mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 09:13:14 +00:00
81 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Adam Moussa
|
e9da186b5f
|
fix(open-swe): port core GitHub-App scope fallback (#1701), workflows:write kept out of standing scope (#181)
* fix: fall back to core GitHub App scope when optional grants missing (#1701) * fix: fall back to core GitHub App scope when optional grants missing Proxy-token minting requested workflows:write and actions:read in the permission set used for every sandbox. GitHub 422s a token request that asks for a permission the installation hasn't granted, so any install without workflows:write failed to mint a token and every run died in before-agent setup with "GitHub App installation token is unavailable". _resolve_proxy_token now walks a permission ladder (full -> +workflows -> core) and returns the first scope that mints, recording the granted scope so hourly proxy refreshes stay consistent. A missing optional grant now degrades to the install-time core scope instead of failing the run; workflow-file HITL pushes still require workflows:write and fail at push time when it is absent. * refactor: flatten proxy-token ladder loop with continue --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> (cherry picked from commit f53caff1aa24a7b29d851b267aa3bdfe62c1e935) Sea Haven fork deviation: upstream #1701 folds workflows:write into the standing BASE/RUNTIME scope. This fork deliberately keeps workflows:write OUT of the standing permission ladder (RUNTIME = core + actions:read; LADDER = (RUNTIME, CORE)) so the sandbox proxy token cannot push .github/workflows/* during normal operation. workflows:write is minted only transiently by WorkflowPushGuardMiddleware for an approved HITL push and dropped on restore, preserving token scope as a backstop for the workflow- push approval control. Security-reviewed (agentic fan-out + GPT-4.1 cross review); the standing-scope-carries-workflows:write bypass was blocked. * fix(open-swe): harden proxy-token restore and mint error handling Two low-severity follow-ups from the security review of the #1701 port. Restore the recorded baseline scope after a workflow-push elevation instead of a hardcoded RUNTIME. An install granted workflows:write but not actions:read resolves its standing token to core; hardcoding RUNTIME on restore requested the ungranted actions:read, 422'd, and fired a false "SECURITY: failed to downscope" error on every approved workflow push before the core fallback recovered. The guard now captures the run's recorded scope before elevating (via the new get_recorded_proxy_permissions) and restores exactly that, falling back to the guaranteed core scope only when the baseline restore fails. Classify installation-token mint failures. get_github_app_installation_token_ with_expiry now treats HTTP 422 (a permission the installation hasn't granted) as the ladder's expected descend signal and keeps it at debug, while a non-422 failure (network/5xx/timeout) is surfaced at WARNING even when errors are otherwise suppressed — so a transient blip no longer silently downscopes a whole run under a debug-only trace. The reduced-scope warning no longer asserts a missing grant as the sole cause. * chore(triage): mark upstream #1701 landed on this branch Ported via PR #181 as Option A (workflows:write kept out of the standing proxy-token scope). Regenerated triage.md from triage.jsonl. --------- Co-authored-by: Ramon Nogueira <ramon.nogueira@langchain.dev> |
||
|
Adam Moussa
|
5350b63c85
|
feat(open-swe): re-add Fable 5 behind an admin toggle (Bedrock) (#172)
Some checks are pending
CI / Lint (push) Waiting to run
CI / Format check (push) Waiting to run
CI / Typecheck (push) Waiting to run
CI / Unit tests (push) Waiting to run
CI / Playwright E2E (push) Waiting to run
CI / Docker build smoke (push) Waiting to run
CI / Triage ledger up to date (push) Waiting to run
CI / ui bun.lock in sync (push) Waiting to run
* feat(models): re-add Fable 5 with admin disable toggle (port of upstream #1677) * refactor(models): convert re-added Fable 5 to Bedrock model IDs * fix(open-swe): correct Fable copy to describe provider data sharing, not ZDR The ported admin toggle description and code comments described Fable 5 as incompatible with Zero Data Retention. That is backwards: Fable 5 requires the account to opt into Bedrock provider_data_share — prompts/completions are retained and shared with Anthropic (up to 30 days, incl. human review). The old UI copy would lead an admin to believe the opposite of what enabling the toggle does. Reword the toggle description and the gate_fable_model / team_settings comments accordingly. Still off by default. Refs #171. |
||
|
seahaven-openswe[bot]
|
0546085672
|
feat: port durable dispatch hardening and startup latency improvements (#160)
Some checks are pending
CI / Lint (push) Waiting to run
CI / Format check (push) Waiting to run
CI / Unit tests (push) Waiting to run
CI / Playwright E2E (push) Waiting to run
CI / Docker build smoke (push) Waiting to run
CI / Triage ledger up to date (push) Waiting to run
CI / ui bun.lock in sync (push) Waiting to run
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
-
|
||
|
seahaven-openswe[bot]
|
c2bc7720cd
|
feat: port LangSmith LLM Gateway routing from upstream (#1671, #1673, #1674, #1678) (#155)
Some checks are pending
CI / Lint (push) Waiting to run
CI / Format check (push) Waiting to run
CI / Unit tests (push) Waiting to run
CI / Playwright E2E (push) Waiting to run
CI / Docker build smoke (push) Waiting to run
CI / Triage ledger up to date (push) Waiting to run
CI / ui bun.lock in sync (push) Waiting to run
* feat: port LangSmith LLM Gateway routing from upstream (#1671, #1673, #1674, #1678) Ports four upstream commits that add opt-in LLM call routing through the LangSmith Gateway, preserving fork conventions (Bedrock/Fireworks model IDs, no-agent-attribution, bun toolchain). - #1671 (e9dc6e01): opt-in gateway routing — new gateway.py, team-settings toggle, admin UI section, wired into make_model for all graph entrypoints - #1673 (702ef908): dedicated LANGSMITH_GATEWAY_API_KEY precedence over platform LANGSMITH_API_KEY - #1674 (5f7c2f46): fix Fireworks gateway base URL to /fireworks (bare host, SDK appends /v1/chat/completions) + SanitizeFireworksMessagesMiddleware - #1678 (73b7d1c0): fix OpenAI Responses reasoning replay — SanitizeOpenAIResponsesMiddleware, store/include config for encrypted reasoning content, reasoning_effort coercion for Chat Completions fallback Refs #134 * fix: downgrade gateway not-routed log to debug, add Bedrock UI note, add sanitizer parity - Downgrade logger.warning to logger.debug in gateway_overrides for not-routed providers and missing API key (Bedrock is the default provider in this fork, so these are expected steady states) - Add Bedrock to the LLMGatewaySection route-toggle description so admins know it is not routed through the gateway - Add SanitizeOpenAIResponsesMiddleware to chat.py for parity with server.py and reviewer.py - Restore the Bedrock region comment in model.py that explains the AWS_REGION / AWS_DEFAULT_REGION precedence Refs #138 --------- Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com> |
||
|
Adam Moussa
|
b65a99f3e9
|
feat: re-land scoped AGENTS auto-load (#1684) + platform issue reporting tool (#1685) (#129)
* feat: auto-load scoped AGENTS on reads (#1684) Adapted from upstream langchain-ai/open-swe #1684 to the fork's direct-import middleware registry and middleware stack ordering. Adds SubdirAgentsReadMiddleware, which appends applicable ancestor AGENTS.md instructions to read_file results once per run, so scoped rules are visible before edits. Wired into get_agent immediately after ToolErrorMiddleware, matching upstream's relative position. Note: this changes file-read behavior for every main-agent run. The reviewer graph uses its own leaner middleware stack and is unaffected. (cherry picked from commit 7f7af71547be2199cea699284676f8ceefba7691) * feat: add platform issue reporting tool (#1685) Adapted from upstream langchain-ai/open-swe #1685 to the fork's direct-import tool registry. Adds the report_platform_issue tool (stdlib-only: returns a locally generated UUIDv7 report id, no external network call) and wires it into get_agent's curated tool list. Dropped upstream's test_task_retry_wraps_inside_tool_error_middleware assertion, which references ToolRetryMiddleware that this fork does not wire into the middleware stack. (cherry picked from commit 88b62322b44103335773002d0745704cd96e9160) --------- Co-authored-by: Ramon Nogueira <ramon.nogueira@langchain.dev> |
||
|
Adam Moussa
|
b3b0274403
|
feat: Re-land deferred upstream features on modular webhooks (#80) (#128)
* fix(webhooks): fall back to vision model for Slack/Linear image threads Re-land upstream #1626 onto the modular webhook structure. When a Slack mention or Linear issue carries images but the resolved model is text-only, fall back to a vision-capable model instead of dropping the images. Re-points default_vision_model_pair at the fork's image-capable models (Opus 4.8 default, else any supports_images model) rather than upstream's openai:/anthropic: provider filter. Refs #80, upstream #1626 * fix(slack): persist trace_message_ts so web-handoff updates the trace reply Re-land upstream #1630 onto the modular structure. The first-mention store_slack_run_mapping call did not pass trace_message_ts, so it was never persisted (nothing to preserve from on first mention) and _notify_slack_web_handoff always skipped the trace-reply update on web handoff. Pass it through and cover it with a test. Refs #80, upstream #1630 * feat(slack): include channel context in Slack prompts Re-land upstream #1633 onto the modular structure. Fetch cached Slack channel metadata once per event (_get_slack_channel_context) and thread it through the docs-plz gate, repo resolution, and process_slack_mention so prompts carry the channel name and a clearly-marked untrusted channel description. Avoids duplicate conversations.info calls. Refs #80, upstream #1633 * feat(tools): add slack_start_new_thread breakout tool Re-land upstream #1638 onto the modular structure. Adds the slack_start_new_thread tool (posts a top-level Slack message and dispatches a fresh agent run for a broken-out task via the durable dispatch_agent_run contract), wires it into the agent tool list and tools/__init__, adds prompt guidance, and excludes it from plan mode so it can't bypass the approval flow. Tool imports only live modules. Refs #80, upstream #1638 * feat(plan): notify Slack on plan approval Re-land upstream #1632 onto the modular structure. When a plan is approved via the dashboard approve endpoint, post a thread reply to the originating Slack thread noting the comment count and approver, after the follow-up run is dispatched. Slack post failures never break approval. Adapted to the fork's approve_plan (no plan_markdown read). Refs #80, upstream #1632 * feat(plan): publish plans from sandbox files Re-land upstream #1635 onto the modular structure, completing the partially-ported change so dev is internally consistent. save_plan now takes a plan_file_path, reads the agent-authored Markdown file from /workspace/plans/ (validating extension/location/UTF-8/size) and publishes it, instead of taking a plan_markdown string. Removes write_file/edit_file from PLAN_MODE_EXCLUDED_TOOLS so the agent can author the plan file, updates enter_plan_mode/reject_plan guidance and the e2e fake LLM. Skips the #1610-only update_plan hunk (not on dev). Refs #80, upstream #1635 * fix(security): SSRF-harden server-side image fetch + stop logging raw image URLs INJ-01 (high): fetch_image_block used follow_redirects=True with no per-hop revalidation and discarded the resolved-IP pin, so an attacker-authored Slack/ Linear image URL could 302-redirect the fetch to an internal host / cloud metadata endpoint (blind SSRF), and DNS-rebinding could bypass the one-shot is_url_safe check. Route image fetches through the same per-hop resolve+pin+ revalidate loop the http_request tool uses, lifted into url_safety as the shared request_with_safe_redirects. Also strip the per-host Slack/Linear bearer token on redirect so it can't be replayed to a redirect target. SC-1 (low): linear.py logged full image URLs (which can carry signed tokens) at DEBUG; multimodal logged them at INFO on every fetch. Log host-only. Sink lived in multimodal.py (unchanged by the feature work) but PR #128 widened its reach by no longer dropping images for text-only models. Fixing on the base branch so #130/#129 inherit it on rebase. Adds fetch_image_block SSRF regression tests (redirect-to-internal blocked; auth stripped on redirect). |
||
|
Ramon Nogueira
|
3c6077c418
|
feat: add Slack reaction tool (#1650)
Co-authored-by: Ramon Nogueira <270434257+ramon-langchain@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> (cherry picked from commit ee224d3e91576f771e93df7bad4523a7a7036324) |
||
|
Ramon Nogueira
|
b2b49ed944
|
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>
(cherry picked from commit
|
||
|
seahaven-openswe[bot]
|
9f7a1cc481
|
feat: post scheduled-run report to a configured Slack channel (#83)
* Post scheduled-run reports to a Slack channel Scheduled runs previously had no source channel and finished silently in the dashboard. Allow an automation to post its final report to a configured Slack channel as the bot, reusing existing Slack plumbing instead of the deferred run-completion webhook. Refs: #82 * Reconcile Slack report feature with dev merge Dev refactored slack_thread_reply to async and already added post_slack_top_level_message_with_ts; drop the duplicate definition and await the tool in the feature's tests. Refs: #82 * Harden scheduled Slack report channel posting The no-thread_ts top-level path fired for every slack_thread_reply call during a scheduled run, spraying disconnected messages and dead interactive buttons into the report channel. Cap top-level posts at one per run and drop options/plan_approval blocks in that mode, so the mechanism (not just the prompt) enforces a single clean report. Also tighten the channel-ID regex to require a leading letter and document why top-level posts store no run mapping. Refs: #82 --------- Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com> |
||
|
Adam Moussa
|
1f060f2a1d
|
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> |
||
|
Adam Moussa
|
a4ed19ba61
|
feat: migrate model providers to Bedrock (Claude) + Fireworks (everything else) (#62)
Some checks failed
CI / Lint (push) Waiting to run
CI / Format check (push) Waiting to run
CI / Unit tests (push) Waiting to run
CI / Playwright E2E (push) Waiting to run
Build & publish app artifacts / Publish + deploy (dev) (push) Has been cancelled
Build & publish app artifacts / Publish + deploy (prod) (push) Has been cancelled
Infra CD / Infra CI (pre-deploy) (push) Has been cancelled
Infra CD / Deploy open-swe-dev (push) Has been cancelled
Infra CD / Deploy open-swe-prod (push) Has been cancelled
* feat: switch model providers to AWS Bedrock (Claude) and Fireworks (non-Claude)
Migrate off direct provider APIs: AWS Bedrock for Anthropic/Claude via the
cross-region inference profile us.anthropic.claude-opus-4-8, Fireworks AI for
all non-Claude models. Drop OpenAI (gpt-5.5) and Google (gemini-3.5-flash)
entirely. DEFAULT_MODEL_ID is now Bedrock Claude; all Fireworks models stay
freely selectable for the agent and reviewer graphs and via team/profile
defaults.
- pyproject: add langchain-aws (ChatBedrockConverse + boto3)
- options.py: Bedrock Claude entry + default; remove openai/google entries
- model.py: bedrock_converse provider_model_kwargs (effort -> thinking budget),
region pin in make_model, bedrock<->fireworks fallback pairing, AWS_REGION/
FIREWORKS_API_KEY local-dev validation
- server.py: provider-aware fallback kwargs build
- sanitize_thinking_blocks: also sanitize ChatBedrockConverse thinking blocks
- model_fallback: treat transient botocore ClientError codes as fallback-worthy
- eval_jobs: repoint hardcoded eval model id to Bedrock Claude
- tests: repoint dropped model ids; drop obsolete google test module
* fix(bedrock): use adaptive thinking + output_config.effort for Opus 4.8
The handoff spec wired Bedrock Converse thinking as
{type: enabled, budget_tokens: N}, but Opus 4.7+ rejects that with a
ValidationException: thinking.type "enabled" is not supported; it requires
thinking.type "adaptive" plus output_config.effort. Verified by live invoke
against us.anthropic.claude-opus-4-8 (account 328440206208, us-east-1):
the enabled+budget shape 400s, adaptive+effort returns normally.
Map profile effort to additional_model_request_fields:
{thinking: {type: adaptive, display: summarized},
output_config: {effort: <low|medium|high|xhigh|max>}}
reusing anthropic_thinking_for/anthropic_effort_for. Update the two
subagent-model tests asserting the old shape.
* fix(deploy): seed Bedrock/Fireworks models, not the dropped anthropic:/openai: ids
Model selection is store-driven, so seed_store.sh's team_settings/default seed is
what runs in prod. It still seeded the removed providers, which would fail at runtime
after the migration:
- agent/builder: anthropic:claude-opus-4-8 -> bedrock_converse:us.anthropic.claude-opus-4-8
- reviewer: openai:gpt-5.5 (dropped) -> bedrock_converse:us.anthropic.claude-opus-4-8
(set SEED_REVIEWER_MODEL to a Fireworks model for a cross-family reviewer)
- fetch-config REQUIRED_PROVIDER_KEYS default ANTHROPIC_API_KEY,OPENAI_API_KEY ->
FIREWORKS_API_KEY (Bedrock auths via host IAM role; dropping the old keys would
otherwise fail-fast at boot)
- docs (DEPLOYMENT/ROTATION/put-config) updated to match.
Surfaced by the cross-family review + verified against deploy/.
* fix(bedrock): security-review NITs — region resolution, error sanitization, reasoning-block strip
From /sh-security-review (all confirmed-low):
- model.py: resolve region from AWS_REGION OR AWS_DEFAULT_REGION (matches
validate_local_dev_llm_config) so the validated region is the one actually used.
- model_fallback.py: sanitize Bedrock AccessDenied/ResourceNotFound errors to the
error code only, so the role ARN + account id in the raw botocore message never
reach logs or the user channel (CWE-209).
- sanitize_thinking_blocks.py: also strip empty Bedrock reasoning_content blocks
(Converse emits reasoning_content, not thinking) so the middleware is not a no-op
on Bedrock; + unit tests. (Empty blocks replay fine today; defensive.)
* deploy(bedrock): grant instance-role Bedrock invoke + repoint LLM_MODEL_ID / eval model ids
Deployment-readiness for the Bedrock migration (PR #62):
- instance-role.ts: least-privilege bedrock:InvokeModel[WithResponseStream] on the
us.anthropic.claude-opus-4-8 inference-profile ARN + the foundation-model ARN in
each routed region (us-east-1/2, us-west-2). The model runs in the server process
on the box, so the EC2 instance role is the principal. Simulator-verified (allowed
for opus-4-8, implicitDeny for other models) and synth-verified. Passed the
mandatory GPT-4.1 IAM cross-review (no blockers, least-privilege confirmed).
- config-store.ts: IaC SSM LLM_MODEL_ID anthropic:claude-opus-4-8 ->
bedrock_converse:us.anthropic.claude-opus-4-8. This SSM value overrides
seed_store.sh's default via pick precedence, so the seed-script fix alone was
insufficient — both sources now point at the supported Bedrock id.
- infra/README.md + evals/reviewer/config.toml: repoint stale anthropic:/google_genai:
ids to the Bedrock id (config.toml's model_id was an active, now-broken value).
AWS_REGION is already wired via user-data.sh (IMDS -> boot.env), so no change needed there.
* chore(secrets): drop OPENAI/GOOGLE/GROQ key shells (revoked, providers removed)
Those three providers were dropped in the Bedrock/Fireworks migration and their keys
revoked; the live Secrets Manager objects (open-swe-{dev,prod}/{OPENAI,GOOGLE,GROQ}_API_KEY)
were deleted (7-day recovery). Remove them from the IaC so a future cdk deploy does not
recreate the shells, and from fetch-config's mirror array so boot stops requesting them:
- config-store.ts SECRET_VARS + descriptions (28 -> 25 shells)
- fetch-config.sh SECRET_VARS array (kept in lockstep)
- put-config.sh: drop the put_secret lines; ANTHROPIC_API_KEY re-labelled optional
(eval judge only — Bedrock builder/reviewer auth via the host IAM role).
REQUIRED_PROVIDER_KEYS is not set in SSM, so it uses the FIREWORKS_API_KEY default.
|
||
|
Adam Moussa
|
8a9974c3c4
|
feat: author Slack/dashboard/schedule commits + PRs as the app by default (#57) (#60)
Some checks failed
CI / Lint (push) Waiting to run
CI / Format check (push) Waiting to run
CI / Unit tests (push) Waiting to run
CI / Playwright E2E (push) Waiting to run
Build & publish app artifacts / Publish + deploy (dev) (push) Has been cancelled
Build & publish app artifacts / Publish + deploy (prod) (push) Has been cancelled
Infra CD / Infra CI (pre-deploy) (push) Has been cancelled
Infra CD / Deploy open-swe-dev (push) Has been cancelled
Infra CD / Deploy open-swe-prod (push) Has been cancelled
* feat: default Slack/dashboard/schedule PRs + commits to the app identity (#57) Slack/dashboard/schedule runs now author PRs and run git/gh operations as the GitHub App seahaven-openswe[bot] by default (matching GitHub-issue runs), so the self-review 422 is impossible by construction rather than guarded in the prompt. A profile flag author_prs_as_user restores per-user attribution. - open_pull_request._resolve_pr_author_token + auth.resolve_github_token: default to the installation token for these sources; per-user only when opted in. - authorship: commit identity -> seahaven-openswe[bot] (numeric noreply; accepted Vercel-resolution risk, documented inline). - self-trigger safety: INTERNAL_BOT_LOGINS + webapp/reviewer_reconcile/reply markers recognize seahaven-openswe[bot] (bot-authored events are now ours). Supersedes the prompt-only guard in #58. * fix: author commits as the app bot in the default path (SH-IDSPLIT-01) Security review found the commit identity was NOT actually unified to the bot: resolve_triggering_user_identity got a 403 from the installation token and fell back to configurable['github_login'], so commits were still authored as the triggering user (commit=user, push+PR=bot — a three-way split that missed the stated goal). Now gate the triggering-user identity resolution on the same default-bot decision as the token: slack/dashboard/schedule default to the app bot identity unless author_prs_as_user is set. * docs(security): record AUTHZ-SLACK-BOT-DEFAULT-001 as an accepted residual (#59) Single-user deployment; bounded by App-on-pilot + ALLOWED_GITHUB_REPOS lock. Revisit (add a per-user gate) before expanding users or the App installation. |
||
|
Adam Moussa
|
a33aaec495
|
fix: resolve security-review findings (sandbox isolation, IAM list scope, webhook replay, info-leak) (#54)
* fix: enforce a replay window on Linear webhooks (AUTHZ-001) verify_linear_signature accepted any correctly-signed body with no freshness check, so a captured request could be replayed indefinitely. Parse the signed webhookTimestamp (Unix ms) and reject requests outside a 60s window, failing closed when the field is missing or malformed — mirroring the Slack verifier. * fix: stop leaking upstream auth-error bodies into user comments get_github_token_for_user folded the raw upstream response text into the error string that becomes a Slack/Linear comment (AUTH-RESP-LEAK-01). Log the full body server-side only and return a generic "GitHub auth failed (status <code>)". Also document the accepted shared-installation-token blast radius on the bot-token-only path (AUTHZ-003). * fix: bind sandbox and token caches to repo to prevent thread-id collision A PR head-branch name is attacker-controllable and get_thread_id_from_branch derives a thread_id from its first UUID with no repo binding (TID-COLLIDE-01). The in-memory sandbox cache and the per-thread GitHub-token cache were keyed on thread_id alone, and a cached sandbox was reused after only an echo-ping, so a different repo's webhook could bind to another thread's sandbox or token. Without changing the persistent thread-id scheme: - Persist the bound repo (owner/name) in thread metadata on sandbox creation and refuse to reuse a sandbox whose bound repo does not match the current event (SandboxRepoMismatchError); the in-memory proxy also carries the binding. - Bind the GitHub-token cache entries to their repo and evict on a cross-repo read so a colliding thread_id cannot be served another repo's token. - Thread repo through the reviewer and the webhook token resolvers. * fix: scope s3:ListBucket to the releases/ prefix (F-1/IAC-04) The instance role and the GitHub deploy app role granted s3:ListBucket on the whole assets bucket. Every caller (deploy.sh, the publish/rollback scripts) only ever lists under releases/, so add a StringLike s3:prefix=releases/* condition. GetBucketLocation has no s3:prefix in its request context, so it moves to its own unconditioned statement. Also document the accepted F-2 cross-env existence-oracle residual on BatchGetSecretValue. * chore: suppress test-fixture credential false positive; document AUTHZ-002 Add a machine-level suppression for the fake Datadog key in the test_team_credentials encryption-roundtrip fixture (CWE-798, not a real credential). Clarify that the within-org thread-write path is intentional by design (AUTHZ-002) — comment only, no behavior change. * fix: casefold repo-binding keys to avoid spurious cross-repo mismatch GitHub owner/name are case-insensitive. Casefold the owner/name key on both the write (binding) and read (compare) sides — repo_cache_key and the metadata bound_repo read — so Org/Repo and org/repo resolve to one repo and a legitimate same-repo run cannot raise a spurious SandboxRepoMismatchError (Gap 2). * fix: stop leaking upstream auth body in unexpected-result branch The 2xx-but-missing-token/url branch echoed the parsed upstream response body into the user-facing error. Return a generic message and log response_data server-side only, mirroring the existing HTTPStatusError fix (Gap 4). * fix: fail closed for unbound-legacy sandboxes and catch repo mismatch Gap 1: a thread with a persisted sandbox_id but no in-memory cache and no recorded bound_repo (a pre-binding legacy thread, post-deploy) previously reconnected-and-served the sandbox to the current repo, then rebound it. Now fail closed: drop the stale id and recreate a fresh sandbox bound to this repo, logging a reconnect-with-missing-binding event. A sandbox is never served to a repo unless its binding is known and matches; new threads bind on first run unchanged. Gap 3: catch SandboxRepoMismatchError at the agent and reviewer run entrypoints, log it for alarming, and surface a clean sanitized error instead of letting an opaque deep-stack exception crash-loop the worker. * chore: suppress test-fixture credential false positive in token-TTL tests Add a machine-level suppression for the fake "ghp_secret" GitHub token used by the cached-token TTL/revocation unit tests (CWE-798). Not a real credential and not a valid PAT; scoped to the unit test only. |
||
|
Johannes du Plessis
|
39681102d6
|
fix: repair orphaned tool calls before model calls (#1604)
When a run is cancelled or the sandbox dies mid-tool-call, LangGraph persists the AIMessage tool_call but never the matching ToolMessage. The next run sends the provider an orphaned tool_use (Anthropic 400: "tool_use ids were found without tool_result blocks"), permanently wedging the thread on every retry. Add RepairOrphanedToolCallsMiddleware, which inserts a synthetic error ToolMessage immediately after any tool_call lacking a result so the agent can retry instead of dying. Wired into the agent and reviewer graphs. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Johannes du Plessis
|
3992d3ef5d
|
feat: repo-scoped dynamic sandbox snapshots (#1595)
* feat: repo-scoped dynamic sandbox snapshots Let admins build a per-repo sandbox image from a custom Dockerfile so runs targeting that repo boot from a snapshot with its deps pre-baked. Snapshot selection is purely additive: repos without a `ready` repo-scoped snapshot always fall back to the configured DEFAULT_SANDBOX_SNAPSHOT_ID. Backend adds a repo_snapshots store module (Dockerfile + build status keyed by owner/name), threads the resolved repo through the LangSmith sandbox creation path, runs builds via SandboxClient.create_snapshot_from_dockerfile in a throwaway builder sandbox, and exposes admin-only CRUD + build endpoints. The UI adds an admin-only Agents-tab page (repo picker + Monaco Dockerfile editor + build status/logs). Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: harden repo snapshot builds Require REPO_SNAPSHOT_BASE_IMAGE for generated Dockerfile templates so admins cannot accidentally build a repo snapshot from a bare Python image that lacks Open SWE's sandbox tools. Allow stale building records to be retried by tracking build_started_at and treating old or missing timestamps as stale. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: document repo snapshot base image config Document REPO_SNAPSHOT_BASE_IMAGE alongside sandbox snapshot setup and convert missing base-image configuration into a handled dashboard API error so admins see a clear configuration message instead of an unhandled template-generation error. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Johannes du Plessis
|
860aee48ee
|
feat: add user-scoped Notion MCP OAuth (#1593)
* feat: add user-scoped Notion MCP OAuth Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: refresh Notion token per tool call Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: normalize Notion wrapper response format Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Ramon Nogueira
|
3a0e2b4672
|
feat: plan mode with model-driven entry and collaborative review (#1580)
* feat: add plan mode for read-only research and planning
Adds a per-run plan_mode flag that puts the agent in a read-only
research phase: a strong prompt section is injected and mutating tools
are stripped via ExcludeToolsMiddleware so the agent proposes a
reviewable implementation plan before any edits. Surfaced in the
dashboard UI with a Plan toggle (Shift+Tab) wired through the thread API.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: enforce plan-mode read-only at tool layer and disable subagents
Addresses PR review: plan mode previously relied on prompt text to keep
the shell read-only and left the task subagent (built with its own
write/PR/Linear tools) unrestricted. Now `task` is excluded so research
cannot be delegated to a mutating subagent, and a new
PlanModeShellGuardMiddleware enforces a read-only command allowlist on
`execute`, blocking writes, git state changes, installs, redirection,
and command substitution regardless of model/prompt-injection compliance.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: harden plan-mode shell guard against wrapped mutations
Block git global options that take values (-C, --git-dir, ...) from being
misread as the subcommand, reject config-injection options (-c,
--config-env, --exec-path), and drop the env command wrapper that could
run arbitrary commands.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* feat: add plan mode with enter_plan_mode tool, profile/team defaults, Slack commands and approval flow
- enter_plan_mode tool: agent self-activates plan mode via Command(update={'plan_mode': True})
- Plan mode resolution: per-thread > profile default > team default > False
- PLAN_MODE_GUIDANCE_SECTION: always-present prompt section telling agent about the tool
- profile_plan_mode_default and team plan_mode_default settings
- Slack plan on/off/status commands with thread metadata persistence
- slack_thread_reply plan_approval=True renders Approve/Revise/Cancel buttons
- Interactivity handler: approve triggers implementation run, cancel posts confirmation
- Frontend: plan_mode_default in Profile/ProfileUpdate/TeamSettings types and UI toggles
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* test: add tests for enter_plan_mode tool, profile/team defaults, Slack plan commands, approval blocks
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* refactor(plan-mode): drop shell guard, rely on prompt for read-only discipline
Remove PlanModeShellGuardMiddleware and its enforcement of read-only shell
commands during plan mode. Plan mode now relies on the system prompt to
instruct the agent not to run mutating commands; the mutating-tool exclusion
(ExcludeToolsMiddleware) is retained.
* test(open-swe): add Playwright E2E for the Slack → PR → web handoff
Local, secrets-free end-to-end suite that drives the full happy path through mock Slack/GitHub control panels and the real dashboard UI. Only the LLM and external SaaS HTTP boundaries (GitHub/Slack APIs, OAuth token mint) are faked — the real process_slack_mention, get_agent, deepagents loop, tools, middleware, and dashboard authorization all run under `langgraph dev` with a scripted fake chat model and a local temp-dir sandbox.
- full_flow: a Slack mention runs the agent, which implements a change in the sandbox, opens a PR against a fake GitHub remote, and replies with the PR link in the same thread.
- dashboard: clicking the bot's real "Open in Web" link loads the built ui/ app (served same-origin); the thread owner can continue the conversation, while a different user sees the same thread read-only (no composer).
Wired into Agent CI as a `Playwright E2E` job that runs on pull requests.
* fix(open-swe): serve E2E UI assets via explicit route; pin Playwright
The dashboard E2E served the built ui/ SPA's /assets via app.mount(StaticFiles), but LangGraph's custom-app loader serves APIRoutes and drops sub-app Mounts, so /assets 404'd under `langgraph dev` in CI — the React app never booted and the composer/transcript never rendered. Serve assets via an explicit route instead.
Also pin @playwright/test to the latest (1.61.0) for reproducible runs, and make the owner composer assertion tolerant of either hydration state.
* test(open-swe): record Playwright trace + video on every E2E run
Capture a replayable trace (DOM snapshots, network, console, source) and a screen recording for every test, not just retries, plus a screenshot on failure. The CI job already uploads playwright-report/ and test-results/, so each run now has a downloadable replay; documented how to open it.
* feat(plan-mode): collaborative plan review with BlockNote + Yjs
When the agent enters plan mode it writes the plan as a markdown file in the
sandbox (save_plan tool), publishes it, and posts a review link to the source
channel. Reviewers open the plan inside the dashboard (under the /agents shell),
read it rendered in a BlockNote editor, and leave inline comments synced live
over Yjs. Only the thread owner can approve; any reviewer can request changes.
On approve/reject the comments are harvested and handed to the agent for the
follow-up run; the agent never sees comments mid-review.
- agent: enter_plan_mode persists plan state; new save_plan tool; prompt shares
the plan-review link.
- dashboard: Yjs WebSocket collab server (pycrdt-websocket) with store-backed
snapshots; plan content/status store; plan REST API (get/approve/reject,
owner-only approve, client-harvested comments); planStatus on thread summaries.
- ui: BlockNote native comments (CommentsExtension + YjsThreadStore) plan page
mounted under the agents shell, with a "Review plan" banner in the thread view
and a back-link; theme-aware (dark mode) using the dashboard tokens.
- e2e: Playwright coverage of the full Slack -> plan -> review -> approve -> PR
flow, including cross-user comment sync and owner-only approval.
* fix(plan-mode): address review feedback (authz, overrides, leaks, deps)
- plan-collab WS: authorize per-thread before joining a room (same read gate as
the REST API) — previously any logged-in user could join any thread (IDOR).
- plan-collab: tie the snapshot flusher to active connections (refcount) so each
opened plan no longer leaks a permanent 1.5s task on the shared event loop.
- plan decisions: include thread_id in the follow-up run configurable so the run
resumes the existing thread; set plan_mode explicitly so approve forces it off.
- get_agent: an explicit per-thread plan_mode (Slack `plan off`, approved plan,
dashboard toggle) now overrides profile/team defaults instead of falling back.
- plan mode tool gating moved to a state-aware PlanModeMiddleware installed
unconditionally, so a mid-run enter_plan_mode restricts the next model turn;
before_agent resets stale plan_mode so a later run isn't forced back into it.
- exclude write-capable http_request from plan mode.
- pin pycrdt / pycrdt-websocket with upper bounds.
Includes the latest base (#1583): E2E UI assets served via explicit route
(fixes the Playwright CI failure — LangGraph's app loader drops sub-app mounts).
* style: ruff format plan_collab.py
* fix(plan-mode): owner-gate Slack approval + same-origin check on collab WS
- Slack "Approve & Implement" now verifies the clicking user is the plan
requester (owner, via the stored triggering_user_id) before implementing —
matching the dashboard API's owner-only approval. Non-owners are pointed to
Revise / feedback.
- The plan-collab WebSocket validates the handshake Origin against the dashboard
allowlist before accept() (no-op when unconfigured, e.g. local/dev), mirroring
the REST require_same_origin CSRF defense.
* fix(plan-mode): enter plan mode only via the model + local mock dev harness
Plan mode is now entered solely when the model calls enter_plan_mode.
Removed the per-user and team plan_mode_default settings (backend + UI)
and the Slack `plan on/off/status` toggle.
- enter_plan_mode returns a terminating ToolMessage, fixing the missing
ToolMessage error that silently dropped plan mode mid-run.
- PlanReview: defer Yjs provider/doc teardown so React StrictMode's dev
remount doesn't destroy and then reuse the collaboration provider.
- e2e plan_review spec asserts plan_mode actually engages.
- LangSmith trace-url resolution is best-effort: bail before any API
call when the tenant is unset, cache failures, log at debug.
- Add `pnpm run dev:mock`: same-origin Vite HMR harness with a real LLM,
Alice/Bob mock users, and a GitHub login picker.
* docs(plan-mode): drop stale references to removed profile/team defaults
The plan_mode middleware docstring and the approve/reject dispatch comment
still described the profile/team plan_mode_default resolution that no longer
exists; reword to match model-driven entry + the per-thread carry.
* feat(plan-mode): let any reviewer edit the plan, not just comment
Drop the owner/commenter split for the plan document: everyone with read
access edits and comments alike (DefaultThreadStoreAuth "editor" for all,
editor always editable until a decision, anyone seeds the empty doc). This
matches the collab WS, which already relays frames to every readable user.
Plan approval stays owner-gated.
* test(plan-mode): assert plan-mode entry via the tool's success message
plan_mode lives only in run state for tool gating; it is not a persisted
thread-state channel, so the previous `values.plan_mode === true` poll
could never pass. Assert instead that enter_plan_mode's success ToolMessage
("Plan mode is active …") lands in the thread — which only happens when the
tool's Command applies cleanly, the exact regression this guards.
---------
Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com>
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
|
||
|
Johannes du Plessis
|
450a25d33f
|
feat: add schedule_thread_wakeup tool for self-polling (#1592)
* feat: add schedule_thread_wakeup tool for self-polling Add a new agent tool that schedules a one-shot re-trigger of the current thread after a configurable delay (1–1440 minutes). Uses a LangGraph cron with end_time to fire exactly once, then retire. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: prevent early thread wakeups Round scheduled wakeup times up to the next whole minute so cron minute precision cannot fire before the requested delay. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
John Kennedy
|
9949077bc7
|
fix: allow GitHub logins for dashboard admins (#1582)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
John Kennedy
|
9db7eab134
|
feat: Add Corridor MCP analyzePlan integration (#1572)
* Add Corridor MCP analyzePlan integration * Update agent/integrations/corridor_mcp.py Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com> * Add Corridor analysis prompt * Only include Corridor prompt when tool loads --------- Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com> |
||
|
Johannes du Plessis
|
60b7f4677a
|
feat: add user-scoped Currents.dev API key for e2e test investigation (#1566)
* feat: add user-scoped Currents.dev API key for e2e test investigation
Allow each user to configure their own Currents.dev API key on the
Profile Settings page. The key is encrypted at rest in a per-user
LangGraph Store namespace and feeds server-side read-only tools that
query the Currents REST API (runs, instances, projects, test results)
so agent runs can inspect e2e test failures including screenshots and
DOM snapshots.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
* fix: add pagination cursors to currents_list_project_runs
Address review feedback: forward starting_after/ending_before cursor
parameters to /projects/{projectId}/runs so the agent can paginate
beyond the first 50 results.
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
|
||
|
Caroline di Vittorio
|
554d754585
|
feat: link PR attribution footer to the originating thread (#1539)
The "Made by Open SWE" PR footer linked to the generic dashboard homepage. Point it at the dashboard thread that generated the PR (/agents/<thread_id>), falling back to the homepage when no thread id is available. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Johannes du Plessis
|
ddd7190864
|
feat: let the agent stop naturally without forced tool calls (#1535)
Remove the hardcoded "call a tool every turn" instruction from the system prompt and delete the ensure_no_empty_msg middleware that re-injected no_op / confirming_completion tool calls. The agent now ends its turn naturally when the model emits a final message with no tool call, which avoids needlessly extending trajectories (and token spend) on tasks that are already complete. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Johannes du Plessis
|
aa98d195a8
|
feat: route graphs to separate LangSmith tracing projects (#1508)
* feat: route graphs to separate LangSmith tracing projects * docs: point graph entrypoint references at traced wrappers --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Johannes du Plessis
|
da20e57bcc
|
fix: refresh sandbox GitHub proxy token before mid-run expiry (#1496)
* fix: refresh sandbox GitHub proxy token before mid-run expiry GitHub App installation tokens expire after exactly 1 hour. The LangSmith sandbox proxy was configured once at run start with a snapshot of that token, so runs longer than ~1h hit 401s on every gh/git call. Record the proxy token's expiry per thread and add a before-model hook that re-configures the proxy with a fresh token when it nears expiry. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: preserve repo-scoped proxy token on mid-run refresh Reviewer runs mint a repository-scoped installation token. Record the repo scope per thread alongside the expiry so the before-model refresh re-mints a token with the same scope instead of an installation-wide token, avoiding privilege expansion on long reviewer runs. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: update passthrough stub for github_proxy_repositories param --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Christian Bromann
|
abf354bb05
|
feat(open-swe): stream agent chat via @langchain/react v2 protocol (#1475)
* feat(dashboard): stream agent chat via @langchain/react v2 protocol Replace the bespoke SSE + React Query polling path with LangGraph’s v2 event stream through credentialed dashboard proxies. Run starts go through stream commands; mid-run follow-ups still queue via /messages. * fix import path * fix tests after rebase * format * PR feedback * improved model fallback * fix image handling * embrace sdk * cleanup * cr * more cleanup * fix cors * harden security --------- Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com> Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Johannes du Plessis
|
f539962c73
|
feat: server-side Datadog/LangSmith observability tools + team creds [closes OPE-54] (#1476)
* feat: server-side Datadog/LangSmith observability tools + team creds Add team-wide observability credential settings (Datadog DD_SITE/API/APP keys, LangSmith API key) stored encrypted server-side, with an admin dashboard section to connect/disconnect each provider. When connected, get_agent loads read-only observability tools server-side: Datadog via its hosted MCP server (langchain-mcp-adapters, toolsets=core) and LangSmith read tools (langsmith_get_trace, langsmith_list_runs). Credentials live in the LangGraph server process and are never exposed to the sandbox. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: address review on observability tools Address PR review feedback: - Authorize observability tools per triggering user (admins + the OBSERVABILITY_AUTHORIZED_EMAILS allowlist) so prompt-injected runs from untrusted contributors can't reach team Datadog/LangSmith data. - Use the documented Datadog MCP auth headers DD_API_KEY / DD_APPLICATION_KEY. - Store each provider's credentials under its own store key to avoid a read-modify-write race dropping the other provider on concurrent saves. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: async email resolution in observability authorization gate --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Johannes du Plessis
|
da8f003933
|
feat: per-repo custom instructions for the coding agent (#1460)
* feat: per-repo custom instructions for the coding agent Adds per-repository custom instructions for the main coding agent, mirroring the reviewer's per-repo style prompts. Instructions are stored in the LangGraph Store, managed via dashboard API + UI (Monaco editor), and appended to the agent's system prompt for runs targeting that repo. Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * chore: wire agent instructions route into generated route tree Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: enforce repo access on instruction routes Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Johannes du Plessis
|
449cb5d1a8
|
fix: make default repository configurable (#1429)
* fix: make default repository configurable Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * fix: preserve dashboard repo-less runs * fix: distinguish explicit repo-less dashboard runs --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Johannes du Plessis
|
a511add856
|
feat: add agent usage leaderboard (#1418)
* feat: add agent usage leaderboard Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com> * fix: bound leaderboard refresh and hide emails Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com> |
||
|
Johannes du Plessis
|
8b18e7e95d
|
fix: Reduce graph load and dashboard repo failures (#1412)
* fix: reduce graph load and dashboard repo failures * fix: surface repo listing timeouts |
||
|
Brace Sproul
|
2070a770c2
|
fix: stop storing GitHub tokens in metadata (#1405)
* fix: stop storing GitHub tokens in metadata Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com> * fix: bound in-process GitHub token cache with 24h TTL + sweep --------- Co-authored-by: open-swe[bot] <215916821+open-swe[bot]@users.noreply.github.com> Co-authored-by: open-swe[bot] <johannes@langchain.dev> |
||
|
open-swe[bot]
|
ae946d1aa5 |
chore: attribute commit co-author to open-swe[bot], not open-swe user
The Co-authored-by trailer and bot git identity used open-swe@users.noreply.github.com, which resolves to the separate open-swe *user* account rather than the open-swe[bot] GitHub App. Switch OPEN_SWE_BOT_EMAIL to the bot's noreply address (215916821+open-swe[bot]@users.noreply.github.com) so co-author credit and the fallback author identity point at the bot. Drive the prompt trailer and sandbox git config from the constant instead of hardcoding the address. |
||
|
Johannes du Plessis
|
0a2e682364
|
fix: scope public reviewer tokens (#1389)
* fix: scope public reviewer tokens Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> * refactor: simplify reviewer token wiring; fix push re-scope + red test - Remove the redundant _check_or_recreate_sandbox_for_proxy / _refresh_github_proxy_or_recreate_for_proxy wrappers and call the underlying functions directly (they already default the token to None). - process_github_push_event: re-scope the GitHub App token when the push payload lacked repo privacy/id but PR metadata reveals a public repo, so reviewer.py never proxies a full-installation token for a public PR. - Clarify the two-token sequence in trigger_pr_review_from_ref. - Fix pre-existing failing test test_proxy_refresh_failure_recreates_sandbox and add coverage for _reviewer_token_for_repo + push-event scoping. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Johannes du Plessis
|
04c346176d
|
feat: open PRs as the triggering user via dedicated tool (#1378)
Add an open_pull_request tool that creates a new PR via the GitHub REST API using the triggering user's OAuth token (resolved by login from the dashboard store), so the PR creator is the user rather than open-swe[bot]. Falls back to the GitHub App installation token for GitHub-triggered runs, unmapped users, and bot-token-only deployments. The user token never enters the sandbox: clone/push/comments still go through the bot proxy via gh. The agent is steered to use the tool only for OPENING a new PR; updates (body edits, mark ready) and pasted/existing PRs continue to use gh pr edit. Existing-PR (422) returns the open PR's URL so re-runs don't create duplicates. |
||
|
Johannes du Plessis
|
4a55145bb1
|
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> |
||
|
open-swe[bot]
|
8130a188ef
|
chore: bump deepagents to 0.6.6 (#1359)
* chore: bump deepagents to 0.6.6 Co-authored-by: Mason Daugherty <61371264+mdrxy@users.noreply.github.com> * chore: remove obsolete deepagents reducer patch Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Mason Daugherty <61371264+mdrxy@users.noreply.github.com> Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com> |
||
|
open-swe[bot]
|
65acc4c9d3
|
fix: sanitize malformed Anthropic thinking blocks (#1357)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com> |
||
|
Johannes du Plessis
|
aeaa92eb8a
|
feat: Configure subagent model defaults (#1342) | ||
|
open-swe[bot]
|
e347aed851
|
feat: make PR creation policy opt-in (#1334)
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com> |
||
|
Johannes du Plessis
|
e87085139b
|
feat: add Agents chat UI for cloud threads (#1323)
* feat(ui): add Agents chat UI ported from open-swe-app
Introduce a Cursor-style Agents surface separate from the dashboard, with ported chat/diff components and mock thread data until LangGraph APIs land.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(dashboard): wire Agents UI to LangGraph thread APIs
Add dashboard thread list/detail/run/message/stream endpoints with a LangGraph message adapter, dashboard OAuth auth for runs, and TanStack Query hooks replacing mock data.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(dashboard): single agent reply per turn in Agents UI
Use UUID thread IDs LangGraph accepts, skip confirming_completion for
dashboard threads, and merge adapter agent messages so duplicate bubbles
do not render.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(ui): polish Agents UI with floating prompt and layout cleanup
Remove no-op chrome (git panel, headers, sidebar search), port CloudPromptBar
from open-swe-app, and refine chat layout so messages scroll behind the input.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(agent): patch deepagents reducer for None messages on checkpoint replay
LangGraph thread state could 500 when cancelled runs left messages as None.
Apply the reducer guard before graph import, fall back to metadata in the
dashboard API, and adjust Agents prompt bar layout.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(ui): unify sidebar user menu and clean up Agents UI navigation
Extract SidebarUserMenu so the dashboard and Agents sidebars render the
same profile button, drop the redundant Agents nav row in favor of the
existing Back to Agents link, add the open-swe logo header to the Agents
sidebar, flatten the New Agent button, and cap the home screen run list
to keep the prompt input in view.
* feat(ui): resizable/collapsible sidebar shared across dashboard and Agents
Add a useSidebarLayout hook + SidebarFrame wrapper so both sidebars
share a persisted width (default 260px, drag to resize, 200-420 range)
and a collapse toggle that hides the panel and surfaces a floating
reopen button. Also adds a DELETE /threads/{id} endpoint and an X-on-
hover thread delete control in the Agents sidebar.
* feat(ui): instant user message and busy indicator on Agents transition
Stash submitted prompts in sessionStorage, pre-populate the new thread
detail cache, and merge pending prompts into the rendered message list
so the Agents page renders the user bubble plus the existing thinking
spinner immediately instead of flashing a skeleton and "Agent is
starting" while the run boots.
* feat(ui): token-stream agent replies in the Agents thread view
Opt the LangGraph runs into messages-tuple streaming and forward those
events through the existing SSE channel. The frontend now applies
AIMessageChunk deltas directly to the cached thread (cancelling any
in-flight refetch first so optimistic tokens are not clobbered) and
keeps positional pending prompts so the user bubble stays in the right
place while the agent streams its reply.
* fix(dashboard): await threads.join_stream before iterating
threads.join_stream is async def returning an AsyncIterator, so it must
be awaited before async for. The SSE endpoint was raising
TypeError: 'async for' requires an object with __aiter__ method, got
coroutine on every connection.
* fix(dashboard): drop messages-tuple stream_mode that broke thinking-mode tool turns
Setting stream_mode=["values","messages-tuple","updates"] on
runs.create forces langchain_anthropic into streaming, and on the
second model call (after tool execution) its serialized thinking
blocks come back malformed, so Anthropic rejects the request with
'messages.1.content.0.thinking.thinking: Field required'. Revert to
the default stream_mode so claude-opus thinking + tool use runs to
completion. The frontend keeps the messages-event handler in place
as a no-op fallback for when streaming is re-enabled.
* feat(agents): per-thread model picker wired through to the run
Add optional model_id/effort to the create-thread and send-message
request bodies, forward them as agent_model_id/agent_effort in the
LangGraph run configurable, and record the resolved choice in thread
metadata so the UI can show the model the run is actually using.
get_agent now picks the per-thread override last (highest priority over
team default + profile override) and falls back gracefully when it is
absent or unsupported.
The frontend prompt bar becomes a controlled component fed by a
shared useModelOptions hook (options + profile -> defaultSelection).
AgentsHome seeds the picker from the user's profile default; the
thread view seeds from the thread's recorded model/effort and lets
each follow-up retarget the run.
* refactor(ui): align Agents prompt bar layout with open-swe-app PromptBar
Drop the absolute-positioned send button, restore the original
px-4 py-3.5 min-h-[106px] flex-col container, and move the model
picker into a mt-auto pt-2 footer row so the placeholder text and
the model selector share the same horizontal padding.
* chore: fix lint/format CI failures
Remove unused imports and reformat two files flagged by ruff.
* fix(tests): stop messages-reducer patch tests from polluting the suite
Restore agent modules after reducer patch tests and import LangSmithSandbox
from agent.server in proxy refresh tests so isinstance checks stay valid.
---------
Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
||
|
Johannes du Plessis
|
32ec9b485f
|
feat: restructure Open SWE Review tab + wire create_prs (#1319)
* feat(dashboard): restructure Open SWE Review tab + wire create_prs Restructures the dashboard around two related changes the reviewer settings have been asking for: - Wire profile.create_prs. Defaults to true (opt-out); when off the system prompt gets a `Pull Request Policy Override` section telling the agent to push the branch and notify with the branch URL instead of opening a PR. Removes the noop Slack Notifications / Allow Artifacts / First Name / Last Name controls and their schema fields. - Repositories opt-in for Open SWE Review. New per-team enabled list stored in the LangGraph Store (`["enabled_review_repos"]`). Every reviewer webhook chokepoint now goes through `_is_repo_enabled_for_review` which AND-combines the existing env allowlist with the dashboard list. Default is empty (opt-in) — admins enable repos per-installation from the new Repositories page nested under Open SWE Review. - Open SWE Review tab now mirrors the Cursor "rules" pattern: main page shows installation rows + a Rules entry; both drill into nested pages (/review/repositories/$owner and /review/styles) with a back link. - Adds the new logo/favicon assets shipped from sidebar + html head. Tests pass with a new autouse fixture (`tests/conftest.py`) that defaults `is_review_repo_enabled` to True for existing allowlist tests. * fix(dashboard): make main content scroll independently of the sidebar Outer flex container was min-h-svh, so it grew with main's content and the whole page scrolled — sidebar moved with it. Pin to h-svh + overflow-hidden so the sidebar stays put and only <main> scrolls. * fix(dashboard): make disabled repo toggles obviously disabled Switch's disabled state used opacity-50 against a muted background, so the not-admin state looked nearly identical to the off state. Bump to opacity-40 + grayscale, and wrap each repo toggle in a span carrying a native hover tooltip explaining why it's disabled. * fix(switch): handle base-ui's data-disabled state base-ui's Switch.Root sets data-disabled (not the HTML disabled attribute) when disabled, so Tailwind's disabled: variant never matches and the button keeps its cursor-pointer + clickable look. Mirror the styling under the data-[disabled] variant and add pointer-events-none so the disabled state is both visible and actually unclickable. * feat(dashboard): paginate per-installation repository list 20 repos per page with Prev / page X of Y / Next controls at the bottom. Pager only renders when there are more than 20 repos. Page resets to 0 when navigating between installations. * feat(dashboard): global default model selectors for Agent + Reviewer Adds team-wide default model + reasoning effort for both agents in the Admin tab so operators can switch models without redeploying. Resolution chain: Agent: hardcoded -> LLM_MODEL_ID env -> team default -> user profile Reviewer: hardcoded -> LLM_MODEL_ID env -> team default -> per-call configurable Team defaults live in team_settings and are validated against the SUPPORTED_MODELS allowlist + the model's supported reasoning efforts. 'Inherit from env' clears the override and falls back to LLM_MODEL_ID. * refactor(models): drop LLM_MODEL_ID env in favour of the team default The team default is now the single source of truth for the runtime model choice; per-user (agent) and per-call configurable (reviewer) selections still win on top. When no admin has touched the team default, it surfaces the hardcoded fallback (DEFAULT_MODEL_ID + its default effort), so the admin UI's dropdown is always pre-populated with a sensible value. The Admin UI loses the 'Inherit from env' option since there is no longer an env layer to inherit from. * chore(models): set hardcoded fallback to gpt-5.5 medium Decouple the team-default boot value (gpt-5.5 / medium) from each model's ProfileForm-suggested default_effort so we can change one without nudging the other. The Opus xhigh default for new user profiles is unchanged. * feat(dashboard): trigger-mode copy, Coming Soon badges, logout in My Settings - Rename trigger mode 'ready_for_review' -> 'once_per_pr' with new description copy that matches the screenshot. Legacy stored values fall back to 'every_push' on read so the UI never shows an unknown selection. - Add a 'Coming soon' badge + greyed-out + disabled state on the controls that don't have runtime consumers yet: Trigger Mode, Autofix Mode, Autofix Severity Threshold, and Automatically fix CI failures. SettingsRow grew a comingSoon prop to keep this consistent. - My Settings drops the noop PR Preferences section and adds a Sign Out button. preferred_pr_destination is removed from the profile schema; old records get the field popped on next write. --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> |
||
|
Johannes du Plessis
|
82852f9eda
|
feat: tune reviewer for precision — web/wiki tools + recalibrated prompt (#1312)
* feat: tune reviewer for precision — web/wiki tools + recalibrated prompt Reviewer agent now has web_search, fetch_url, and http_request alongside the finding tools, so it can verify library semantics and consult the DeepWiki auto-generated wiki for public repos (https://deepwiki.com/<owner>/<repo>) before flagging cross-file or architectural concerns. Prompt rewritten to push precision over recall: - explicit severity ladder pushing reviews toward bimodal high/low instead of defaulting to medium - ≤200-char description target (gold set averages ~186 chars; we were at ~436) - mandatory docs / wiki / code lookup before flagging concurrency, security, or perf — the three categories that dominated false positives - "do not flag" list covering compiler/linter-catchable nits, speculative claims without a concrete attacker/interleaving/scale, style preferences the codebase doesn't share, and test-quality nits on non-test diffs - smart file-selection guidance for large PRs (deprioritize generated / vendored / pure-rename hunks) Eval config switched to openai:gpt-5.5 + high reasoning effort for the next benchmark run. * trim prompt * subagent prompting * confidence ratings * added medium * enforce confidence threshold * . * reviewer: precision-tuned prompt + drop confidence gate Rewrites the reviewer system prompt around a defensibility bar (anchor + failure mode + maintainer wouldn't say "not a bug"), an explicit do-not-file list (style nits, speculation, scope-policing, same-bug fan-out), and a checklist of 10 bug archetypes drawn from a per-PR audit of the eval golden set. The audit showed 145 FPs in the last eval split ~28% speculative, ~26% style-nit, ~31% real-but-unscored (mostly same-archetype fan-out); the new prompt targets each class directly. Confidence is still recorded on every finding for post-hoc calibration but no longer gates publication — the audit showed the gate was a no-op (agent self-rated 65% of findings "high" regardless), and the prompt's defensibility bar is the actual discipline. Drops CONFIDENCE_ORDER, CONFIDENCE_THRESHOLD, the confidence_threshold kwarg on filter_findings_for_publish, the confidence_filtered score_mode, and the min_confidence kwarg on the eval target's _extract_comments — all dead once the gate is gone. Also removes the "informational" severity tier from the Severity enum, SEVERITY_ORDER, and all validators / tests / docstrings. It was reserved for FYI observations the dataset never rewards. * benchmax * adding google provider * slight steering * tuning * more tuning * fix * cleanup * reducing overfitting * Add per-repo review style profiles and inject them into the reviewer. Dashboard users can analyze historical PR review feedback per repository, edit the resulting style guide, and have it loaded from LangGraph Store at reviewer runtime (including Martian eval runs) keyed by owner/name. Co-authored-by: Cursor <cursoragent@cursor.com> * Fix review style job errors leaking exception details to clients. Return generic dashboard messages while logging full stack traces server-side. Co-authored-by: Cursor <cursoragent@cursor.com> --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com> Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|
Johannes du Plessis
|
834efbc33c
|
feat: Adds ability to run evals against deployment (#1311)
* feat: tighten reviewer eval workflow Require the reviewer to verify and dedupe findings before recording them, and make benchmark runs safe to execute against deployed reviewer graphs without posting GitHub reviews. * chore: move reviewer eval settings to config Load reviewer benchmark settings from the default eval config file so deployed eval runs do not require a wide CLI surface. * feat: allow reviewer eval model overrides Pass reviewer model and reasoning effort from the eval config into reviewer runs so isolated benchmark deployments can test Opus 4.7 high thinking. * fix: use adaptive thinking for Opus 4.7 Switch Opus 4.7 model overrides to Anthropic adaptive thinking with effort instead of the deprecated budgeted thinking payload rejected by the API. * refactor: use latest Anthropic effort API Remove legacy Anthropic budget-token thinking support and route Anthropic efforts through adaptive thinking plus effort. * revert prompting |
||
|
Johannes du Plessis
|
88856a04fa
|
feat: open-swe dashboard for per-user profile config (#1302)
* feat: dashboard backend — GitHub OAuth, profile CRUD, admin endpoints Adds agent/dashboard/ FastAPI router mounted at /dashboard/api covering: - GitHub App OAuth login → JWT cookie session (cross-domain ready) - profile CRUD against LangGraph Store with model+effort validation - admin gate via CONFIGURED_ADMINS - /repos via /user/installations using the user's encrypted OAuth token CORS allowlist on webapp.py is opt-in via DASHBOARD_ALLOWED_ORIGINS so the Vercel-hosted frontend can call the LangSmith deployment with credentials. * feat: apply dashboard profile model/effort overrides in get_agent Look up the triggering user's GitHub login from config (direct field or GITHUB_USER_EMAIL_MAP reverse lookup), read their profile from the Store, and apply default_model + reasoning_effort to make_model when both are valid. Effort 'max' is captured on the profile but not yet wired through — the OpenAI Reasoning Literal doesn't accept it. * feat: ui/ TanStack Start dashboard for profile config Scaffolded with the shadcn b7CScJIjA preset (TanStack Start template, base-ui primitives, Tailwind v4). Three routes: - /login — Sign in with GitHub (links to /dashboard/api/auth/login) - /profile — Edit default model, reasoning effort, default repo - /admin — Admin-only: list users and edit other profiles API client (src/lib/api.ts) uses credentials: include so the osw_session cookie set by the OAuth callback rides cross-origin. VITE_DASHBOARD_API_BASE_URL points at the LangSmith deployment. Effort options re-render when the model changes; 'max' on Opus 4.7 is captured on the profile but ignored downstream until anthropic reasoning is wired through make_model. * feat: searchable Combobox for default repo picker Replaces the Select with a base-ui Combobox so users can filter by typing, the popup is wider than the trigger so full owner/repo names are readable, and the list caps at max-h-80 to stay on screen. * fix: address review comments + wire default_repo and Anthropic thinking Security/correctness fixes from PR review: * Open redirect: validate `redirect_to` in `/auth/login` against `DASHBOARD_BASE_URL` + `DASHBOARD_ALLOWED_ORIGINS` before signing it into the state JWT. Anything off-allowlist falls back to the dashboard base URL. (PR #1302 r3250054386) * Login CSRF: bind the OAuth `state` to the requesting browser. At `/auth/login` we generate a fresh nonce, set it as a short-lived HttpOnly SameSite=Lax cookie scoped to `/dashboard/api/auth`, and embed `hash_state_nonce(nonce)` in the state JWT. At `/auth/callback` we require the cookie nonce to hash-match the state JWT's nonce_hash (constant-time compare). (PR #1302 r3250054395) * RMW race in profile vs token writes: split storage into two namespaces — `["profiles"]` for user-editable settings and `["oauth_tokens"]` for the encrypted GitHub token. Each upsert now only writes its own namespace so an in-flight profile save can no longer clobber a fresh token from a concurrent re-login (and vice versa). (PR #1302 r3250054393) * /repos pagination: follow `Link: rel="next"` for both `/user/installations` and per-installation `/repositories` with per_page=100, capped at 1000 items. (PR #1302 r3250054401) Feature wires: * default_repo: applied as a fallback in `get_slack_repo_config` (after explicit-repo / thread metadata, before the env defaults) and in the Linear webhook (after comment-body extraction, before team mapping). Both paths resolve the triggering user's GitHub login via GITHUB_USER_EMAIL_MAP and read the profile's default_repo. * Anthropic "thinking" effort: `make_model` now accepts a `thinking` kwarg; `get_agent` maps profile effort {low,medium,high,xhigh,max} to budget_tokens {1k,4k,12k,32k,60k} when the chosen model is anthropic. OpenAI path still ignores "max" since the Literal doesn't accept it. |
||
|
Johannes du Plessis
|
5c7c78406c
|
fix: keep sandbox backend stable across recovery (#1294)w
Use a per-thread proxy so in-flight tools continue through the latest recreated sandbox instead of holding a stale backend reference. |
||
|
open-swe[bot]
|
85343fab63
|
feat: TTL and revocation handling for cached GitHub OAuth tokens [closes AB-2322] (#1280)
* feat: TTL and revocation handling for cached GitHub OAuth tokens [closes AB-2322] Persist github_token_expires_at alongside github_token_encrypted, treat expired cache entries as missing so we re-resolve before kicking off runs, and invalidate the cached ciphertext on a downstream 401 so the next invocation gets a fresh token instead of replaying a revoked one. Co-authored-by: Johannes du Plessis <51395795+johannes117@users.noreply.github.com> * webapp: forward installation-token expiry to reviewer cache writes The three reviewer-thread persist sites in webapp.py were calling get_github_app_installation_token() (no expiry) and persist_encrypted_github_token without expires_at, so cached App tokens were treated as never-expiring even though they actually expire in ~1 hour. --------- 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> |
||
|
Johannes du Plessis
|
094b2df939
|
feat: cross-provider model fallback on transient errors (#1281)
When the primary model raises a transient provider error (5xx, 429, connection/timeout) the request is retried once against a fallback model from the other provider. Anthropic primaries fall back to OpenAI and vice versa. Also bumps the SDK max_retries from the default 2 to 6 so quick blips stay on the primary and keep prompt caching warm. Triggered by 529 OverloadedError traces that ended runs silently with no Slack/Linear/PR reply. |
||
|
Johannes du Plessis
|
743b2b9ba4
|
fix: recover from mid-run sandbox death (#1274)
* fix: recover from mid-run sandbox death Recreate dead sandboxes during tool execution and stop repeated unrecoverable timeout loops with a user-facing notification. * fix: count repeated sandbox recreations Treat consecutive sandbox recreations as an unrecovered failure streak so outages cannot loop until the model-call limit. |
||
|
Johannes du Plessis
|
5d1020e8d7
|
fix: restore Co-authored-by trailer for triggering user (#1271)
The gh-cli migration removed agent/middleware/open_pr.py and agent/tools/commit_and_open_pr.py — the only callers of add_user_coauthor_trailer / add_pr_collaboration_note. Since then the agent has been driving commits and PRs entirely via gh, with no attribution back to the Slack/Linear/GitHub user who triggered the run. Resolve the triggering user's identity in get_agent (reusing the existing authorship helpers) and inject a Collaborative Attribution section into the system prompt with the exact trailer and PR-body note to use. The section is only rendered when an identity is resolvable, so runs without a known triggering user are unchanged. |