == [], production-default fail-closed
denies, None sync chain still synchronous), and mutation M18 (restoring
the miss's sync fallback) verified red. 252 tests green on the affected
surface.

* docs(authz): sync every decision-batch contract description to the new miss semantics

Review round 1 on #6508 — all documentation-level: the docstrings still
described the miss-as-synchronous-fallback contract this PR removes.

- _activation_allowed (both middlewares): a covered name returns the
  batched decision; a miss resolves per the carried provider-error policy
  with a WARNING and never touches a provider; None (sync chain /
  disabled) is the only synchronous case.
- _collect_activation_decisions / _resolve_policy_registry /
  _active_skills_for_paths: the reason not to diverge is now a
  policy-resolved miss (denied under the production fail-closed default;
  allowed without any provider consult under fail-open; logged loudly),
  not a silent sync fallback.
- The two _REGISTRY_LOAD_FAILED sentinel comments, same rewording.
- Drop unused tmp_path/monkeypatch fixtures from the two new miss tests.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-09 16:09:17 +08:00
Wenchao An
beaae22088
feat(extensions): add host-bound Agent run control (#6190)
* feat(extensions): add host-bound Agent run control

* fix(extensions): preserve internal launches and scope run control

* docs(extensions): use a plugin-local run operation key
2026-10-03 21:16:01 +08:00
Wenchao An
59b051b0fd
feat(frontend): support extension providers in composer mentions (#6189)
* feat(frontend): support extension providers in composer mentions

* fix(mentions): retain settled plugin suggestions during search

* fix(extensions): validate identifiers and skip empty mention searches

* test: stabilize history pagination after latest page refresh

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-03 20:30:23 +08:00