2026-05-26 16:24:34 -07:00
|
|
|
from __future__ import annotations
|
|
|
|
|
|
|
|
|
|
from typing import Any
|
|
|
|
|
|
|
|
|
|
from langgraph.config import get_config
|
|
|
|
|
|
refactor: consolidate reviewer modules into agent/review/
Part of the domain-reorg adoption (build plan step C2): fork content,
upstream layout. Nine 1:1 module moves (reviewer_diff/eval_store/
findings/groups/publish/reconcile/trace_context + review_style_
collector/guidance) into agent/review/, with internal relative
imports re-wired to the new package depth. agent/review/__init__.py
mirrors upstream's thin re-export shim (one of the 21 verified "A"
structural adds).
Rewrote the 38 grep hits across importer files (agent/{analyzer,
ci_autofix,reviewer,webapp}.py, agent/dashboard/*, agent/middleware/
settle_review_check.py, agent/tools/*, agent/utils/github_feedback.py,
agent/webhooks/github.py, evals/reviewer/*, and the reviewer test
suite) to point at agent.review.*; 4 of the 38 hits were name
collisions (list_reviewer_findings, reviewer_outcomes,
_reviewer_thread_id, reviewer_thread_id — not the moved modules) and
were left untouched. tests/test_github_checks.py's module-alias
import (`from agent import reviewer_publish`) follows upstream's own
`from agent.review import publish as reviewer_publish` pattern so
downstream `reviewer_publish.*` call sites needed no changes.
agent/reviewer.py and agent/webapp.py stay in place per the hard
rule (fork content, import-only rewire) and are not part of this
package.
Gates: ruff check + ruff format --check, pytest --co -q (1637
collected), full unit suite (1637 passed), and the reviewer/findings
suite in isolation (pytest -k "review or finding", 421 passed).
2026-07-17 13:52:03 -04:00
|
|
|
from ..review.findings import (
|
2026-05-27 10:52:30 -07:00
|
|
|
Finding,
|
2026-06-10 10:44:13 -07:00
|
|
|
ReviewerThreadMissingError,
|
2026-05-27 10:52:30 -07:00
|
|
|
get_finding,
|
|
|
|
|
get_thread_id_from_runtime,
|
2026-06-10 10:44:13 -07:00
|
|
|
thread_missing_tool_result,
|
2026-05-27 10:52:30 -07:00
|
|
|
update_finding_fields,
|
2026-05-27 17:26:08 -07:00
|
|
|
update_finding_surface,
|
2026-05-27 10:52:30 -07:00
|
|
|
)
|
refactor: consolidate reviewer modules into agent/review/
Part of the domain-reorg adoption (build plan step C2): fork content,
upstream layout. Nine 1:1 module moves (reviewer_diff/eval_store/
findings/groups/publish/reconcile/trace_context + review_style_
collector/guidance) into agent/review/, with internal relative
imports re-wired to the new package depth. agent/review/__init__.py
mirrors upstream's thin re-export shim (one of the 21 verified "A"
structural adds).
Rewrote the 38 grep hits across importer files (agent/{analyzer,
ci_autofix,reviewer,webapp}.py, agent/dashboard/*, agent/middleware/
settle_review_check.py, agent/tools/*, agent/utils/github_feedback.py,
agent/webhooks/github.py, evals/reviewer/*, and the reviewer test
suite) to point at agent.review.*; 4 of the 38 hits were name
collisions (list_reviewer_findings, reviewer_outcomes,
_reviewer_thread_id, reviewer_thread_id — not the moved modules) and
were left untouched. tests/test_github_checks.py's module-alias
import (`from agent import reviewer_publish`) follows upstream's own
`from agent.review import publish as reviewer_publish` pattern so
downstream `reviewer_publish.*` call sites needed no changes.
agent/reviewer.py and agent/webapp.py stay in place per the hard
rule (fork content, import-only rewire) and are not part of this
package.
Gates: ruff check + ruff format --check, pytest --co -q (1637
collected), full unit suite (1637 passed), and the reviewer/findings
suite in isolation (pytest -k "review or finding", 421 passed).
2026-07-17 13:52:03 -04:00
|
|
|
from ..review.publish import (
|
2026-05-27 10:52:30 -07:00
|
|
|
fetch_pr_review_threads,
|
|
|
|
|
fetch_review_thread_id_for_comment,
|
2026-05-28 12:44:00 -07:00
|
|
|
render_resolution_comment,
|
|
|
|
|
reply_to_review_comment,
|
2026-05-27 10:52:30 -07:00
|
|
|
resolve_review_thread,
|
|
|
|
|
)
|
refactor: consolidate reviewer modules into agent/review/
Part of the domain-reorg adoption (build plan step C2): fork content,
upstream layout. Nine 1:1 module moves (reviewer_diff/eval_store/
findings/groups/publish/reconcile/trace_context + review_style_
collector/guidance) into agent/review/, with internal relative
imports re-wired to the new package depth. agent/review/__init__.py
mirrors upstream's thin re-export shim (one of the 21 verified "A"
structural adds).
Rewrote the 38 grep hits across importer files (agent/{analyzer,
ci_autofix,reviewer,webapp}.py, agent/dashboard/*, agent/middleware/
settle_review_check.py, agent/tools/*, agent/utils/github_feedback.py,
agent/webhooks/github.py, evals/reviewer/*, and the reviewer test
suite) to point at agent.review.*; 4 of the 38 hits were name
collisions (list_reviewer_findings, reviewer_outcomes,
_reviewer_thread_id, reviewer_thread_id — not the moved modules) and
were left untouched. tests/test_github_checks.py's module-alias
import (`from agent import reviewer_publish`) follows upstream's own
`from agent.review import publish as reviewer_publish` pattern so
downstream `reviewer_publish.*` call sites needed no changes.
agent/reviewer.py and agent/webapp.py stay in place per the hard
rule (fork content, import-only rewire) and are not part of this
package.
Gates: ruff check + ruff format --check, pytest --co -q (1637
collected), full unit suite (1637 passed), and the reviewer/findings
suite in isolation (pytest -k "review or finding", 421 passed).
2026-07-17 13:52:03 -04:00
|
|
|
from ..review.reconcile import reconcile_findings_with_review_threads
|
2026-05-26 16:24:34 -07:00
|
|
|
from ..utils.github_token import get_github_token
|
feat: outcomes dataset + bootstrap/continual split via skills (#1365)
* fix: reset stale sandbox creation sentinel
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
* fix: treat SANDBOX_CREATING as a timestamped cross-process lock
Only reset the sentinel when proven stale (older than the creation
timeout); otherwise wait for the worker that holds the lock so a
concurrent run does not create a duplicate sandbox.
* feat(analyzer): outcomes dataset + bootstrap/continual split via skills
Rename the review_style_analyzer graph to `analyzer` and split it into two
modes, plus capture reviewer finding outcomes for continual learning.
- Outcomes dataset: upsert resolved-by-commit (positive), dismissed (false
positive), and GitHub/Slack thumbs findings into a single LangSmith dataset
(openswe-reviewer-outcomes), keyed deterministically per finding+source.
Emit points wired into update_finding, resolve_finding_thread, and the
GitHub/Slack reaction handlers.
- Two playbooks delivered as deepagents skills (bootstrap-repo-analysis,
continual-learning), served as virtual files via a CompositeBackend /skills/
route + StateBackend (seeded into the run files channel at invoke time, never
written to the sandbox). Mode is set by the launcher; continual runs fall
back to the GitHub App installation token.
- Split launcher into start_bootstrap_analysis + start_continual_run; register
a per-repo nightly continual-learning cron when bootstrap completes.
- New read_finding_outcomes tool feeds confirmed/dismissed findings back to the
continual playbook.
Tests for outcome label mapping, skills helper, and cron idempotency.
* fix(analyzer): anchor continual cron runs to a real thread_id
The nightly continual-learning cron is threadless, and get_analyzer
early-returns an empty agent when configurable.thread_id is missing — so
every cron-launched run no-op'd before reading outcomes or saving a refined
prompt. Include the repo's deterministic analyzer thread_id in the continual
run configurable so the run executes; the threadless run carries no message
history, so nightly runs don't accumulate context.
* refactor(analyzer): move cron lifecycle calls out of the review-styles store
Drop the inline `analyzer_cron` imports from review_styles.py (added only to
dodge a circular import) by relocating the cron-trigger calls to the layer
above the store: registration to the save_review_style tool (after a prompt is
saved) and removal to the dashboard delete route. review_styles.py is now a
pure store again with top-level imports only.
* refactor: hoist reviewer_outcomes imports to module level
Move the two inline emit_finding_status_outcome imports introduced in this PR
(update_finding, resolve_finding_thread) to top-level imports. reviewer_outcomes
only depends on langsmith, so there is no circular import to avoid.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-01 13:25:12 -07:00
|
|
|
from ..utils.reviewer_outcomes import emit_finding_status_outcome
|
2026-05-26 16:24:34 -07:00
|
|
|
|
|
|
|
|
|
2026-05-28 16:04:38 -07:00
|
|
|
def _normalize_note(note: str | None) -> str | None:
|
|
|
|
|
if note is None:
|
|
|
|
|
return None
|
|
|
|
|
normalized = note.strip()
|
|
|
|
|
return normalized or None
|
|
|
|
|
|
|
|
|
|
|
chore: sync upstream/main, defer #1621 modular webhooks (#81)
* chore: bake sfw binary into sandbox image (#1611)
sfw only ships a launcher that fetches its real binary at first run and does a
daily update check against api.github.com/repos/SocketDev/sfw-free. Both fail in
the sandbox (restricted egress; the proxy injects the GitHub App installation
token, which lacks access to that repo), so `sfw yarn install` errors with
"could not fetch its binary". Pin sfw 2.0.6, warm + verify the binary cache at
build, and set SFW_SKIP_UPDATE_CHECK=1 so runs use the baked binary offline.
* feat: editable plan mode + fix review-plan banner overlap (#1610)
* feat: editable plan mode + fix review-plan banner overlap
Lets the thread owner edit the plan markdown by hand from the plan-review
page (Edit -> textarea -> Save) via a new PUT /dashboard/api/plan/{id}
endpoint that re-publishes the plan and mirrors it into the sandbox
plan.md, so approve hands the edited plan to the agent as the source of
truth. Also fixes the collapsed git-panel's floating expand button
covering the "Review plan ->" banner by reserving space for it.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: abort plan approval when the published plan read fails
get_plan_content() swallowed store errors and returned None, so a
transient failure during approve would still mark the plan approved and
dispatch the generic fallback text — silently dropping an owner's edited
plan. Read the plan strictly (raise_on_error=True) so approval aborts
instead, matching the comment read.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show message timestamps (#1609)
* feat: show message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: suppress fallback message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: stable message + tool-call hover timestamps
Stamp a stable client-side arrival time per message and tool call (keyed
by id, persisted to localStorage). Messages render the timestamp inline;
tool rows reveal a dim timestamp chip on hover. Real backend created_at
still takes precedence when present.
* fix: hide client-stamped message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add PR trace resolution (#1612)
* feat: add PR trace resolution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: inject reviewer trace context as JSON
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: address review on PR trace resolution
Use the documented LangSmith metadata filter syntax
(and(eq(metadata_key,...), eq(metadata_value,...))) instead of
has(metadata, '{...}'), which does not match runs — _list_thread_runs
was silently returning nothing. Bound full-text searches to a 90-day
window so they don't hit LangSmith's large-window rate limit.
Also folds in the best-effort branch->head-sha resolver (dropping the
weighted scoring/threshold + repo/file evidence + GitHub hydration),
sandbox JSON injection, and the admin "Resolve trace" dry-run endpoint.
The IDOR findings are moot: resolve_pr_to_threads/summarize_agent_session
were removed; resolution now runs deterministically from the trusted run
config with no model-controlled pr_url or thread_id.
* fix: scope branch trace search to the repo
Branch names like fix-tests aren't unique across repos (or older PRs) in
a shared tracing project, so an unscoped branch hit could resolve to an
unrelated thread and write its runs into the reviewer sandbox. Require
the repo slug to co-occur with the branch in matched runs; the full head
SHA stays unscoped since it is globally unique. Addresses open-swe review
on PR #1612.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: include plan links in PR descriptions (#1613)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: gate workflow pushes with approval (#1614)
* feat: gate workflow pushes with approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve proxy refresh test compatibility
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: bind workflow approvals to pushed ref
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: recover thread work as patch (#1615)
* feat: recover thread work as patch
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: search sandbox cwd for recovery patches
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: omit plan link in PR description when no plan exists (#1618)
Plan links in PR descriptions were always built from the thread id, so
runs that never produced a plan linked to an empty plan-review page.
Now the plan content store is consulted first; the link is only added
when a plan with non-empty markdown actually exists. A transient store
failure degrades gracefully (no link) rather than blocking PR creation.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add filter & grouping menu to agents threads sidebar (#1617)
Add a Cursor-style control to the agents sidebar that groups (None/Date/
Status/Project), filters (ownership, status, source, pull request, model,
repo, include-resolved), and compacts the threads list. All client-side over
already-fetched sidebar threads; preferences persist in localStorage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: update langsmith sdk to 0.9.3 (#1616)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: clickable shared PR header in git panel and reviews (#1620)
* feat: clickable shared PR header in git panel and reviews
Replace the standalone "View PR" button in the agent git panel with a
clickable PR title, matching the reviews view. Extract a shared PrHeader
component reused by both the git panel and the review main body.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: drop PrHeader wrapper, use shared component directly
The review-side PrHeader was just a thin adapter mapping detail -> the
shared component's props. Inline it at the call site and use the shared
PrHeader directly so there's a single component.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: durable interrupt dispatch + completion webhook (#1621)
* wip(rebuild): core reliability spine
- remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring)
- dispatch core: agent/dispatch.py with multitask_strategy=interrupt +
durability=sync + completion webhook; reroute all webhook + plan triggers;
drop the racy in-process lock + is_thread_active busy-check
- completion webhook: agent/completion.py + /webhooks/run-complete loopback
route for failure/timeout replies (idempotent)
Co-authored-by: open-swe[bot]
* feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning
Parallel batch on top of the reliability spine:
- async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the
http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden
the IP check to 'not is_global' (+ IPv4-mapped unwrap)
- reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list
-> cancel_many), wired into the scheduler graph via task='reconcile'
- shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare
httpx.AsyncClient() across utils/dashboard/webapp/middleware
- run budget: MODEL_CALL_RECURSION_LIMIT 5000->250
- fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8)
- drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls)
- confirm tool-result eviction + summarization auto-wired via backend
- slim system prompt ~8% (full harness-profile rewrite deferred)
Co-authored-by: open-swe[bot]
* feat(rebuild): harness-profile prompt + split webhooks out of webapp
- prompt.py: own the system prompt via a registered harness profile
(OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that
share it stay safe), registered across all 4 providers; per-thread values
stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k
tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped
ALL-CAPS markers.
- webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into
agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the
routes + tests; moved handlers reach shared helpers via the webapp namespace
to preserve the test suite's monkeypatch targets.
Full suite: 1168 passing, lint clean.
Co-authored-by: open-swe[bot]
* Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks
Reverts the 250 cap from the run-budget change — long-running tasks legitimately
need many model calls. The notify_step_limit_reached safety net still fires if a
run does hit the cap, so runs end with a signal either way.
Co-authored-by: open-swe[bot]
* fix: address PR review (auth, SSRF, interrupted status, redirect headers)
- completion.py: drop `interrupted` from failure statuses — with
multitask_strategy=interrupt a follow-up ends the prior run as interrupted,
which is healthy, not a failure to report. [open-swe]
- /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when
RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest.
[corridor-security]
- SSRF: extract the URL validator to agent/utils/url_safety.py and apply it
before server-side image fetches in multimodal.fetch_image_block.
[corridor-security]
- http_request: preserve caller headers/extensions across redirect hops instead
of dropping them on the first hop. [open-swe]
Co-authored-by: open-swe[bot]
* chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo)
Co-authored-by: open-swe[bot]
* fix: fail closed on run-complete webhook auth when secret unset
Corridor follow-up: verify_run_complete_token returns False (not True) when
RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never
unauthenticated. Logs a startup warning when the secret is absent, and dispatch
skips registering the webhook when there's no secret (no rejected callbacks).
Co-authored-by: open-swe[bot]
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: restore forced tool call to prevent premature run stops (#1622)
Restore the ensure_no_empty_msg middleware and the always-call-a-tool system-prompt instruction that #1535 removed. When the model emits a message with no tool call (and hasn't already messaged the user or confirmed completion), the middleware re-injects a no_op / confirming_completion tool call so the run continues instead of ending mid-task.
Shipping to test whether it fixes runs that stop halfway through.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore(deps): bump langgraph-checkpoint from 4.1.0 to 4.1.1 (#1619)
Bumps [langgraph-checkpoint](https://github.com/langchain-ai/langgraph) from 4.1.0 to 4.1.1.
- [Release notes](https://github.com/langchain-ai/langgraph/releases)
- [Commits](https://github.com/langchain-ai/langgraph/compare/checkpoint==4.1.0...checkpoint==4.1.1)
---
updated-dependencies:
- dependency-name: langgraph-checkpoint
dependency-version: 4.1.1
dependency-type: indirect
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* fix: post reviewer resolution notes verbatim (#1624)
* fix: post reviewer resolution notes verbatim
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: stabilize dashboard follow-up e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make e2e attribution marker durable
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: only echo found e2e attribution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: check live dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* hotfix: stop prompting agent/reviewer to wrap installs in sfw (#1625)
Installs hung when prefixed with sfw inside the sandbox (trace 019f0608
stalled on a pending `sfw npm install` execute, never returned). Strip the
Socket Firewall guidance from the agent and reviewer prompts so installs run
through the project's package manager directly. sfw stays in the Docker image;
nothing invokes it now.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make plan view mobile friendly (#1636)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: fall back to vision model for image threads (#1626)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: surface Slack thread errors (#1627)
* fix: surface Slack thread errors
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: don't set failure_reply_posted on Slack preprocessing errors
The preprocessing error handler was setting failure_reply_posted=True,
the same idempotency flag handle_run_completion checks to suppress
duplicate run-failure replies. Since preprocessing failures happen
before any run exists but the flag persists on the thread, a subsequent
run failure on the same thread would be silently ignored.
The preprocessing handler already posts its own Slack reply, so the
run-completion idempotency flag should not be set here.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: avoid recapping Slack replies (#1629)
* chore: avoid recapping Slack replies
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: simplify Slack reply prompt wording
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: update Slack trace reply on web handoff (#1630)
* fix: update Slack trace reply on web handoff
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: trigger web handoff on dashboard starts
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: format web handoff as contextual fragment
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve trace_message_ts when overwriting Slack run mapping
When store_slack_run_mapping is called without trace_message_ts (e.g. on
follow-up Slack mentions), it was unconditionally overwriting the
thread-level mapping and clobbering the timestamp captured from the
initial trace reply. After that, _notify_slack_web_handoff could not find
the original message, so a subsequent move to Web silently skipped the
Slack trace update.
Now, when trace_message_ts is not passed, the existing thread mapping is
read first and its trace_message_ts is preserved.
* style: ruff format
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* fix: pre-bundle shiki/@pierre deps to stop dev dynamic-import failures (#1643)
* fix(ui): pre-bundle shiki/@pierre deps to stop dev dynamic-import failures
shiki lazy-imports a grammar per language and these libs only live inside
lazy route components, so Vite's startup scanner never sees them. They get
discovered on first thread navigation, triggering a dep re-optimize +
force-reload that aborts the in-flight route-chunk import, surfacing as
"Failed to fetch dynamically imported module: .../$threadId.tsx".
Pre-bundle them (and the github themes + common code-block languages) via
optimizeDeps.include so the optimize happens once at startup. Dev-only;
production bundles are unaffected.
* fix: pre-bundle canonical shiki docker/make langs instead of aliases
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show queued dashboard follow-ups (#1631)
* feat: show queued dashboard follow-ups
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: de-dupe queued follow-ups while streaming
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: notify Slack on plan approval (#1632)
* feat: notify Slack on plan approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: post Slack approval notice after successful dispatch
Move the _maybe_post_plan_approved_to_slack call until after
_dispatch_followup succeeds so the Slack thread is not told
implementation is beginning before the LangGraph run is created.
Addresses PR review comment.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: include Slack channel context in prompts (#1633)
Add cached Slack channel metadata enrichment for Slack-triggered runs so prompts can include channel names and descriptions without duplicate conversations.info calls.\n\nCo-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
* chore: keep plan guidance high-level (#1634)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: publish plans from sandbox files (#1635)
* feat: publish plans from sandbox files
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: avoid fixed plan filenames
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: virtualize local sandbox file paths
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve plan_file_path across set_plan_status
set_plan_status was rewriting the content record with only markdown
and status, dropping plan_file_path. After a reject, the owner's
dashboard edit would mirror to a different file than the agent's
original, and the next save_plan could republish the stale file.
Preserve plan_file_path when updating status.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: return to thread after plan approval (#1637)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Slack breakout thread tool (#1638)
* feat: add Slack breakout thread tool
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: make fake LLM scripts declarative
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: exclude slack_start_new_thread from plan mode
The breakout tool can dispatch a fresh agent run that starts outside the
current plan-mode state, bypassing the approval flow. Add it to
PLAN_MODE_EXCLUDED_TOOLS so it's hidden alongside the other mutating
tools while planning.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: require bun for ui agent work (#1639)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: request actions read for sandbox logs (#1642)
* fix: request actions read for sandbox logs
Request optional Actions read permission for sandbox proxy tokens, with fallback for installations that have not approved it yet. Update setup docs and prompt guidance for safe GitHub Actions log usage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: restore actions:read scope after workflow push
After an approved workflow push, the guard was restoring the proxy with
BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS, which excludes the actions: read
scope this PR adds. Restore with RUNTIME_PROXY_TOKEN_PERMISSIONS (which
includes actions: read) and fall back to BASE if the install hasn't
granted Actions read — mirroring the pattern in _create_sandbox_with_proxy.
Addresses review comment on PR #1642.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: widen split review diffs (#1647)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: install missing deps before verification (#1646)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm (#1645)
* chore: require pnpm for ui agent work
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm
Replace Bun and Yarn lockfiles with pnpm lockfile and update UI/Vercel commands to use pnpm.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* ci: use corepack for ui pnpm e2e build
Run pnpm through Corepack in the E2E global setup so CI can use the pinned package manager without a separate pnpm install step.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Sonnet 5 to model picker (#1651)
* chore: update Sonnet examples to Sonnet 5
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: add Sonnet 5 to model picker
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* Remove dead breakout-thread e2e scenario after dropping the tool
The merge resolution deferred upstream's Slack breakout-thread tool
(slack_start_new_thread, #1638) since it depends on the #1621 dispatch
module, but the e2e harness still scripted it. Removing the tool name
from fake_llm.py's _tool_step call left a malformed scenario, crashing
the langgraph-dev web server at import (TypeError: _tool_step() missing
'call_id') and failing Playwright E2E.
Drop the "breakout" script scenario, its _is_breakout_request helper +
ScriptRule, and the corresponding full_flow.spec.ts test.
* Revert upstream pnpm switch; keep bun for the UI build
The merge auto-adopted upstream's pnpm switch (#1645) in tests/e2e/
global-setup.ts and ui/package.json, but our fork builds the UI with
bun (vercel.json + the E2E workflow's setup-bun). That left the
Playwright globalSetup running `corepack pnpm install --frozen-lockfile`
with no pnpm-lock.yaml, failing E2E at UI build time.
Revert global-setup.ts and ui/package.json to the dev (bun) baseline,
drop the merge-added ui/pnpm-lock.yaml, and remove the re-added
ui/AGENTS.md (our fork had deleted it).
* Align plan-review e2e + UI with the HEAD (pre-#1635) backend
The merge left a split plan vertical: the backend save_plan/plan_api are
HEAD (we deferred the editable-plan/sandbox-publish features #1610/#1635/
#1637 per #80), but the plan UI and e2e harness were upstream's. The
fake_llm scenario called save_plan(plan_file_path=...) — upstream's
file-based #1635 contract — while HEAD save_plan takes plan_markdown,
so the plan never saved and PlanReview never rendered (E2E failure on
the plan-review locator).
Pass plan_markdown to save_plan, and revert PlanReview.tsx / plan.ts /
$threadId_.plan.tsx / plan_review.spec.ts to the dev baseline so the
whole plan flow (save -> render -> approve -> implement) is consistent
with the HEAD backend.
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <ramon.nogueira@langchain.dev>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: Caroline di Vittorio <43390382+carolinedivittorio@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>
Co-authored-by: Mukil Loganathan <mukil@langchain.dev>
2026-06-30 16:45:19 -04:00
|
|
|
async def resolve_finding_thread(
|
2026-05-26 16:24:34 -07:00
|
|
|
finding_id: str,
|
2026-05-28 16:04:38 -07:00
|
|
|
note: str,
|
2026-05-26 16:24:34 -07:00
|
|
|
status: str = "dismissed",
|
|
|
|
|
) -> dict[str, Any]:
|
|
|
|
|
"""Resolve the GitHub review thread for a tracked Open SWE finding.
|
|
|
|
|
|
|
|
|
|
Use ``status="resolved"`` when the code now fixes the issue. Use
|
|
|
|
|
``status="dismissed"`` when analysis shows the original review comment was
|
chore: sync upstream/main, defer #1621 modular webhooks (#81)
* chore: bake sfw binary into sandbox image (#1611)
sfw only ships a launcher that fetches its real binary at first run and does a
daily update check against api.github.com/repos/SocketDev/sfw-free. Both fail in
the sandbox (restricted egress; the proxy injects the GitHub App installation
token, which lacks access to that repo), so `sfw yarn install` errors with
"could not fetch its binary". Pin sfw 2.0.6, warm + verify the binary cache at
build, and set SFW_SKIP_UPDATE_CHECK=1 so runs use the baked binary offline.
* feat: editable plan mode + fix review-plan banner overlap (#1610)
* feat: editable plan mode + fix review-plan banner overlap
Lets the thread owner edit the plan markdown by hand from the plan-review
page (Edit -> textarea -> Save) via a new PUT /dashboard/api/plan/{id}
endpoint that re-publishes the plan and mirrors it into the sandbox
plan.md, so approve hands the edited plan to the agent as the source of
truth. Also fixes the collapsed git-panel's floating expand button
covering the "Review plan ->" banner by reserving space for it.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: abort plan approval when the published plan read fails
get_plan_content() swallowed store errors and returned None, so a
transient failure during approve would still mark the plan approved and
dispatch the generic fallback text — silently dropping an owner's edited
plan. Read the plan strictly (raise_on_error=True) so approval aborts
instead, matching the comment read.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show message timestamps (#1609)
* feat: show message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: suppress fallback message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: stable message + tool-call hover timestamps
Stamp a stable client-side arrival time per message and tool call (keyed
by id, persisted to localStorage). Messages render the timestamp inline;
tool rows reveal a dim timestamp chip on hover. Real backend created_at
still takes precedence when present.
* fix: hide client-stamped message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add PR trace resolution (#1612)
* feat: add PR trace resolution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: inject reviewer trace context as JSON
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: address review on PR trace resolution
Use the documented LangSmith metadata filter syntax
(and(eq(metadata_key,...), eq(metadata_value,...))) instead of
has(metadata, '{...}'), which does not match runs — _list_thread_runs
was silently returning nothing. Bound full-text searches to a 90-day
window so they don't hit LangSmith's large-window rate limit.
Also folds in the best-effort branch->head-sha resolver (dropping the
weighted scoring/threshold + repo/file evidence + GitHub hydration),
sandbox JSON injection, and the admin "Resolve trace" dry-run endpoint.
The IDOR findings are moot: resolve_pr_to_threads/summarize_agent_session
were removed; resolution now runs deterministically from the trusted run
config with no model-controlled pr_url or thread_id.
* fix: scope branch trace search to the repo
Branch names like fix-tests aren't unique across repos (or older PRs) in
a shared tracing project, so an unscoped branch hit could resolve to an
unrelated thread and write its runs into the reviewer sandbox. Require
the repo slug to co-occur with the branch in matched runs; the full head
SHA stays unscoped since it is globally unique. Addresses open-swe review
on PR #1612.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: include plan links in PR descriptions (#1613)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: gate workflow pushes with approval (#1614)
* feat: gate workflow pushes with approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve proxy refresh test compatibility
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: bind workflow approvals to pushed ref
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: recover thread work as patch (#1615)
* feat: recover thread work as patch
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: search sandbox cwd for recovery patches
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: omit plan link in PR description when no plan exists (#1618)
Plan links in PR descriptions were always built from the thread id, so
runs that never produced a plan linked to an empty plan-review page.
Now the plan content store is consulted first; the link is only added
when a plan with non-empty markdown actually exists. A transient store
failure degrades gracefully (no link) rather than blocking PR creation.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add filter & grouping menu to agents threads sidebar (#1617)
Add a Cursor-style control to the agents sidebar that groups (None/Date/
Status/Project), filters (ownership, status, source, pull request, model,
repo, include-resolved), and compacts the threads list. All client-side over
already-fetched sidebar threads; preferences persist in localStorage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: update langsmith sdk to 0.9.3 (#1616)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: clickable shared PR header in git panel and reviews (#1620)
* feat: clickable shared PR header in git panel and reviews
Replace the standalone "View PR" button in the agent git panel with a
clickable PR title, matching the reviews view. Extract a shared PrHeader
component reused by both the git panel and the review main body.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: drop PrHeader wrapper, use shared component directly
The review-side PrHeader was just a thin adapter mapping detail -> the
shared component's props. Inline it at the call site and use the shared
PrHeader directly so there's a single component.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: durable interrupt dispatch + completion webhook (#1621)
* wip(rebuild): core reliability spine
- remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring)
- dispatch core: agent/dispatch.py with multitask_strategy=interrupt +
durability=sync + completion webhook; reroute all webhook + plan triggers;
drop the racy in-process lock + is_thread_active busy-check
- completion webhook: agent/completion.py + /webhooks/run-complete loopback
route for failure/timeout replies (idempotent)
Co-authored-by: open-swe[bot]
* feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning
Parallel batch on top of the reliability spine:
- async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the
http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden
the IP check to 'not is_global' (+ IPv4-mapped unwrap)
- reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list
-> cancel_many), wired into the scheduler graph via task='reconcile'
- shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare
httpx.AsyncClient() across utils/dashboard/webapp/middleware
- run budget: MODEL_CALL_RECURSION_LIMIT 5000->250
- fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8)
- drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls)
- confirm tool-result eviction + summarization auto-wired via backend
- slim system prompt ~8% (full harness-profile rewrite deferred)
Co-authored-by: open-swe[bot]
* feat(rebuild): harness-profile prompt + split webhooks out of webapp
- prompt.py: own the system prompt via a registered harness profile
(OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that
share it stay safe), registered across all 4 providers; per-thread values
stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k
tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped
ALL-CAPS markers.
- webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into
agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the
routes + tests; moved handlers reach shared helpers via the webapp namespace
to preserve the test suite's monkeypatch targets.
Full suite: 1168 passing, lint clean.
Co-authored-by: open-swe[bot]
* Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks
Reverts the 250 cap from the run-budget change — long-running tasks legitimately
need many model calls. The notify_step_limit_reached safety net still fires if a
run does hit the cap, so runs end with a signal either way.
Co-authored-by: open-swe[bot]
* fix: address PR review (auth, SSRF, interrupted status, redirect headers)
- completion.py: drop `interrupted` from failure statuses — with
multitask_strategy=interrupt a follow-up ends the prior run as interrupted,
which is healthy, not a failure to report. [open-swe]
- /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when
RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest.
[corridor-security]
- SSRF: extract the URL validator to agent/utils/url_safety.py and apply it
before server-side image fetches in multimodal.fetch_image_block.
[corridor-security]
- http_request: preserve caller headers/extensions across redirect hops instead
of dropping them on the first hop. [open-swe]
Co-authored-by: open-swe[bot]
* chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo)
Co-authored-by: open-swe[bot]
* fix: fail closed on run-complete webhook auth when secret unset
Corridor follow-up: verify_run_complete_token returns False (not True) when
RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never
unauthenticated. Logs a startup warning when the secret is absent, and dispatch
skips registering the webhook when there's no secret (no rejected callbacks).
Co-authored-by: open-swe[bot]
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: restore forced tool call to prevent premature run stops (#1622)
Restore the ensure_no_empty_msg middleware and the always-call-a-tool system-prompt instruction that #1535 removed. When the model emits a message with no tool call (and hasn't already messaged the user or confirmed completion), the middleware re-injects a no_op / confirming_completion tool call so the run continues instead of ending mid-task.
Shipping to test whether it fixes runs that stop halfway through.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore(deps): bump langgraph-checkpoint from 4.1.0 to 4.1.1 (#1619)
Bumps [langgraph-checkpoint](https://github.com/langchain-ai/langgraph) from 4.1.0 to 4.1.1.
- [Release notes](https://github.com/langchain-ai/langgraph/releases)
- [Commits](https://github.com/langchain-ai/langgraph/compare/checkpoint==4.1.0...checkpoint==4.1.1)
---
updated-dependencies:
- dependency-name: langgraph-checkpoint
dependency-version: 4.1.1
dependency-type: indirect
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* fix: post reviewer resolution notes verbatim (#1624)
* fix: post reviewer resolution notes verbatim
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: stabilize dashboard follow-up e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make e2e attribution marker durable
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: only echo found e2e attribution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: check live dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* hotfix: stop prompting agent/reviewer to wrap installs in sfw (#1625)
Installs hung when prefixed with sfw inside the sandbox (trace 019f0608
stalled on a pending `sfw npm install` execute, never returned). Strip the
Socket Firewall guidance from the agent and reviewer prompts so installs run
through the project's package manager directly. sfw stays in the Docker image;
nothing invokes it now.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make plan view mobile friendly (#1636)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: fall back to vision model for image threads (#1626)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: surface Slack thread errors (#1627)
* fix: surface Slack thread errors
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: don't set failure_reply_posted on Slack preprocessing errors
The preprocessing error handler was setting failure_reply_posted=True,
the same idempotency flag handle_run_completion checks to suppress
duplicate run-failure replies. Since preprocessing failures happen
before any run exists but the flag persists on the thread, a subsequent
run failure on the same thread would be silently ignored.
The preprocessing handler already posts its own Slack reply, so the
run-completion idempotency flag should not be set here.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: avoid recapping Slack replies (#1629)
* chore: avoid recapping Slack replies
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: simplify Slack reply prompt wording
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: update Slack trace reply on web handoff (#1630)
* fix: update Slack trace reply on web handoff
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: trigger web handoff on dashboard starts
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: format web handoff as contextual fragment
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve trace_message_ts when overwriting Slack run mapping
When store_slack_run_mapping is called without trace_message_ts (e.g. on
follow-up Slack mentions), it was unconditionally overwriting the
thread-level mapping and clobbering the timestamp captured from the
initial trace reply. After that, _notify_slack_web_handoff could not find
the original message, so a subsequent move to Web silently skipped the
Slack trace update.
Now, when trace_message_ts is not passed, the existing thread mapping is
read first and its trace_message_ts is preserved.
* style: ruff format
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* fix: pre-bundle shiki/@pierre deps to stop dev dynamic-import failures (#1643)
* fix(ui): pre-bundle shiki/@pierre deps to stop dev dynamic-import failures
shiki lazy-imports a grammar per language and these libs only live inside
lazy route components, so Vite's startup scanner never sees them. They get
discovered on first thread navigation, triggering a dep re-optimize +
force-reload that aborts the in-flight route-chunk import, surfacing as
"Failed to fetch dynamically imported module: .../$threadId.tsx".
Pre-bundle them (and the github themes + common code-block languages) via
optimizeDeps.include so the optimize happens once at startup. Dev-only;
production bundles are unaffected.
* fix: pre-bundle canonical shiki docker/make langs instead of aliases
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show queued dashboard follow-ups (#1631)
* feat: show queued dashboard follow-ups
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: de-dupe queued follow-ups while streaming
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: notify Slack on plan approval (#1632)
* feat: notify Slack on plan approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: post Slack approval notice after successful dispatch
Move the _maybe_post_plan_approved_to_slack call until after
_dispatch_followup succeeds so the Slack thread is not told
implementation is beginning before the LangGraph run is created.
Addresses PR review comment.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: include Slack channel context in prompts (#1633)
Add cached Slack channel metadata enrichment for Slack-triggered runs so prompts can include channel names and descriptions without duplicate conversations.info calls.\n\nCo-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
* chore: keep plan guidance high-level (#1634)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: publish plans from sandbox files (#1635)
* feat: publish plans from sandbox files
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: avoid fixed plan filenames
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: virtualize local sandbox file paths
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve plan_file_path across set_plan_status
set_plan_status was rewriting the content record with only markdown
and status, dropping plan_file_path. After a reject, the owner's
dashboard edit would mirror to a different file than the agent's
original, and the next save_plan could republish the stale file.
Preserve plan_file_path when updating status.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: return to thread after plan approval (#1637)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Slack breakout thread tool (#1638)
* feat: add Slack breakout thread tool
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: make fake LLM scripts declarative
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: exclude slack_start_new_thread from plan mode
The breakout tool can dispatch a fresh agent run that starts outside the
current plan-mode state, bypassing the approval flow. Add it to
PLAN_MODE_EXCLUDED_TOOLS so it's hidden alongside the other mutating
tools while planning.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: require bun for ui agent work (#1639)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: request actions read for sandbox logs (#1642)
* fix: request actions read for sandbox logs
Request optional Actions read permission for sandbox proxy tokens, with fallback for installations that have not approved it yet. Update setup docs and prompt guidance for safe GitHub Actions log usage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: restore actions:read scope after workflow push
After an approved workflow push, the guard was restoring the proxy with
BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS, which excludes the actions: read
scope this PR adds. Restore with RUNTIME_PROXY_TOKEN_PERMISSIONS (which
includes actions: read) and fall back to BASE if the install hasn't
granted Actions read — mirroring the pattern in _create_sandbox_with_proxy.
Addresses review comment on PR #1642.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: widen split review diffs (#1647)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: install missing deps before verification (#1646)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm (#1645)
* chore: require pnpm for ui agent work
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm
Replace Bun and Yarn lockfiles with pnpm lockfile and update UI/Vercel commands to use pnpm.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* ci: use corepack for ui pnpm e2e build
Run pnpm through Corepack in the E2E global setup so CI can use the pinned package manager without a separate pnpm install step.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Sonnet 5 to model picker (#1651)
* chore: update Sonnet examples to Sonnet 5
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: add Sonnet 5 to model picker
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* Remove dead breakout-thread e2e scenario after dropping the tool
The merge resolution deferred upstream's Slack breakout-thread tool
(slack_start_new_thread, #1638) since it depends on the #1621 dispatch
module, but the e2e harness still scripted it. Removing the tool name
from fake_llm.py's _tool_step call left a malformed scenario, crashing
the langgraph-dev web server at import (TypeError: _tool_step() missing
'call_id') and failing Playwright E2E.
Drop the "breakout" script scenario, its _is_breakout_request helper +
ScriptRule, and the corresponding full_flow.spec.ts test.
* Revert upstream pnpm switch; keep bun for the UI build
The merge auto-adopted upstream's pnpm switch (#1645) in tests/e2e/
global-setup.ts and ui/package.json, but our fork builds the UI with
bun (vercel.json + the E2E workflow's setup-bun). That left the
Playwright globalSetup running `corepack pnpm install --frozen-lockfile`
with no pnpm-lock.yaml, failing E2E at UI build time.
Revert global-setup.ts and ui/package.json to the dev (bun) baseline,
drop the merge-added ui/pnpm-lock.yaml, and remove the re-added
ui/AGENTS.md (our fork had deleted it).
* Align plan-review e2e + UI with the HEAD (pre-#1635) backend
The merge left a split plan vertical: the backend save_plan/plan_api are
HEAD (we deferred the editable-plan/sandbox-publish features #1610/#1635/
#1637 per #80), but the plan UI and e2e harness were upstream's. The
fake_llm scenario called save_plan(plan_file_path=...) — upstream's
file-based #1635 contract — while HEAD save_plan takes plan_markdown,
so the plan never saved and PlanReview never rendered (E2E failure on
the plan-review locator).
Pass plan_markdown to save_plan, and revert PlanReview.tsx / plan.ts /
$threadId_.plan.tsx / plan_review.spec.ts to the dev baseline so the
whole plan flow (save -> render -> approve -> implement) is consistent
with the HEAD backend.
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <ramon.nogueira@langchain.dev>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: Caroline di Vittorio <43390382+carolinedivittorio@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>
Co-authored-by: Mukil Loganathan <mukil@langchain.dev>
2026-06-30 16:45:19 -04:00
|
|
|
not valid. ``note`` is required and is posted verbatim as the full GitHub reply body.
|
2026-05-26 16:24:34 -07:00
|
|
|
"""
|
|
|
|
|
if status not in {"resolved", "dismissed"}:
|
|
|
|
|
return {"success": False, "error": f"Invalid status: {status}"}
|
2026-05-28 16:04:38 -07:00
|
|
|
normalized_note = _normalize_note(note)
|
|
|
|
|
if normalized_note is None:
|
|
|
|
|
return {
|
|
|
|
|
"success": False,
|
|
|
|
|
"error": "Resolving or dismissing a finding requires a note with the message to post.",
|
|
|
|
|
}
|
2026-05-26 16:24:34 -07:00
|
|
|
|
|
|
|
|
config = get_config()
|
|
|
|
|
configurable = config.get("configurable", {}) if isinstance(config, dict) else {}
|
|
|
|
|
repo_config = configurable.get("repo") if isinstance(configurable, dict) else None
|
|
|
|
|
pr_number = configurable.get("pr_number") if isinstance(configurable, dict) else None
|
|
|
|
|
if (
|
|
|
|
|
not isinstance(repo_config, dict)
|
|
|
|
|
or not repo_config.get("owner")
|
|
|
|
|
or not repo_config.get("name")
|
|
|
|
|
or not isinstance(pr_number, int)
|
|
|
|
|
):
|
|
|
|
|
return {"success": False, "error": "Missing repo or PR info in run config"}
|
|
|
|
|
|
|
|
|
|
token = get_github_token()
|
|
|
|
|
if not token:
|
|
|
|
|
return {"success": False, "error": "No GitHub token available"}
|
|
|
|
|
|
2026-06-10 10:44:13 -07:00
|
|
|
try:
|
chore: sync upstream/main, defer #1621 modular webhooks (#81)
* chore: bake sfw binary into sandbox image (#1611)
sfw only ships a launcher that fetches its real binary at first run and does a
daily update check against api.github.com/repos/SocketDev/sfw-free. Both fail in
the sandbox (restricted egress; the proxy injects the GitHub App installation
token, which lacks access to that repo), so `sfw yarn install` errors with
"could not fetch its binary". Pin sfw 2.0.6, warm + verify the binary cache at
build, and set SFW_SKIP_UPDATE_CHECK=1 so runs use the baked binary offline.
* feat: editable plan mode + fix review-plan banner overlap (#1610)
* feat: editable plan mode + fix review-plan banner overlap
Lets the thread owner edit the plan markdown by hand from the plan-review
page (Edit -> textarea -> Save) via a new PUT /dashboard/api/plan/{id}
endpoint that re-publishes the plan and mirrors it into the sandbox
plan.md, so approve hands the edited plan to the agent as the source of
truth. Also fixes the collapsed git-panel's floating expand button
covering the "Review plan ->" banner by reserving space for it.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: abort plan approval when the published plan read fails
get_plan_content() swallowed store errors and returned None, so a
transient failure during approve would still mark the plan approved and
dispatch the generic fallback text — silently dropping an owner's edited
plan. Read the plan strictly (raise_on_error=True) so approval aborts
instead, matching the comment read.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show message timestamps (#1609)
* feat: show message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: suppress fallback message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: stable message + tool-call hover timestamps
Stamp a stable client-side arrival time per message and tool call (keyed
by id, persisted to localStorage). Messages render the timestamp inline;
tool rows reveal a dim timestamp chip on hover. Real backend created_at
still takes precedence when present.
* fix: hide client-stamped message timestamps
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add PR trace resolution (#1612)
* feat: add PR trace resolution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: inject reviewer trace context as JSON
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: address review on PR trace resolution
Use the documented LangSmith metadata filter syntax
(and(eq(metadata_key,...), eq(metadata_value,...))) instead of
has(metadata, '{...}'), which does not match runs — _list_thread_runs
was silently returning nothing. Bound full-text searches to a 90-day
window so they don't hit LangSmith's large-window rate limit.
Also folds in the best-effort branch->head-sha resolver (dropping the
weighted scoring/threshold + repo/file evidence + GitHub hydration),
sandbox JSON injection, and the admin "Resolve trace" dry-run endpoint.
The IDOR findings are moot: resolve_pr_to_threads/summarize_agent_session
were removed; resolution now runs deterministically from the trusted run
config with no model-controlled pr_url or thread_id.
* fix: scope branch trace search to the repo
Branch names like fix-tests aren't unique across repos (or older PRs) in
a shared tracing project, so an unscoped branch hit could resolve to an
unrelated thread and write its runs into the reviewer sandbox. Require
the repo slug to co-occur with the branch in matched runs; the full head
SHA stays unscoped since it is globally unique. Addresses open-swe review
on PR #1612.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: include plan links in PR descriptions (#1613)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: gate workflow pushes with approval (#1614)
* feat: gate workflow pushes with approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve proxy refresh test compatibility
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: bind workflow approvals to pushed ref
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: recover thread work as patch (#1615)
* feat: recover thread work as patch
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: search sandbox cwd for recovery patches
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: omit plan link in PR description when no plan exists (#1618)
Plan links in PR descriptions were always built from the thread id, so
runs that never produced a plan linked to an empty plan-review page.
Now the plan content store is consulted first; the link is only added
when a plan with non-empty markdown actually exists. A transient store
failure degrades gracefully (no link) rather than blocking PR creation.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add filter & grouping menu to agents threads sidebar (#1617)
Add a Cursor-style control to the agents sidebar that groups (None/Date/
Status/Project), filters (ownership, status, source, pull request, model,
repo, include-resolved), and compacts the threads list. All client-side over
already-fetched sidebar threads; preferences persist in localStorage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: update langsmith sdk to 0.9.3 (#1616)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: clickable shared PR header in git panel and reviews (#1620)
* feat: clickable shared PR header in git panel and reviews
Replace the standalone "View PR" button in the agent git panel with a
clickable PR title, matching the reviews view. Extract a shared PrHeader
component reused by both the git panel and the review main body.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: drop PrHeader wrapper, use shared component directly
The review-side PrHeader was just a thin adapter mapping detail -> the
shared component's props. Inline it at the call site and use the shared
PrHeader directly so there's a single component.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor: durable interrupt dispatch + completion webhook (#1621)
* wip(rebuild): core reliability spine
- remove PR-babysitting (ci_autofix + ci_monitor graph + webhook wiring)
- dispatch core: agent/dispatch.py with multitask_strategy=interrupt +
durability=sync + completion webhook; reroute all webhook + plan triggers;
drop the racy in-process lock + is_thread_active busy-check
- completion webhook: agent/completion.py + /webhooks/run-complete loopback
route for failure/timeout replies (idempotent)
Co-authored-by: open-swe[bot]
* feat(rebuild): async tools, reconcile, shared http timeouts, assembly tuning
Parallel batch on top of the reliability spine:
- async-ify all 24 tools (drop asyncio.run; requests->httpx); re-implement the
http_request/fetch_url SSRF + DNS-rebinding defense httpx-natively and harden
the IP check to 'not is_global' (+ IPv4-mapped unwrap)
- reconcile.py: stale pending-run sweep (threads.search -> per-thread runs.list
-> cancel_many), wired into the scheduler graph via task='reconcile'
- shared DEFAULT_HTTP_TIMEOUT (agent/utils/http.py) on every bare
httpx.AsyncClient() across utils/dashboard/webapp/middleware
- run budget: MODEL_CALL_RECURSION_LIMIT 5000->250
- fix stale OpenAI->Anthropic fallback id (claude-opus-4-5 -> 4-8)
- drop redundant custom repair middleware (deepagents auto-adds PatchToolCalls)
- confirm tool-result eviction + summarization auto-wired via backend
- slim system prompt ~8% (full harness-profile rewrite deferred)
Co-authored-by: open-swe[bot]
* feat(rebuild): harness-profile prompt + split webhooks out of webapp
- prompt.py: own the system prompt via a registered harness profile
(OPEN_SWE_SHARED_BASE, kept neutral so the read-only reviewer/analyzer that
share it stay safe), registered across all 4 providers; per-thread values
stay in construct_system_prompt. Assembled main-agent prompt ~6.8k -> ~3.1k
tokens (~55% smaller); de-duped PR/commit/suite/force-push guidance; dropped
ALL-CAPS markers.
- webapp.py 3325 -> 1890 LOC: moved 14 per-source handlers into
agent/webhooks/{linear,slack,github}.py; webapp re-exports them for the
routes + tests; moved handlers reach shared helpers via the webapp namespace
to preserve the test suite's monkeypatch targets.
Full suite: 1168 passing, lint clean.
Co-authored-by: open-swe[bot]
* Restore MODEL_CALL_RECURSION_LIMIT to 5000 for long-running tasks
Reverts the 250 cap from the run-budget change — long-running tasks legitimately
need many model calls. The notify_step_limit_reached safety net still fires if a
run does hit the cap, so runs end with a signal either way.
Co-authored-by: open-swe[bot]
* fix: address PR review (auth, SSRF, interrupted status, redirect headers)
- completion.py: drop `interrupted` from failure statuses — with
multitask_strategy=interrupt a follow-up ends the prior run as interrupted,
which is healthy, not a failure to report. [open-swe]
- /webhooks/run-complete: shared-secret auth — dispatch appends ?token= when
RUN_COMPLETE_WEBHOOK_SECRET is set; route verifies via hmac.compare_digest.
[corridor-security]
- SSRF: extract the URL validator to agent/utils/url_safety.py and apply it
before server-side image fetches in multimodal.fetch_image_block.
[corridor-security]
- http_request: preserve caller headers/extensions across redirect hops instead
of dropping them on the first hop. [open-swe]
Co-authored-by: open-swe[bot]
* chore: remove REBUILD_PLAN.md (planning doc, not needed in the repo)
Co-authored-by: open-swe[bot]
* fix: fail closed on run-complete webhook auth when secret unset
Corridor follow-up: verify_run_complete_token returns False (not True) when
RUN_COMPLETE_WEBHOOK_SECRET is unset, so the public route is never
unauthenticated. Logs a startup warning when the secret is absent, and dispatch
skips registering the webhook when there's no secret (no rejected callbacks).
Co-authored-by: open-swe[bot]
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: restore forced tool call to prevent premature run stops (#1622)
Restore the ensure_no_empty_msg middleware and the always-call-a-tool system-prompt instruction that #1535 removed. When the model emits a message with no tool call (and hasn't already messaged the user or confirmed completion), the middleware re-injects a no_op / confirming_completion tool call so the run continues instead of ending mid-task.
Shipping to test whether it fixes runs that stop halfway through.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore(deps): bump langgraph-checkpoint from 4.1.0 to 4.1.1 (#1619)
Bumps [langgraph-checkpoint](https://github.com/langchain-ai/langgraph) from 4.1.0 to 4.1.1.
- [Release notes](https://github.com/langchain-ai/langgraph/releases)
- [Commits](https://github.com/langchain-ai/langgraph/compare/checkpoint==4.1.0...checkpoint==4.1.1)
---
updated-dependencies:
- dependency-name: langgraph-checkpoint
dependency-version: 4.1.1
dependency-type: indirect
...
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
* fix: post reviewer resolution notes verbatim (#1624)
* fix: post reviewer resolution notes verbatim
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: stabilize dashboard follow-up e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make e2e attribution marker durable
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: only echo found e2e attribution
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: check live dashboard attribution in e2e
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* hotfix: stop prompting agent/reviewer to wrap installs in sfw (#1625)
Installs hung when prefixed with sfw inside the sandbox (trace 019f0608
stalled on a pending `sfw npm install` execute, never returned). Strip the
Socket Firewall guidance from the agent and reviewer prompts so installs run
through the project's package manager directly. sfw stays in the Docker image;
nothing invokes it now.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: make plan view mobile friendly (#1636)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: fall back to vision model for image threads (#1626)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: surface Slack thread errors (#1627)
* fix: surface Slack thread errors
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: don't set failure_reply_posted on Slack preprocessing errors
The preprocessing error handler was setting failure_reply_posted=True,
the same idempotency flag handle_run_completion checks to suppress
duplicate run-failure replies. Since preprocessing failures happen
before any run exists but the flag persists on the thread, a subsequent
run failure on the same thread would be silently ignored.
The preprocessing handler already posts its own Slack reply, so the
run-completion idempotency flag should not be set here.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: avoid recapping Slack replies (#1629)
* chore: avoid recapping Slack replies
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: simplify Slack reply prompt wording
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: update Slack trace reply on web handoff (#1630)
* fix: update Slack trace reply on web handoff
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: trigger web handoff on dashboard starts
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: format web handoff as contextual fragment
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve trace_message_ts when overwriting Slack run mapping
When store_slack_run_mapping is called without trace_message_ts (e.g. on
follow-up Slack mentions), it was unconditionally overwriting the
thread-level mapping and clobbering the timestamp captured from the
initial trace reply. After that, _notify_slack_web_handoff could not find
the original message, so a subsequent move to Web silently skipped the
Slack trace update.
Now, when trace_message_ts is not passed, the existing thread mapping is
read first and its trace_message_ts is preserved.
* style: ruff format
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* fix: pre-bundle shiki/@pierre deps to stop dev dynamic-import failures (#1643)
* fix(ui): pre-bundle shiki/@pierre deps to stop dev dynamic-import failures
shiki lazy-imports a grammar per language and these libs only live inside
lazy route components, so Vite's startup scanner never sees them. They get
discovered on first thread navigation, triggering a dep re-optimize +
force-reload that aborts the in-flight route-chunk import, surfacing as
"Failed to fetch dynamically imported module: .../$threadId.tsx".
Pre-bundle them (and the github themes + common code-block languages) via
optimizeDeps.include so the optimize happens once at startup. Dev-only;
production bundles are unaffected.
* fix: pre-bundle canonical shiki docker/make langs instead of aliases
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: show queued dashboard follow-ups (#1631)
* feat: show queued dashboard follow-ups
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: de-dupe queued follow-ups while streaming
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: notify Slack on plan approval (#1632)
* feat: notify Slack on plan approval
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: post Slack approval notice after successful dispatch
Move the _maybe_post_plan_approved_to_slack call until after
_dispatch_followup succeeds so the Slack thread is not told
implementation is beginning before the LangGraph run is created.
Addresses PR review comment.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
* feat: include Slack channel context in prompts (#1633)
Add cached Slack channel metadata enrichment for Slack-triggered runs so prompts can include channel names and descriptions without duplicate conversations.info calls.\n\nCo-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
* chore: keep plan guidance high-level (#1634)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: publish plans from sandbox files (#1635)
* feat: publish plans from sandbox files
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: avoid fixed plan filenames
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: virtualize local sandbox file paths
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: preserve plan_file_path across set_plan_status
set_plan_status was rewriting the content record with only markdown
and status, dropping plan_file_path. After a reject, the owner's
dashboard edit would mirror to a different file than the agent's
original, and the next save_plan could republish the stale file.
Preserve plan_file_path when updating status.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: return to thread after plan approval (#1637)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Slack breakout thread tool (#1638)
* feat: add Slack breakout thread tool
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: make fake LLM scripts declarative
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: exclude slack_start_new_thread from plan mode
The breakout tool can dispatch a fresh agent run that starts outside the
current plan-mode state, bypassing the approval flow. Add it to
PLAN_MODE_EXCLUDED_TOOLS so it's hidden alongside the other mutating
tools while planning.
---------
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: require bun for ui agent work (#1639)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: request actions read for sandbox logs (#1642)
* fix: request actions read for sandbox logs
Request optional Actions read permission for sandbox proxy tokens, with fallback for installations that have not approved it yet. Update setup docs and prompt guidance for safe GitHub Actions log usage.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: restore actions:read scope after workflow push
After an approved workflow push, the guard was restoring the proxy with
BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS, which excludes the actions: read
scope this PR adds. Restore with RUNTIME_PROXY_TOKEN_PERMISSIONS (which
includes actions: read) and fall back to BASE if the install hasn't
granted Actions read — mirroring the pattern in _create_sandbox_with_proxy.
Addresses review comment on PR #1642.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: widen split review diffs (#1647)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: install missing deps before verification (#1646)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm (#1645)
* chore: require pnpm for ui agent work
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: switch ui to pnpm
Replace Bun and Yarn lockfiles with pnpm lockfile and update UI/Vercel commands to use pnpm.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* ci: use corepack for ui pnpm e2e build
Run pnpm through Corepack in the E2E global setup so CI can use the pinned package manager without a separate pnpm install step.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add Sonnet 5 to model picker (#1651)
* chore: update Sonnet examples to Sonnet 5
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* chore: add Sonnet 5 to model picker
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* Remove dead breakout-thread e2e scenario after dropping the tool
The merge resolution deferred upstream's Slack breakout-thread tool
(slack_start_new_thread, #1638) since it depends on the #1621 dispatch
module, but the e2e harness still scripted it. Removing the tool name
from fake_llm.py's _tool_step call left a malformed scenario, crashing
the langgraph-dev web server at import (TypeError: _tool_step() missing
'call_id') and failing Playwright E2E.
Drop the "breakout" script scenario, its _is_breakout_request helper +
ScriptRule, and the corresponding full_flow.spec.ts test.
* Revert upstream pnpm switch; keep bun for the UI build
The merge auto-adopted upstream's pnpm switch (#1645) in tests/e2e/
global-setup.ts and ui/package.json, but our fork builds the UI with
bun (vercel.json + the E2E workflow's setup-bun). That left the
Playwright globalSetup running `corepack pnpm install --frozen-lockfile`
with no pnpm-lock.yaml, failing E2E at UI build time.
Revert global-setup.ts and ui/package.json to the dev (bun) baseline,
drop the merge-added ui/pnpm-lock.yaml, and remove the re-added
ui/AGENTS.md (our fork had deleted it).
* Align plan-review e2e + UI with the HEAD (pre-#1635) backend
The merge left a split plan vertical: the backend save_plan/plan_api are
HEAD (we deferred the editable-plan/sandbox-publish features #1610/#1635/
#1637 per #80), but the plan UI and e2e harness were upstream's. The
fake_llm scenario called save_plan(plan_file_path=...) — upstream's
file-based #1635 contract — while HEAD save_plan takes plan_markdown,
so the plan never saved and PlanReview never rendered (E2E failure on
the plan-review locator).
Pass plan_markdown to save_plan, and revert PlanReview.tsx / plan.ts /
$threadId_.plan.tsx / plan_review.spec.ts to the dev baseline so the
whole plan flow (save -> render -> approve -> implement) is consistent
with the HEAD backend.
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Johannes du Plessis <johannes@langchain.dev>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Ramon Nogueira <ramon.nogueira@langchain.dev>
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com>
Co-authored-by: Caroline di Vittorio <43390382+carolinedivittorio@users.noreply.github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>
Co-authored-by: Mukil Loganathan <mukil@langchain.dev>
2026-06-30 16:45:19 -04:00
|
|
|
result = await _resolve_finding_thread_async(
|
|
|
|
|
finding_id=finding_id,
|
|
|
|
|
status=status,
|
|
|
|
|
note=normalized_note,
|
|
|
|
|
owner=str(repo_config["owner"]),
|
|
|
|
|
repo=str(repo_config["name"]),
|
|
|
|
|
pr_number=pr_number,
|
|
|
|
|
token=token,
|
2026-05-26 16:24:34 -07:00
|
|
|
)
|
2026-06-10 10:44:13 -07:00
|
|
|
except ReviewerThreadMissingError as exc:
|
|
|
|
|
return thread_missing_tool_result(exc)
|
feat: outcomes dataset + bootstrap/continual split via skills (#1365)
* fix: reset stale sandbox creation sentinel
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
* fix: treat SANDBOX_CREATING as a timestamped cross-process lock
Only reset the sentinel when proven stale (older than the creation
timeout); otherwise wait for the worker that holds the lock so a
concurrent run does not create a duplicate sandbox.
* feat(analyzer): outcomes dataset + bootstrap/continual split via skills
Rename the review_style_analyzer graph to `analyzer` and split it into two
modes, plus capture reviewer finding outcomes for continual learning.
- Outcomes dataset: upsert resolved-by-commit (positive), dismissed (false
positive), and GitHub/Slack thumbs findings into a single LangSmith dataset
(openswe-reviewer-outcomes), keyed deterministically per finding+source.
Emit points wired into update_finding, resolve_finding_thread, and the
GitHub/Slack reaction handlers.
- Two playbooks delivered as deepagents skills (bootstrap-repo-analysis,
continual-learning), served as virtual files via a CompositeBackend /skills/
route + StateBackend (seeded into the run files channel at invoke time, never
written to the sandbox). Mode is set by the launcher; continual runs fall
back to the GitHub App installation token.
- Split launcher into start_bootstrap_analysis + start_continual_run; register
a per-repo nightly continual-learning cron when bootstrap completes.
- New read_finding_outcomes tool feeds confirmed/dismissed findings back to the
continual playbook.
Tests for outcome label mapping, skills helper, and cron idempotency.
* fix(analyzer): anchor continual cron runs to a real thread_id
The nightly continual-learning cron is threadless, and get_analyzer
early-returns an empty agent when configurable.thread_id is missing — so
every cron-launched run no-op'd before reading outcomes or saving a refined
prompt. Include the repo's deterministic analyzer thread_id in the continual
run configurable so the run executes; the threadless run carries no message
history, so nightly runs don't accumulate context.
* refactor(analyzer): move cron lifecycle calls out of the review-styles store
Drop the inline `analyzer_cron` imports from review_styles.py (added only to
dodge a circular import) by relocating the cron-trigger calls to the layer
above the store: registration to the save_review_style tool (after a prompt is
saved) and removal to the dashboard delete route. review_styles.py is now a
pure store again with top-level imports only.
* refactor: hoist reviewer_outcomes imports to module level
Move the two inline emit_finding_status_outcome imports introduced in this PR
(update_finding, resolve_finding_thread) to top-level imports. reviewer_outcomes
only depends on langsmith, so there is no circular import to avoid.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-01 13:25:12 -07:00
|
|
|
if result.get("success") and isinstance(result.get("finding"), dict):
|
|
|
|
|
thread_id = configurable.get("thread_id") if isinstance(configurable, dict) else None
|
|
|
|
|
emit_finding_status_outcome(
|
|
|
|
|
result["finding"],
|
|
|
|
|
status,
|
|
|
|
|
configurable=configurable,
|
|
|
|
|
thread_id=thread_id if isinstance(thread_id, str) else None,
|
|
|
|
|
)
|
|
|
|
|
return result
|
2026-05-26 16:24:34 -07:00
|
|
|
|
|
|
|
|
|
|
|
|
|
async def _resolve_finding_thread_async(
|
|
|
|
|
*,
|
|
|
|
|
finding_id: str,
|
|
|
|
|
status: str,
|
2026-05-28 16:04:38 -07:00
|
|
|
note: str,
|
2026-05-26 16:24:34 -07:00
|
|
|
owner: str,
|
|
|
|
|
repo: str,
|
|
|
|
|
pr_number: int,
|
|
|
|
|
token: str,
|
|
|
|
|
) -> dict[str, Any]:
|
|
|
|
|
thread_id = get_thread_id_from_runtime()
|
2026-05-27 10:52:30 -07:00
|
|
|
finding = await _get_finding_with_pr_backfill(
|
|
|
|
|
thread_id=thread_id,
|
|
|
|
|
finding_id=finding_id,
|
|
|
|
|
owner=owner,
|
|
|
|
|
repo=repo,
|
|
|
|
|
pr_number=pr_number,
|
|
|
|
|
token=token,
|
|
|
|
|
)
|
2026-05-26 16:24:34 -07:00
|
|
|
if finding is None:
|
|
|
|
|
return {"success": False, "error": f"No finding found with id {finding_id}"}
|
|
|
|
|
|
2026-05-27 10:52:30 -07:00
|
|
|
github_thread_ids = _thread_ids_for_finding(finding)
|
|
|
|
|
for comment_id in _comment_ids_for_finding(finding):
|
|
|
|
|
thread_node_id = await fetch_review_thread_id_for_comment(
|
2026-05-26 16:24:34 -07:00
|
|
|
owner=owner,
|
|
|
|
|
repo=repo,
|
|
|
|
|
pr_number=pr_number,
|
|
|
|
|
review_comment_id=comment_id,
|
|
|
|
|
token=token,
|
|
|
|
|
)
|
2026-05-27 10:52:30 -07:00
|
|
|
if thread_node_id and thread_node_id not in github_thread_ids:
|
|
|
|
|
github_thread_ids.append(thread_node_id)
|
|
|
|
|
if not github_thread_ids:
|
2026-05-26 16:24:34 -07:00
|
|
|
return {"success": False, "error": "Could not resolve GitHub review thread id"}
|
|
|
|
|
|
2026-05-27 10:52:30 -07:00
|
|
|
resolved_thread_ids = _str_list(finding.get("github_resolved_thread_ids"))
|
2026-05-28 12:44:00 -07:00
|
|
|
posted_resolution_comment_ids = _int_list(finding.get("github_posted_resolution_comment_ids"))
|
|
|
|
|
comment_ids = _comment_ids_for_finding(finding)
|
|
|
|
|
resolution_body = render_resolution_comment(finding, status, note=note)
|
2026-05-28 16:04:38 -07:00
|
|
|
if resolution_body is None:
|
|
|
|
|
return {"success": False, "error": "Missing resolution note"}
|
2026-05-28 12:44:00 -07:00
|
|
|
|
2026-05-27 10:52:30 -07:00
|
|
|
resolved_count = 0
|
2026-05-28 12:44:00 -07:00
|
|
|
for idx, github_thread_id in enumerate(github_thread_ids):
|
2026-05-27 10:52:30 -07:00
|
|
|
if github_thread_id in resolved_thread_ids:
|
|
|
|
|
continue
|
2026-05-28 12:44:00 -07:00
|
|
|
primary_comment_id = comment_ids[idx] if idx < len(comment_ids) else None
|
|
|
|
|
if primary_comment_id and primary_comment_id not in posted_resolution_comment_ids:
|
|
|
|
|
reply = await reply_to_review_comment(
|
|
|
|
|
owner=owner,
|
|
|
|
|
repo=repo,
|
|
|
|
|
pr_number=pr_number,
|
|
|
|
|
review_comment_id=primary_comment_id,
|
|
|
|
|
body=resolution_body,
|
|
|
|
|
token=token,
|
|
|
|
|
)
|
|
|
|
|
if reply and isinstance(reply.get("id"), int):
|
|
|
|
|
posted_resolution_comment_ids.append(primary_comment_id)
|
2026-05-27 10:52:30 -07:00
|
|
|
ok = await resolve_review_thread(thread_node_id=github_thread_id, token=token)
|
|
|
|
|
if ok:
|
|
|
|
|
resolved_thread_ids.append(github_thread_id)
|
|
|
|
|
resolved_count += 1
|
|
|
|
|
if resolved_count == 0 and not all(
|
|
|
|
|
github_thread_id in resolved_thread_ids for github_thread_id in github_thread_ids
|
|
|
|
|
):
|
2026-05-26 16:24:34 -07:00
|
|
|
return {"success": False, "error": "GitHub did not resolve the review thread"}
|
|
|
|
|
|
|
|
|
|
updates: dict[str, Any] = {
|
|
|
|
|
"status": status,
|
2026-05-27 10:52:30 -07:00
|
|
|
"github_review_thread_id": github_thread_ids[0],
|
|
|
|
|
"github_review_thread_ids": github_thread_ids,
|
|
|
|
|
"github_resolved_thread_ids": resolved_thread_ids,
|
|
|
|
|
"github_thread_resolved": all(
|
|
|
|
|
github_thread_id in resolved_thread_ids for github_thread_id in github_thread_ids
|
|
|
|
|
),
|
2026-05-26 16:24:34 -07:00
|
|
|
}
|
2026-05-28 16:04:38 -07:00
|
|
|
updates["last_reconciliation_note"] = note
|
|
|
|
|
updates["resolution_note"] = note
|
2026-05-28 12:44:00 -07:00
|
|
|
if posted_resolution_comment_ids:
|
|
|
|
|
updates["github_posted_resolution_comment_ids"] = posted_resolution_comment_ids
|
2026-05-26 16:24:34 -07:00
|
|
|
updated = await update_finding_fields(thread_id, finding_id, updates)
|
2026-05-27 17:26:08 -07:00
|
|
|
surface_updates: dict[str, Any] = {
|
|
|
|
|
"state": "resolved" if updates["github_thread_resolved"] else "resolve_pending",
|
|
|
|
|
"github_review_thread_id": github_thread_ids[0],
|
|
|
|
|
"last_error": None
|
|
|
|
|
if updates["github_thread_resolved"]
|
|
|
|
|
else "Not all GitHub threads resolved",
|
|
|
|
|
}
|
|
|
|
|
await update_finding_surface(thread_id, finding_id, surface_updates)
|
|
|
|
|
updated = await get_finding(thread_id, finding_id)
|
2026-05-27 10:52:30 -07:00
|
|
|
return {"success": True, "finding": updated, "resolved_thread_count": resolved_count}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
async def _get_finding_with_pr_backfill(
|
|
|
|
|
*,
|
|
|
|
|
thread_id: str,
|
|
|
|
|
finding_id: str,
|
|
|
|
|
owner: str,
|
|
|
|
|
repo: str,
|
|
|
|
|
pr_number: int,
|
|
|
|
|
token: str,
|
|
|
|
|
) -> Finding | None:
|
|
|
|
|
finding = await get_finding(thread_id, finding_id)
|
|
|
|
|
if finding is None:
|
|
|
|
|
return None
|
|
|
|
|
if _thread_ids_for_finding(finding) or _comment_ids_for_finding(finding):
|
|
|
|
|
return finding
|
|
|
|
|
|
|
|
|
|
review_threads = await fetch_pr_review_threads(
|
|
|
|
|
owner=owner,
|
|
|
|
|
repo=repo,
|
|
|
|
|
pr_number=pr_number,
|
|
|
|
|
token=token,
|
|
|
|
|
)
|
|
|
|
|
if review_threads:
|
|
|
|
|
await reconcile_findings_with_review_threads(thread_id, review_threads)
|
|
|
|
|
finding = await get_finding(thread_id, finding_id)
|
|
|
|
|
return finding
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _int_list(value: Any) -> list[int]:
|
|
|
|
|
if not isinstance(value, list):
|
|
|
|
|
return []
|
|
|
|
|
return [item for item in value if isinstance(item, int)]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _str_list(value: Any) -> list[str]:
|
|
|
|
|
if not isinstance(value, list):
|
|
|
|
|
return []
|
|
|
|
|
return [item for item in value if isinstance(item, str) and item]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _comment_ids_for_finding(finding: dict[str, Any]) -> list[int]:
|
|
|
|
|
comment_ids = _int_list(finding.get("github_review_comment_ids"))
|
|
|
|
|
comment_id = finding.get("github_review_comment_id")
|
|
|
|
|
if isinstance(comment_id, int) and comment_id not in comment_ids:
|
|
|
|
|
comment_ids.insert(0, comment_id)
|
|
|
|
|
return comment_ids
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _thread_ids_for_finding(finding: dict[str, Any]) -> list[str]:
|
|
|
|
|
thread_ids = _str_list(finding.get("github_review_thread_ids"))
|
|
|
|
|
thread_id = finding.get("github_review_thread_id")
|
|
|
|
|
if isinstance(thread_id, str) and thread_id and thread_id not in thread_ids:
|
|
|
|
|
thread_ids.insert(0, thread_id)
|
|
|
|
|
return thread_ids
|