1875 Commits

Author SHA1 Message Date
quifox
420b39ed90
fix(acp): apply invocation timeout to initialization and session creation (#6292)
* fix(acp): apply invocation timeout to initialization and session creation

* fix(acp): preserve SDK timeout errors before the invocation deadline
2026-10-05 14:39:59 +08:00
NanPan
8237dd75b3
fix(boxlite): keep private-loop shutdown retryable (#6283)
* fix(boxlite): keep private-loop shutdown retryable

* test(boxlite): cover private-loop shutdown retry

* docs(sandbox): pin BoxLite loop shutdown ownership

* fix(ci): format BoxLite shutdown changes and trim guidance

* fix(boxlite): drain acquisitions before shutdown teardown

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-05 13:38:17 +08:00
Hyeonsang Cho
52046aa82e
fix(projects): convert shelf documents outside the SQLite write lock (#6305)
* fix(projects): convert shelf documents outside the SQLite write lock

Lazy conversion ran pymupdf/markitdown inside the BEGIN IMMEDIATE
transaction that serializes the derived/converted.md publish against
trash and purge. On SQLite that lock is database-wide, so every unrelated
writer (run status, thread metadata, the scheduler) waited for the whole
conversion and failed with "database is locked" past busy_timeout (30s).

Conversion now writes into .staging/ outside any transaction. The
document row lock is taken only to revalidate the live row and atomically
rename the output into place (publish_under_live_lock, renamed from
convert_under_live_lock); a row trashed or purged meanwhile discards the
staged output, so nothing is published after purge. A read-only probe
skips converting rows that are already gone, a failed conversion is
still revalidated so a purged row reports content_missing, and the
conversion is drained on cancellation so its staging file is always
removed.

* docs(changelog): reference #6305 in the shelf conversion lock entry

* fix(projects): share one conversion across concurrent first reads

A first-read conversion holds a bounded file-IO pool thread for its
whole duration. With the conversion moved out of the row lock,
concurrent first reads of one document each converted on their own
thread, so a burst of reads could starve unrelated offloaded file work.

Route the conversion through a single-flight keyed by (user, document,
project): the first reader leads and the rest wait on its result
without holding a pool thread. The map holds concurrent.futures.Future
values under a threading.Lock because the read tool also runs on the
isolated subagent loop. Followers wait through asyncio.shield, so a
cancelled follower cannot cancel the shared future, and a leader that
is cancelled or raises hands the work to a follower instead of failing
it.
2026-10-05 13:34:19 +08:00
siye566
e8f1e269e5
fix(uploads): exclude punctuated numeric columns from document outlines (#6266)
* fix(uploads): exclude punctuated numeric columns from outlines

* fix(uploads): filter currency and later numeric outline columns

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-05 13:20:00 +08:00
sxh
ef76f085a3
fix(skills): stop reporting an env path, shebang or flag as an env dump (#6297)
* fix(skills): stop reporting an env path, shebang or flag as an env dump

* fix(skills): report shell env dumps only at a command position

`shell-env-dump` matched the word `env` anywhere it was not preceded by a path, dot, dash or word character, so ordinary argument text (`echo env`) and comment text (`# env`, `# export -p`) were still reported as environment dumps. Anchor the match to a shell command position -- the start of a line or right after a `;`, `&`, `|`, `(`, `)` or `{` separator, optionally behind `NAME=value` assignment prefixes -- and add regression cases for argument and comment text.

* fix(skills): ignore an env dump inside a comment or heredoc body

`shell-env-dump` matches `env`, `printenv` and `export -p` at a command
position, but the text it sees is still raw shell. A `;` inside a comment
(`# documentation; env is only an example`) and a bare `env` line inside
heredoc data both sit at a command position on paper while the shell runs
neither, so both were reported as environment dumps.

Reduce the text to shell code before matching: a quote-aware pass strips
comments (only a `#` at a word start opens one) and blanks heredoc bodies,
covering `<<-` tab stripping and quoted delimiters, while keeping one output
line per input line so reported line numbers stay correct. Real commands
after a separator (`true; env`) and on the line that opens a heredoc
(`env <<EOF`) still report.

* fix(skills): report env dumps after a keyword and stop masking ${#...}

The command-position anchor for `shell-env-dump` accepted only a line start or a
`;`, `&`, `|`, `(`, `)` or `{` separator, so real dumps were dropped: after a
reserved word that introduces a command (`if true; then env; fi`,
`while true; do printenv; done`), after `exec` (`exec env`) and inside a backtick
substitution (``V=`env` ``). Accept those positions too, with a guard so a path
component (`./then env`) does not arm the anchor, and add the backtick to the
separator set.

A `{` directly before a `#` is not a word start -- bash reads `${#HOME}` as the
length operator and `}#` as part of a word, while a brace group needs the space
of `{ # ...`. The comment heuristic no longer treats `{` and `}` as comment
openers, so `n=${#HOME}; env` keeps its `; env` and is reported again, while
`${env}` (a variable read, not a command) stays silent.

---------

Co-authored-by: sxh313 <sxh313@users.noreply.github.com>
2026-10-05 12:25:41 +08:00
Daoyuan Li
49dcd49f91
fix(agents): keep malformed todo statuses recoverable (#6299)
* fix(agents): keep malformed todo statuses recoverable

* docs(agents): fit todo guidance within inherited size limit

* docs(agents): clarify todo attribution guidance

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-05 12:21:39 +08:00
siye566
335c383147
fix(paths): reject Windows console device aliases (#6279) 2026-10-05 10:25:51 +08:00
Hyeonsang Cho
c540399a5e
fix(gateway): scope per-run reads to the run's data identity (#6282)
* fix(gateway): scope per-run message and event reads to the run's data identity

start_run stamps run-event rows with the raw trusted owner id, but
GET /runs/{rid}/messages and /runs/{rid}/events called the event store with
user_id=AUTO, which resolves to the internal caller's make_safe_user_id form.
On the database event store, owners whose id contains characters outside
[A-Za-z0-9_-] (IM channel ids such as "feishu:owner-777") therefore got an
empty list. The regenerate source-run scan had the same mismatch and fell
back or returned 409.

Pass _run_scope_user_id() explicitly, as the thread message routes already
do (#5448), and add user_id to RunEventStore.list_messages_by_run() so every
backend accepts it like list_messages()/list_events(). Browser and API
sessions keep their per-user filter.

* fix(gateway): scope workspace-changes and archive reads to the run's data identity

The same raw-owner mismatch reached two more run-scoped routes. On the SQL
stores, GET /runs/{rid}/workspace-changes reported no changes because its
event lookup used user_id=AUTO, and GET /runs/{rid}/artifacts/archive
answered 404 because both its run-row lookup and its run.delivery event
lookup did.

Pass _run_scope_user_id() to both, and let get_workspace_changes_response()
forward an explicit user_id to the event store.

* docs(changelog): reference #6282 in the run-scope read fix entries

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-05 10:23:55 +08:00
Hyeonsang Cho
56aa71c583
fix(runtime): keep renewing the lease while a staged terminal run finalizes (#6263)
* fix(runtime): keep renewing the lease while a staged terminal run finalizes

With an event store, run_agent stages the terminal status in memory and
commits it to the run store only after the journal flush, delivery receipt,
workspace scan and duration checkpoint. _renew_leases selected runs by local
status, so it stopped renewing as soon as the status was staged. A
finalization longer than lease_seconds + grace_seconds let a peer, or this
worker's own reconciler, claim the still-active row and record the
successful run as an orphan error.

The worker now marks RunRecord.terminal_commit_pending until the deferred
commit is attempted, and lease renewal treats it like the existing
scheduled-goal barrier: keep renewing, release on a confirmed own commit,
and fence when a peer claims the row. A fenced run stops renewing.

* docs(changelog): reference #6263 for the staged terminal lease renewal fix

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-05 07:07:04 +08:00
sxh
ee44d1ebc7
fix(skills): report secret assignments whose key is quoted (#6276)
* fix(skills): report secret assignments whose key is quoted

The line-oriented secret sweep required the credential name to be followed
directly by ':' or '=', so a JSON config ('{"api_key": "..."}') never matched
while the same binding in YAML, .env, .ini or shell did. Allow one optional
quote between the key and the separator.

* fix(skills): match secret assignments whose key has a separator prefix

The line-oriented sweep anchored the credential word with `\b`, which cannot
land after `_` because `_` is a word character. So `access_token`,
`client_secret` and `MY_API_KEY` — the common spellings in OAuth and
service-account config — matched nothing, and `_SECRET_TOKEN_PATTERNS` does
not backstop JWT- or `GOCSPX-`-style values, so such a package produced no
finding at all.

Guard the word with "not preceded by an alphanumeric" instead: a separator
(`_`, `.`, `-`) may now introduce it, while a run of letters (`tokenizer`,
`secretive`, `credentials_file`) still stays quiet.

---------

Co-authored-by: sxh313 <sxh313@users.noreply.github.com>
2026-10-04 21:15:18 +08:00
quifox
e8de7584b7
fix: include completed child usage in lead budget checks (#6218)
* fix: include completed child usage in lead budget checks

* test: require completed usage middleware in lead budget regressions

* docs: fit middleware guidance within the size budget

Condense the subagent, loop, and token budget guard descriptions while retaining their limits, lifecycle rules, and completed child usage ordering.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-04 21:14:35 +08:00
sxh
4abba38734
fix(skills): recognise eval fixture paths behind an earlier evals segment (#6271)
is_eval_fixture_path returned on the first 'evals' segment, so a path whose
'evals/fixtures/' came after a plain 'evals' segment read as a non-fixture.
Move the 'fixtures' test into the loop condition so every segment is checked.

Co-authored-by: sxh313 <sxh313@users.noreply.github.com>
2026-10-04 20:47:15 +08:00
Daoyuan Li
4dad94dcc0
fix(tui): guard conversation switching and invalid resume references (#6249)
* fix(tui): guard conversation switching and invalid resume references

* fix(tui): discard late stream actions after conversation switches

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-04 19:28:32 +08:00
Daoyuan Li
5c3329afad
fix(tui): preserve cursor and undo on unchanged history recalls (#6248)
* fix(tui): preserve composer on Up with empty history

* fix(tui): preserve cursor and undo on identical history recalls
2026-10-04 17:04:58 +08:00
Grapette.L
e7e5a5e9a3
fix(gateway): read uvicorn's WEB_CONCURRENCY in the remaining worker-count readers (#6253)
* fix(gateway): read uvicorn's WEB_CONCURRENCY in the remaining worker-count readers

* fix(gateway): name the worker spelling an operator can act on

The browser refusal and the dedupe warning both took the count but printed
GATEWAY_WORKERS, so on the launches that pass uvicorn no --workers the advice
silences the gate while the extra processes keep starting. Resolve which
variable set the count and print that, and let an unparsable GATEWAY_WORKERS
fall through to WEB_CONCURRENCY instead of reporting a single worker.

Also stop the comments from claiming the readers are equivalent: they share
the two spellings and the blank-means-unset rule, but channel_connections.py
turns an unparsable value into 0 and refuses while these stay inert.

* docs: state the single-worker requirement under both spellings

The browser tool group and the inbound dedupe warning now refuse or warn on
WEB_CONCURRENCY as well, so guidance that names only GATEWAY_WORKERS=1 is
incomplete for the shipped Dockerfile and serve.sh launches, where uvicorn
takes the process count from WEB_CONCURRENCY.

* test(features): isolate the browser capability surface from the shell's worker count

browser_capability() asks for the Gateway worker count, which this change makes
readable from WEB_CONCURRENCY, so an exported count in the invoking shell turned
test_features_reports_browser_control_enabled_when_configured_and_runtime_available
into a failure that has nothing to do with the router.
2026-10-04 16:36:01 +08:00
KennySimpson
830de11c66
fix(uploads): exclude indented bold lines from outlines (#6194)
* fix(uploads): exclude indented bold lines from outlines

* refactor(uploads): name the indented-code pattern
2026-10-04 14:54:08 +08:00
subhash7476
20bd989fc1
feat(runtime): add per-LLM-call telemetry and summarization no-op event (#6236)
* feat(runtime): add P0 per-LLM-call telemetry and summarization no-op counter

Measurement only; no runtime behavior changes.

- RunJournal enriches llm.ai.response / llm.error metadata with
  langchain_run_id, caller_category, provider, model, stop_reason, status,
  token counts and rendered request size (chars). Unavailable values are None.
- Summarization middleware emits a middleware:summarize event per summarizer
  call and counts outputs identical to the prior summary_text. The call is
  never skipped.
- All telemetry fails soft.

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

* fix(runtime): register summarize middleware tag, document telemetry contract

- Add MIDDLEWARE_SUMMARIZE_TAG to the middleware event catalog and the
  contract's known_tags; emit the middleware:summarize event with it.
- Document the optional per-call telemetry metadata on llm.ai.response and
  llm.error in contracts/run_event_stream_contract.json.
- Measure request size by walking string leaves instead of json.dumps on the
  event-loop thread.
- Initialise summarization call/no-op counters in __init__.
- Move RunJournal telemetry docs to the runtime guide.
- Add tests: llm.error without a start, replayed on_llm_end, and a DB-store
  metadata round trip.

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

* fix(runtime): refresh token counters on usage replay

---------

Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-04 14:52:04 +08:00
yetuge
23e69a0c94
fix(config): reject boolean integer settings in scheduler_config (#6258)
#6229 gave the scheduler its own integer knobs, but they accept YAML
booleans: recursion_limit: true loads as 1, so every scheduler-launched
run dies at its first LangGraph super-step - the same hole the
app-config guard already closes for Gateway runs (#6171), now on the
same-named field. max_concurrent_runs: true serializes the scheduler
and poll_interval_seconds: true polls five times a second.

Mirror the app-config boolean guard: a before-validator rejects booleans
with a field-specific error across all six integer fields, keeping
integers and numeric strings as-is. lease_seconds and
queue_timeout_seconds already reject true via their higher ge floors,
but with a misleading "should be greater than or equal to" message -
the guard gives every field the same boolean-specific error.

Signed-off-by: yetuge <2219677952@qq.com>
2026-10-04 14:42:06 +08:00
destire-mio
73a305cd87
fix(models): omit Codex tool results with blank call IDs (#6234)
* fix(models): omit Codex tool results with blank call IDs

* fix(models): validate Codex call and result IDs symmetrically

Use one strip-based validity check for assistant calls and tool results while preserving non-blank IDs verbatim. Add paired regressions for ordinary and invalid tool calls, plus non-blank correlation controls.

Validation: 126 focused tests passed; 210 blocking-I/O tests passed; backend lint and format checks passed. Paired regression fails on the previous implementation for whitespace-only IDs.

* fix(models): log dropped Codex tool results

---------

Co-authored-by: destire-mio <248462155+destire-mio@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-04 12:44:05 +08:00
yetuge
e59f6e5e92
fix(config): reject booleans for the subagent and ACP invocation backstops (#6242)
YAML booleans coerce into the ge=1 integer backstops that bound every
subagent and ACP invocation: timeout_seconds: true became 1 (the executor's
future.result(timeout=...) then killed every subagent run after one second)
and max_turns: true became 1 (the LangGraph recursion budget collapsed to a
single super-step). The ACP agent timeout mirrors subagents.timeout_seconds
and shared the hole. false was already rejected by ge=1, so only true
slipped through - silently. Mirror the app-config boolean guard: reject
bools before coercion in SubagentOverrideConfig, CustomSubagentConfig and
SubagentsAppConfig (timeout_seconds/max_turns/max_total_per_run) and
ACPAgentConfig (timeout_seconds), keeping None, integers, and numeric
strings as-is.

Signed-off-by: yetuge <2219677952@qq.com>
2026-10-04 12:41:13 +08:00
Hyeonsang Cho
1f7600e355
fix(memory): treat facts deleted during unlocked DeerMem scans as removed (#6255)
* fix(memory): treat facts deleted during unlocked DeerMem scans as removed

load(), reload(), and the full rebuild_index() scan list agent fact
files without the storage locks. A delete committed between the listing
and opening a file raised MemoryStorageCorruption for intact data, which
surfaced as HTTP 500 from the memory API and an empty memory block in
the prompt. A listed fact that no longer exists is now skipped; an entry
that is still present but unreadable is still corruption.

* docs(changelog): reference #6255 for the DeerMem vanished-fact fix

* docs(memory): note lock coverage and heuristic limits of the vanished-fact skip
2026-10-04 12:37:33 +08:00
sxh
130a9ab9f0
fix(skillscan): report secrets bound by unpacking and container or conditional literals (#6247)
* fix(skillscan): report secrets bound by unpacking and container literals

The AST walk behind secret-env-assignment claims "precision, never less
coverage", but it only read a single assignment target and a bare string
value, so a credential moved into `host, api_key = endpoint, "..."` or
into `api_key = ["..."]` stopped being reported even though the pre-#5648
line sweep still reported the same bytes.

Pair unpacking targets with values positionally (fixed head and tail only,
so a runtime-sized slice names nothing) and assert on each literal a
container or conditional holds, in source order.

* fix(skillscan): distinguish mapping labels from credentials

---------

Co-authored-by: sxh313 <sxh313@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-04 11:00:05 +08:00
Gumayusy
d9d9ff9708
fix: fence stale notification delivery claims (#6211)
* fix: fence stale notification delivery claims

* test: cover notification claim migration upgrades

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-04 10:43:05 +08:00
yetuge
0eed90df3a
refactor(config): converge the boolean guards into one shared helper (#6226)
* refactor(config): converge the boolean guards into one shared helper

Willem-bd's #6171 review follow-up: a tiny shared helper lets the next numeric field get the guard in one line and unifies the messages. Consolidates 14 validator copies across 9 config files into deerflow/config/_boolean_guards.reject_boolean(value, info, kind=...); the bare per-file messages gain their field name prefix, command_timeout keeps its distinct wording.

Signed-off-by: yetuge <2219677952@qq.com>

* refactor(config): converge stream_bridge_config and pin the guard wording

Review follow-ups on #6226: convert the last surviving per-file copy (stream_bridge_config) so deerflow/config is fully converged, make kind required keyword-only so a float field cannot silently inherit integer wording, and pin the unified field-prefixed messages with direct tests.

Signed-off-by: yetuge <2219677952@qq.com>

* test(config): cast the boolean-guard test probe to ValidationInfo

The _info probe was annotated -> object, so a type checker flags every call
site that passes its result to reject_boolean's info: ValidationInfo
parameter (runtime was fine since the helper only reads .field_name).
Return cast(ValidationInfo, _Probe(field_name)) to keep the probe honest
for both.

Signed-off-by: yetuge <2219677952@qq.com>

---------

Signed-off-by: yetuge <2219677952@qq.com>
2026-10-04 09:09:15 +08:00
Hyeonsang Cho
e3064f541b
fix(memory): sign DeerMem reload before reading the document (#6238)
* fix(memory): sign DeerMem reload before reading the document

reload() read the document before computing its cache signature, so a
write committed in between cached the old document under the new
signature and later load() calls served stale memory until the next
write. Compute the signature first, matching load().

* test(memory): cover markdown storage and agent scope in reload race test

* docs(changelog): reference #6238 for the DeerMem reload fix
2026-10-04 07:29:56 +08:00
wgwfn3
aaeed26d69
fix(uploads): drain conversion workers before source cleanup (#5999)
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-04 07:24:55 +08:00
NanPan
68dcaa6025
fix(sandbox): keep shutdown retryable while idle reaper is live (#6231)
* fix(sandbox): fail shutdown while idle reaper is live

* test(sandbox): pin live idle reaper timeout

* fix(sandbox): keep shutdown retryable after reaper timeout

* fix(sandbox): keep shutdown retryable after reaper timeout

* fix(sandbox): keep shutdown retryable after reaper timeout

* fix(sandbox): keep shutdown retryable after reaper timeout

* docs(sandbox): pin idle-reaper shutdown ownership

* fix(sandbox): keep AIO warm entries retryable

* test(sandbox): fix AIO retry regression import

* test(sandbox): cover retryable provider shutdown guards

* test(sandbox): assert warm ownership survives failed shutdown
2026-10-04 07:01:13 +08:00
Totoro
35023bb908
feat(scheduler): create conversation schedules and support agent self-stop (#6229)
* feat(scheduler): create conversation schedules and support agent self-stop

* fix(scheduler): validate goals and trial requests before dispatch

---------

Co-authored-by: Totoro-qaq <279883115+Totoro-qaq@users.noreply.github.com>
2026-10-04 06:46:13 +08:00
creed
9eb01b371a
feat(config): select an explicit backend dotenv file (#6227)
Signed-off-by: 97three <2212371308@qq.com>
2026-10-03 23:11:48 +08:00
creed
7bb3624c06
feat(serper): add configured source-domain filters (#6228)
* feat(serper): add configured source-domain filters

Signed-off-by: 97three <2212371308@qq.com>

* fix(helm): align embedded config version with example

Signed-off-by: 97three <2212371308@qq.com>

---------

Signed-off-by: 97three <2212371308@qq.com>
2026-10-03 21:58:50 +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
Daoyuan Li
9b16792168
fix(tui): preserve drafts when Down is not navigating history (#6219) 2026-10-03 16:43:17 +08:00
Guo-Yixin
7b8a7925c2
fix(config): reject invalid tool output budgets (#6172)
* fix(config): validate tool output budget limits

* fix(config): align Helm config schema version
2026-10-03 16:38:00 +08:00
Hyeonsang Cho
261279ff80
fix(lark): match broker subcommand denylist through separate option values (#6212)
* fix(lark): match broker subcommand denylist through separate option values

The opt-in DEERFLOW_LARK_BROKER_DENY_SUBCOMMANDS check dropped only
`-`-prefixed tokens and compared the rest from the start, so the value in
`--profile work config show` became the leading positional and a
`config show` rule never matched. Real lark-cli 1.0.65 runs `config show`
for that shape and for `config --profile work show`.

The broker cannot know which options take a value, so a rule now matches
when its tokens appear in order among the non-flag tokens. A contiguous
match would still miss a value placed between the path tokens. Argument
values that spell a denied path in order are refused too (fail-closed).

* docs(changelog): reference #6212 for the lark broker denylist fix

* docs(lark): call denylist entries command paths, not prefixes

Entries are matched as in-order subsequences now, so the remaining
'prefix' wording in the BrokerConfig comment, the parse_deny_subcommands
and run_lark_cli docstrings, and the broker README undersold the rule.
Also rewrap the comment and docstring lines this PR had pushed past ~80
columns.
2026-10-03 15:58:01 +08:00
lilei
741948ba9b
fix: invalidate converted uploads after same-size source edits (#6165)
* fix: invalidate converted uploads after same-size source edits

* fix: log converted upload ownership rejection reasons

* docs: clarify source timestamp limits and thread ownership
2026-10-03 14:51:05 +08:00
Xx
e1ec4c6e43
fix(sandbox): scope ignore patterns to the search root in glob/grep (#5667)
* fix(sandbox): scope ignore patterns to the search root in glob/grep

Rebuilt on top of current main so the changelog entry lands in the
Unreleased (2.2.0) Fixed section rather than the now-released 2.1.0 block.

* test(sandbox): cover the include_dirs glob branch at an ignored search root

The file.list_path branch only ran against a non-ignored tree, so a
regression there would go unnoticed. Two cases now exercise it with an
ignored root: the requested root keeps its contents, and ignored
descendants stay hidden.
2026-10-03 14:35:09 +08:00
Xuehao Xu
9b17bef630
feat(channel): add QQ WebSocket channel (#6081)
* feat: add QQ WebSocket channel

* fix: address QQ channel review feedback

* docs: trim inherited agent guidance below CI limit

* fix: align QQ gateway and passive reply limits with protocol

* docs: keep merged channel guidance within CI budget
2026-10-03 14:32:44 +08:00
yetuge
6e76c14384
fix(config): reject boolean integer settings in app_config (#6171)
* fix(config): reject boolean integer settings in app_config

Follows the loop-detection and circuit-breaker guards: YAML booleans next
to integer knobs load cleanly, and Pydantic coerces booleans to 1/0.

- recursion_limit coerced from `true` to 1, so every Gateway run that does
  not supply its own limit hit the LangGraph recursion ceiling at the
  first super-step (max_recursion_limit likewise clamped the ceiling to 1).
- The five llm_call integers coerced similarly: retry_max_attempts as
  `true` disabled retries, max_concurrent_calls as `true` serialized the
  pipeline.

All seven integer fields now fail configuration loading with a
field-specific error, while valid integers and numeric strings keep their
existing behavior. Mirrors the loop-detection helper (#6017) and the
in-file circuit-breaker validator.

Signed-off-by: yetuge <2219677952@qq.com>

* docs(changelog): record the app-config boolean rejection

Changelog entries for #6171, mirroring the #6017 entry format in both
languages.

Signed-off-by: yetuge <2219677952@qq.com>

* test(config): pin the False-side coercion regression in the boolean guards

Per review: the tests only exercised `True`. On the `ge=1` fields `false`
already failed the constraint pre-fix, but on the `ge=0` fields
(`max_concurrent_calls`, the two delay fields) `false` coerced silently to
the harmless-looking `0`, disabling the concurrency cap with no error.
Parametrize both boolean tests over `[True, False]` to lock that regression
in as well.

Signed-off-by: yetuge <2219677952@qq.com>

---------

Signed-off-by: yetuge <2219677952@qq.com>
2026-10-03 14:29:41 +08:00
Hyeonsang Cho
7f7668d975
fix(community): refuse non-global addresses in the shared SSRF guard (#6202)
* fix(community): refuse non-global addresses in the shared SSRF guard

is_blocked_address ORed is_private, is_loopback, is_link_local,
is_reserved, is_multicast and is_unspecified. None of them covers the
100.64.0.0/10 shared address space, which holds CGNAT and Tailscale
hosts and Alibaba Cloud's 100.100.100.200 instance metadata endpoint, so
web_fetch, web_capture, the agentic browser and personal MCP connections
could reach it, including through the IPv4-mapped ::ffff:100.100.100.200
form a DNS answer can carry.

Also refuse any address that is not is_global, the classification the
repo's other SSRF filters already use. Keep the existing flags alongside
it: some non-public forms still report is_global, such as the NAT64
spelling of a metadata address (64:ff9b::a9fe:a9fe) and 224.0.0.1, so an
is_global-only check would newly allow them.

* docs(changelog): reference #6202 in the shared address space entry

* test(community): pin the IPv4-mapped metadata spelling at the web_fetch and personal MCP entry points

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-03 10:29:56 +08:00
Hyeonsang Cho
bb4f7ac5e2
fix(browser): pin browser connections to the SSRF-vetted addresses (#6201)
* fix(browser): pin browser connections to the SSRF-vetted addresses

The navigate screen and the per-request guard resolve a hostname to vet
it, but Chromium resolved the name again to open the connection. A
rebinding DNS server could answer both checks with a public address and
the connection with a private or cloud-metadata one, and the browser
followed it.

Launch each private browser through a per-session loopback SOCKS5 proxy.
Over SOCKS5 Chromium sends the hostname itself, so the proxy resolves it
exactly once through the session's egress resolver and connects only to
the addresses that resolver vetted. resolve_browser_egress applies the
same allow_private_addresses policy as validate_browser_url, on top of a
new url_safety.resolve_public_addresses helper that
validate_public_http_url now shares. Loopback is proxied explicitly with
bypass "<-loopback>". The tools, navigate_and_capture and the Live
WebSocket all pass the resolver, because a thread's first caller fixes
its launch options.

CDP-attached Chrome is unchanged. Delegated fetch services (crawl4ai,
Browserless, fastcrw) still resolve on their own side, which the Gateway
cannot pin.

* docs(changelog): reference #6201 in the browser egress pinning entry

* fix(browser): bound egress proxy faults and close, and record the WebRTC gap

Review follow-ups for the pinned browser egress proxy:

- A resolver exception other than ValueError escaped the connection
  handler as an unretrieved task error. Log it with its traceback and
  reply SOCKS5 general failure (0x01), so a resolver fault stays
  distinguishable from a policy refusal (0x02).
- Bound the resolve with its own timeout. The handshake timeout did not
  cover it, so a wedged getaddrinfo held the half-open tunnel until
  Chromium gave up. A timeout replies host unreachable.
- Bound close(): Server.wait_closed() also waits for a connection whose
  handler registered after the writer sweep, which could stall session
  close and eviction for the 15 s handshake. A handler that starts after
  close now drops its connection without opening a tunnel.
- Docs said a launched browser connects "solely" through the proxy.
  WebRTC UDP does not traverse a SOCKS proxy, so AGENTS.md, README (en/zh)
  and both changelogs now scope the guarantee to TCP and name the gap.
2026-10-03 10:05:47 +08:00
siye566
3a7e160a55
fix(paths): reject superscript Windows device names (#6148) 2026-10-03 09:04:06 +08:00
TAI-YUAN GUO
a873b78950
fix(tui): preserve multiline pasted input (carries #4630 forward) (#6168)
* fix(tui): preserve multiline pasted input

The TUI composer used a single-line `Input`, so a bracketed paste
containing code, a stack trace, or multiple paragraphs kept only the
first line when submitted. The composer is now a multiline `TextArea`:
Enter still submits, Up/Down move inside the document before falling
back to input history at the first/last line, and the slash palette is
unchanged.

Originally #4630 by @felix-windsor, cherry-picked onto current main;
conflicts in app.py key gating (transcript paging keys), test imports,
and the relocated TUI docs were resolved by hand.

Fixes #4613

* fix(tui): submit multiline input unchanged and document the widgets layer

Address the review on #4630:

- Send non-command input to the agent and history exactly as typed or
  pasted. Only the empty-input check uses strip(), so leading
  indentation and trailing newlines in pasted code and stack traces
  survive. Slash commands are still trimmed so they resolve as before.
- widgets/composer.py imports Textual, so the module-layout notes in
  tui/AGENTS.md and docs/TUI.md now exempt widgets/ alongside app.py.
- Cover pressing Down on the last document line (history fallback),
  whitespace-only input, and slash commands with surrounding whitespace.

Co-authored-by: Felix <felixwindsor3344@gmail.com>
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

* fix(tui): treat soft-wrapped rows as composer navigation boundaries

TextArea soft-wraps long lines, and its Up/Down move between the wrapped
rows of one logical line. The history fallback only looked at logical
rows, so Up from the second visual row of a long prompt recalled history
instead of moving the cursor, and Down from its first visual row could
replace the draft with history's empty value.

Use the TextArea navigator's first/last wrapped-row checks for the
boundaries, and cover wrapped prompts in both directions. Also restore a
tui/AGENTS.md sentence about PageUp/PageDown to the app.py entry it
belongs to.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Felix <felixwindsor3344@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-10-03 08:29:29 +08:00
siye566
f11be0a7bc
fix(sandbox): pin utf-8 decoding on the local sandbox backend's subprocess calls (#5905)
* fix(sandbox): pin utf-8 decoding on the local sandbox backend's subprocess calls

The local container backend shells out to docker / the container runtime
with text-mode subprocess calls that do not pass an encoding, so output is
decoded with the platform's preferred encoding. On hosts whose ANSI code
page is not UTF-8 (cp936 Chinese Windows, cp1252 Western European), any
non-ASCII byte in the CLI output raises inside subprocess's reader thread:
stdout/stderr come back None, the JSON-parsing call sites then crash on
None or silently mis-parse, and stderr diagnostics are dropped.

Pin encoding="utf-8" with errors="replace" on every text-mode call in
the module. The container CLIs write UTF-8 on every platform; replace
keeps the parseable portion of any non-conforming output alive instead of
discarding it wholesale.

* test(sandbox): validate UTF-8 subprocess settings per call

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-03 08:27:54 +08:00
Carl Calaquian
9e3589bb96
fix(tenki): upgrade sdk and preserve timeout failures (#6162)
* fix(tenki): upgrade sdk and preserve timeout failures

* fix(tenki): tolerate noisy warm-pool health probes

* docs(tenki): compact sandbox guidance within chain budget

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-03 08:19:14 +08:00
Grapette.L
8cd7aef578
fix(community): normalize max_results before handing it to Firecrawl and fastCRW (#6175)
* fix(community): normalize max_results before handing it to Firecrawl and fastCRW

* test(community): pin the explicit-null max_results shape

The parametrized `omitted` case reused None as its "key absent" marker, so
`extra["max_results"] = configured` never ran for None and the key-present,
value-null YAML shape never reached _coerce_max_results. Use a distinct
sentinel for absence and add an explicit-null case per provider.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-02 23:49:22 +08:00
Zeren Wang
19b7590333
feat(typesafe): make the risk-gate eval rubric-calibratable and its policy reproducible (#6179)
* feat(typesafe): expose instructions/criteria overrides in the risk-gate eval

The pre-enablement evaluation could not answer the question an operator
actually asks when the gates fail: is the miss/false-block a model limit or
a rubric limit? --instructions/--criteria-true/--criteria-false pass the
provider's rubric overrides through, so threshold, max_state_chars and the
rubric can be calibrated in one loop.

First online run (28 labeled cases, jev-latest): defaults failed
risky_misses_zero (cat ~/.aws/credentials at p=0.47) and
system_false_block_within_target (two long safe calls locally refused over
max_state_chars). With threshold 0.4, max_state_chars 8000 and a
criteria.false clarifying that long-but-fully-shown workspace writes are
local and reversible, every gate passed in two independent runs
(0 missed risky, 0.0% false block; risky floor 0.48, safe ceiling 0.28).
Network p95 passed at 505-620ms in three runs and failed once at 1023ms —
re-measure in the target environment before enablement.

* feat(typesafe): record the effective risk policy in the eval report

A custom-rubric run was indistinguishable from a default-policy run in the
recorded configuration, so its verdict could not be reproduced. Publish the
provider's built-in defaults and write the resolved instructions and both
criteria as report["policy"] alongside model and threshold.

* feat(typesafe): mark the eval policy on stdout and pin flag passthrough

Address the PR #6179 review notes: read the rubric-override flags by
direct attribute access so a plumbing mistake fails loudly instead of
silently evaluating the default policy, print policy=default|custom in
the report header so a custom-rubric run is distinguishable on the
console too, and pin the flag-to-provider passthrough with an offline
provider-construction test.
2026-10-02 22:56:24 +08:00
Linyao Du
616c6e2e36
fix(uploads): reject Windows staging aliases before batch ingestion (#6149)
* fix(uploads): reject Windows staging aliases before batch ingestion

* fix(uploads): cover shelf names and case-insensitive staging aliases

* test(uploads): isolate legacy alias filesystem cases
2026-10-02 22:50:30 +08:00
Hyeonsang Cho
457aa3a492
fix(community): resolve SSRF-guarded hostnames off the event loop (#6140)
* test(blocking-io): catch socket.getaddrinfo on the event loop

Blockbuster wraps socket.socket methods but not the module-level
resolver, so a synchronous hostname lookup on the loop passes the strict
gate. The SSRF guard in deerflow.community.url_safety resolves with
socket.getaddrinfo from async web tools, and the anchors added next stay
green against that unfixed code without this rule.

Add socket.getaddrinfo to _PROJECT_BLOCKING_RULES, scoped to app.* and
deerflow.* callers. loop.getaddrinfo and asyncio.to_thread resolve in a
worker thread and are not flagged. The full make test-blocking-io suite
stays green with the rule active (187 passed).

* fix(community): resolve SSRF-guarded hostnames off the event loop

validate_public_http_url resolves hostnames with blocking
socket.getaddrinfo. The crawl4ai and Browserless web_fetch, web_capture,
browser_navigate, the Gateway browser navigate route, and the Live
stream's navigate input and seed all called it directly from async code,
so a slow DNS answer for a model- or user-chosen URL stalled the Gateway
event loop for the whole lookup.

Run the guard through asyncio.to_thread at each of those call sites, the
same way personal_network already offloads it. The screening result is
unchanged. fastcrw's web_fetch is a sync tool and personal MCP validation
already runs in a worker, so neither needed a change.

* docs(changelog): reference #6140 in the SSRF guard event-loop entry

* fix(browser): run the Playwright request guard off the shared browser loop

BrowserSession._install_request_guard screens every redirect hop, iframe
and subresource by calling the SSRF guard inside the async route
callback. The guard resolves hostnames with blocking socket.getaddrinfo,
and that callback runs on the process-wide Playwright loop, which also
pumps Live frames and input for every browser session, so one slow
lookup stalled all of them.

Run the guard through asyncio.to_thread there as well, and pin it with a
strict-gate anchor that drives the real route handler. Also note in the
url_safety docstring that the screen is check-time only: a caller that
re-resolves at connect time is not pinned to the vetted IPs.

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-02 22:33:48 +08:00
Insecshin
759136e074
fix(config): correct Gemini official endpoint reasoning example (#6161)
* fix(config): correct Gemini official endpoint reasoning example

* docs: clarify official Gemini endpoint heading
2026-10-02 22:32:21 +08:00
creed
f4af75a7fd
feat(community): add bounded retries for Jina web fetch (#6143)
* feat(community): add bounded retries for Jina web fetch

Closes #6116

Keep retries opt-in and share a total deadline across requests and backoff. Preserve cancellation and the existing Error contract. Include offline DNS and local-wheel fixture corrections needed to run the complete backend suite in the isolated verifier.

Signed-off-by: 97three <2212371308@qq.com>

* docs(community): scope Jina retry guidance to its provider

Signed-off-by: 97three <2212371308@qq.com>

* fix(community): jitter bounded Jina retry backoff

* docs(community): apply provider-scoped Jina guidance

Signed-off-by: 97three <2212371308@qq.com>

---------

Signed-off-by: 97three <2212371308@qq.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
2026-10-02 21:35:56 +08:00