2026-07-03 11:46:00 -04:00
<!-- GENERATED — do not hand-edit. Edit docs/upstream-sync/triage.jsonl, then run `make triage-render` . Staleness is enforced in CI by `make triage-check` . -->
# Upstream triage ledger
Commits on `upstream/main` (langchain-ai/open-swe) not yet in `dev` , and the decision on each.
Rows key on the **upstream SHA** (stable across local cherry-picks). Deferred rows are provisional
— re-inspect before picking. See the fork-maintenance runbook in `CLAUDE.md` .
2026-07-13 12:45:10 -04:00
**Last synced `upstream/main` :** `30832d29` (2026-07-13)
2026-07-03 11:46:00 -04:00
| sha | pr | subject | decision | why | branch |
|---|---|---|---|---|---|
| `0b76afdc` | #1653 | reviews block agenda, sticky headers, diff scroll | Landed | | cherry-pick-upstream |
| `7530653b` | #1655 | ResizeObserver settle for review scroll-to | Landed | | cherry-pick-upstream |
| `23bd4a63` | #1660 | top padding to sticky review block header | Landed | | cherry-pick-upstream |
| `9e5a1924` | #1656 | purge expired thread_wakeup crons | Landed | | cherry-pick-upstream |
| `63eb9a08` | #1661 | sidebar filter popover border tokens | Landed | | cherry-pick-upstream |
| `bc7ce591` | #1668 | preserve dashboard redirect after login | Landed | | cherry-pick-upstream |
| `f32e492a` | #1637 | return to thread after plan approval | Landed | | cherry-pick-upstream |
| `7ee3e057` | #1636 | make plan view mobile friendly | Landed | | cherry-pick-upstream |
| `6575c327` | #1654 | disable React StrictMode | Landed | kept fork's `PwaUpdateProvider` | cherry-pick-upstream |
2026-07-08 19:02:09 -04:00
| `00906401` | #1610 | editable plan mode | Landed | re-implemented in fork via #130 (editable plan mode) | |
2026-07-08 19:20:26 -04:00
| `f5670f24` | #1639 | require bun for ui agent work | Landed | cherry-picked (-x) in this PR (#132 ) | PR1 |
feat: port durable dispatch hardening and startup latency improvements (#160)
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* feat: port durable dispatch hardening and startup latency improvements
Port five upstream PRs onto dev:
- #1621 / #1658: durable dispatch with loopback webhook defense,
create_durable_run helper, _config_with_prepare_run_id, degradation
to None for relative/loopback completion webhook URLs
- #1696: run-level completion webhook deduplication (replace
claim-then-post with post-then-flag per run_id), DeferredErrorModel
for graph-factory resilience, ToolRetryMiddleware for task subagents,
TimeoutWrapupMiddleware for all three graphs
- #1697: lazy-load __init__.py for agent.middleware, agent.tools,
agent.dashboard (PEP 562); defer heavy imports (exa_py in web_search,
agent.webapp in request_pr_review, deepagents in sandbox.py); add
ttl_cache.py with stale-while-revalidate for tool loaders
Refs: #137
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* fix: restore RepairOrphaned middleware export and repoint model fake to deferred_model boundary
* fix: restore RepairOrphanedToolCallsMiddleware, fix E2E model-fake patch, drop dead ttl_cache
- Re-add RepairOrphanedToolCallsMiddleware to the lazy middleware __init__
(_MIDDLEWARE_MODULES, __all__, TYPE_CHECKING) so agent.reviewer can import it.
- Reroute E2E model patching to deferred_model.make_model so make_model_or_defer
(used by all three graph factories) returns the scripted fake instead of
building a real model with fake credentials.
- Drop unused agent/utils/ttl_cache.py — no agent module imports it.
- Fix import ordering in agent/reviewer.py and agent/analyzer.py (ruff I001).
- Format tests/test_dispatch.py.
* fix: claim-then-post run-level failure dedup; stop permanent suppression
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
2026-07-09 17:11:25 -04:00
| `209132d3` | #1621 | durable interrupt dispatch + completion webhook | Landed | investigate first — may be applied | durable-dispatch |
| `02bb4dfd` | #1658 | don't attach loopback run-complete webhooks | Landed | | durable-dispatch |
| `29015fad` | #1614 | gate workflow pushes with approval | Landed | | durable-dispatch |
feat: port plan-review & workflow-approval UX (#159)
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* fix: carry workflows:write on the standing proxy token
Complete the half-ported upstream 216cf181 cascade. The port dropped
_run_with_workflow_token from the guard but missed the paired github_app
change, so an approved .github/workflows push ran with the base token
(no workflows:write) and GitHub 403'd it.
Add workflows:write to BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS and delete the
now-orphaned WORKFLOW_RUNTIME_PROXY_TOKEN_PERMISSIONS constant; update the
github_app and proxy_auth tests to match. The HITL approval gate in
workflow_push_guard.py is unchanged — this only lets the standing token
push once a human approves.
* fix: restore transient workflow-token elevation (revert standing workflows:write)
The standing GitHub-App proxy token (BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS) is
ALWAYS-ON, so carrying workflows:write on it made the fork's HITL workflow-push
guard the sole control over unapproved workflow pushes. The guard's git-push
parser has gaps (obfuscated-expansion push, `gh api` REST contents PUT,
fully-qualified cross-branch refspecs); with a permanently workflows-scoped
token those gaps become live unapproved-workflow-push exploits (1 critical, 2
high — security review BLOCK on #159).
Restore dev's transient-elevation model:
- Drop workflows:write from BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS; re-add the
WORKFLOW_RUNTIME_PROXY_TOKEN_PERMISSIONS constant (base + workflows:write).
- Re-introduce _run_with_workflow_token in the guard: it mints the
workflows-scoped token via refresh_proxy_token around the approved,
guard-normalized fixed_command, then downscopes to RUNTIME then BASE in a
finally. Route the approval branch through it.
- Restore the dev token/elevation tests.
The standing token no longer carries workflows:write, so the three parser
bypasses hit GitHub 403 again; an approved push still succeeds because the
elevation grants workflows:write only around the normalized command. Keeps all
of #159's diff-preview / approval-URL / Slack-card guard additions.
* fix: reject protocol-relative path from sanitizeAuthRedirect (open redirect)
sanitizeAuthRedirect returned parsed.pathname+search+hash, which `new URL` can
resolve to a protocol-relative `//host` (e.g. input `/..//evil.com` normalizes
same-origin, passing the origin check, but yields a path starting with `//`).
ClientRedirect / login.tsx feed that path to window.location.replace, so it
navigates cross-origin — an open redirect. Reject any resolved path that is not
a single-leading-slash path (`^/[^/]`), falling back to the default. Adds
coverage for `/..//evil.com`, `/.//evil.com`, and `//evil.com`.
* fix: log SECURITY error when workflow-token downscope fails
The elevate->push->downscope finally block was silent on failure. If both
refresh_proxy_token calls fail, the sandbox retains workflows:write for the
rest of the run with no signal. Log a SECURITY error on the partial and full
downscope-failure paths so the retention is observable.
Addresses the GPT-4.1 cross-family review of the token-scope remediation.
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
2026-07-09 16:03:13 -04:00
| `546042a4` | #1652 | add workflow approval UI | Landed | | plan-approval |
2026-07-08 19:02:09 -04:00
| `ae04b72b` | #1635 | publish plans from sandbox files | Landed | ported (adapted) in #128 (save_plan reads sandbox file) | plan-approval |
feat: port plan-review & workflow-approval UX (#159)
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* fix: carry workflows:write on the standing proxy token
Complete the half-ported upstream 216cf181 cascade. The port dropped
_run_with_workflow_token from the guard but missed the paired github_app
change, so an approved .github/workflows push ran with the base token
(no workflows:write) and GitHub 403'd it.
Add workflows:write to BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS and delete the
now-orphaned WORKFLOW_RUNTIME_PROXY_TOKEN_PERMISSIONS constant; update the
github_app and proxy_auth tests to match. The HITL approval gate in
workflow_push_guard.py is unchanged — this only lets the standing token
push once a human approves.
* fix: restore transient workflow-token elevation (revert standing workflows:write)
The standing GitHub-App proxy token (BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS) is
ALWAYS-ON, so carrying workflows:write on it made the fork's HITL workflow-push
guard the sole control over unapproved workflow pushes. The guard's git-push
parser has gaps (obfuscated-expansion push, `gh api` REST contents PUT,
fully-qualified cross-branch refspecs); with a permanently workflows-scoped
token those gaps become live unapproved-workflow-push exploits (1 critical, 2
high — security review BLOCK on #159).
Restore dev's transient-elevation model:
- Drop workflows:write from BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS; re-add the
WORKFLOW_RUNTIME_PROXY_TOKEN_PERMISSIONS constant (base + workflows:write).
- Re-introduce _run_with_workflow_token in the guard: it mints the
workflows-scoped token via refresh_proxy_token around the approved,
guard-normalized fixed_command, then downscopes to RUNTIME then BASE in a
finally. Route the approval branch through it.
- Restore the dev token/elevation tests.
The standing token no longer carries workflows:write, so the three parser
bypasses hit GitHub 403 again; an approved push still succeeds because the
elevation grants workflows:write only around the normalized command. Keeps all
of #159's diff-preview / approval-URL / Slack-card guard additions.
* fix: reject protocol-relative path from sanitizeAuthRedirect (open redirect)
sanitizeAuthRedirect returned parsed.pathname+search+hash, which `new URL` can
resolve to a protocol-relative `//host` (e.g. input `/..//evil.com` normalizes
same-origin, passing the origin check, but yields a path starting with `//`).
ClientRedirect / login.tsx feed that path to window.location.replace, so it
navigates cross-origin — an open redirect. Reject any resolved path that is not
a single-leading-slash path (`^/[^/]`), falling back to the default. Adds
coverage for `/..//evil.com`, `/.//evil.com`, and `//evil.com`.
* fix: log SECURITY error when workflow-token downscope fails
The elevate->push->downscope finally block was silent on failure. If both
refresh_proxy_token calls fail, the sandbox retains workflows:write for the
rest of the run with no signal. Log a SECURITY error on the partial and full
downscope-failure paths so the retention is observable.
Addresses the GPT-4.1 cross-family review of the token-scope remediation.
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
2026-07-09 16:03:13 -04:00
| `c03a6be7` | #1634 | keep plan guidance high-level | Landed | | plan-approval |
2026-07-08 19:02:09 -04:00
| `96cceb74` | #1632 | notify Slack on plan approval | Landed | ported (adapted) in #128 | plan-approval |
2026-07-08 19:27:31 -04:00
| `2f56d754` | #1618 | omit plan link when no plan exists | Landed | already in dev via #81 (upstream-sync); ledger was stale (was: likely regression) | plan-approval |
2026-07-03 15:51:31 -04:00
| `ee224d3e` | #1650 | add Slack reaction tool | Landed | | slack-tooling |
| `747ce4bb` | #1638 | add Slack breakout thread tool | Landed | | slack-tooling |
| `27d90ef1` | #1633 | include Slack channel context in prompts | Landed | | slack-tooling |
2026-07-08 19:02:09 -04:00
| `92dbf6f9` | #1630 | update Slack trace reply on web handoff | Landed | ported in #128 (trace_message_ts on first-mention run mapping) | slack-tooling |
2026-07-03 15:51:31 -04:00
| `bb36448b` | #1627 | surface Slack thread errors | Landed | | slack-tooling |
feat: port LangSmith LLM Gateway routing from upstream (#1671, #1673, #1674, #1678) (#155)
* 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>
2026-07-09 14:44:15 -04:00
| `73b7d1c0` | #1678 | fix OpenAI Responses reasoning replay | Landed | | gateway-routing |
| `5f7c2f46` | #1674 | fix Fireworks Gateway base URL | Landed | | gateway-routing |
| `702ef908` | #1673 | dedicated LangSmith gateway API key | Landed | | gateway-routing |
| `e9dc6e01` | #1671 | opt-in LangSmith LLM Gateway routing | Landed | | gateway-routing |
2026-07-03 11:46:00 -04:00
| `289f5e3a` | #1651 | add Sonnet 5 to model picker | Landed | already in dev; added Bedrock family fallback fix (c16fb915) | gateway-routing |
2026-07-08 19:02:09 -04:00
| `5da3d0c6` | #1624 | post reviewer resolution notes verbatim | Landed | cherry-picked (-x) in #127 | reviewer-misc |
| `69148f54` | #1612 | add PR trace resolution | Landed | cherry-picked (-x) in #127 | reviewer-misc |
| `6d125526` | #1625 | stop wrapping installs in sfw | Landed | already present in dev; empty pick confirmed in #127 | reviewer-misc |
| `320bb39a` | #1657 | opt-in tracemalloc for aiohttp sessions | Landed | cherry-picked (-x) in #127 | reviewer-misc |
| `4f913198` | #1647 | widen split review diffs | Landed | already present in dev; empty pick confirmed in #127 | reviewer-misc |
2026-07-08 19:27:31 -04:00
| `20f63e8c` | #1646 | install missing deps before verification | Landed | already in dev via #81 (upstream-sync); ledger was stale | prompt-tweaks |
2026-07-08 19:02:09 -04:00
| `2f237b53` | #1626 | fall back to vision model for image threads | Landed | ported (adapted to Bedrock/Fireworks vision) in #128 | gateway-routing |
2026-07-10 13:00:12 -04:00
| `fbc6de85` | #1667 | chore(deps): bump fireworks-ai from 1.2.0a75 to 1.2.0a86 (#1667 ) | Landed | Superseded by #158 (fireworks-ai a85 -> a88, efeb6b12); dev already exceeds a86. No port needed. | deps |
feat: port model-fallback resilience from upstream (#1694, #1695) (#161)
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* feat: port durable dispatch hardening and startup latency improvements
Port five upstream PRs onto dev:
- #1621 / #1658: durable dispatch with loopback webhook defense,
create_durable_run helper, _config_with_prepare_run_id, degradation
to None for relative/loopback completion webhook URLs
- #1696: run-level completion webhook deduplication (replace
claim-then-post with post-then-flag per run_id), DeferredErrorModel
for graph-factory resilience, ToolRetryMiddleware for task subagents,
TimeoutWrapupMiddleware for all three graphs
- #1697: lazy-load __init__.py for agent.middleware, agent.tools,
agent.dashboard (PEP 562); defer heavy imports (exa_py in web_search,
agent.webapp in request_pr_review, deepagents in sandbox.py); add
ttl_cache.py with stale-while-revalidate for tool loaders
Refs: #137
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* feat: port model-fallback resilience from upstream (#1694, #1695)
- Add httpx.TransportError to the transient-exception set so
incomplete chunked reads on streamed responses trigger a
fallback instead of cancelling the run (#1694 / c9f6dd86).
- Rewrite fallback to alternate primary/fallback with exponential
backoff instead of a single failover, so the agent survives
multi-minute gateway outages spanning both providers (#1695 /
c9a9a7cd).
- Default backoff schedule (0, 5, 15, 30, 45) reaches past the
gateway's ~30s recovery window; jittered ±25%.
- On exhaustion, surface a terminal AIMessage explaining the
outage instead of crashing — progress is checkpointed so the
user can retrigger to continue.
- Preserve fork conventions: Bedrock ClientError retryability
check, sync wrap_model_call (using time.sleep instead of
asyncio.sleep), and existing access-error surfacing for
Anthropic, OpenAI, and Bedrock (botocore) provider errors.
- Update triage ledger (c9f6dd86, c9a9a7cd → landed) and
re-render triage.md.
Refs: #139
* fix: align workflow-push-guard tests with dev's transient-elevation impl
The dev merge auto-combined dev's elevation tests with the stale passthrough
tests inherited from the durable-dispatch branch; the passthrough tests
contradict dev's restored _run_with_workflow_token impl. Take dev's test file.
* fix: drop dead ttl_cache module; make fallback backoff jitter two-sided
ttl_cache.py was re-introduced via the dev merge but dev/#160 deliberately
removed it as dead code (no agent importer). Remove it to match dev.
Also make _jittered_delay symmetric (±25%) to match its docstring.
* chore(upstream-sync): triage 4 new upstream commits (#1708-#1713)
Synced ledger to upstream/main (71e3b818). New rows all deferred:
- #1708 add GPT-5.6 OpenAI models (FLAG-HUMAN: fork picker is Bedrock/Fireworks-only)
- #1709 stale admin model defaults after upgrades
- #1710 bump langchain-fireworks 1.4.4
- #1713 align reviewer eval with published findings
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
2026-07-09 18:28:21 -04:00
| `c9f6dd86` | #1694 | fix: fall back on model stream transport errors (#1694 ) | Landed | adds httpx.TransportError to transient set; small conflict w/ dev's diverged Bedrock fallback | model-fallback |
| `c9a9a7cd` | #1695 | fix: retry model fallback exhaustion (#1695 ) | Landed | alternating retry+backoff rewrite; reconcile by hand w/ dev's Bedrock + sync wrap path | model-fallback |
feat: port durable dispatch hardening and startup latency improvements (#160)
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* feat: port durable dispatch hardening and startup latency improvements
Port five upstream PRs onto dev:
- #1621 / #1658: durable dispatch with loopback webhook defense,
create_durable_run helper, _config_with_prepare_run_id, degradation
to None for relative/loopback completion webhook URLs
- #1696: run-level completion webhook deduplication (replace
claim-then-post with post-then-flag per run_id), DeferredErrorModel
for graph-factory resilience, ToolRetryMiddleware for task subagents,
TimeoutWrapupMiddleware for all three graphs
- #1697: lazy-load __init__.py for agent.middleware, agent.tools,
agent.dashboard (PEP 562); defer heavy imports (exa_py in web_search,
agent.webapp in request_pr_review, deepagents in sandbox.py); add
ttl_cache.py with stale-while-revalidate for tool loaders
Refs: #137
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* fix: restore RepairOrphaned middleware export and repoint model fake to deferred_model boundary
* fix: restore RepairOrphanedToolCallsMiddleware, fix E2E model-fake patch, drop dead ttl_cache
- Re-add RepairOrphanedToolCallsMiddleware to the lazy middleware __init__
(_MIDDLEWARE_MODULES, __all__, TYPE_CHECKING) so agent.reviewer can import it.
- Reroute E2E model patching to deferred_model.make_model so make_model_or_defer
(used by all three graph factories) returns the scripted fake instead of
building a real model with fake credentials.
- Drop unused agent/utils/ttl_cache.py — no agent module imports it.
- Fix import ordering in agent/reviewer.py and agent/analyzer.py (ruff I001).
- Format tests/test_dispatch.py.
* fix: claim-then-post run-level failure dedup; stop permanent suppression
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
2026-07-09 17:11:25 -04:00
| `e5dbc788` | #1696 | fix: Harden durable agent runs (#1696 ) | Landed | large durable-run hardening; 3 new modules dev lacks; rewrites fork dispatch/completion | durable-dispatch |
2026-07-08 19:02:09 -04:00
| `52fe2916` | #1698 | feat: add PR review link route (#1698 ) | Landed | cherry-picked (-x) in #127 (PR review link route) | reviewer-misc |
feat: port durable dispatch hardening and startup latency improvements (#160)
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* feat: port durable dispatch hardening and startup latency improvements
Port five upstream PRs onto dev:
- #1621 / #1658: durable dispatch with loopback webhook defense,
create_durable_run helper, _config_with_prepare_run_id, degradation
to None for relative/loopback completion webhook URLs
- #1696: run-level completion webhook deduplication (replace
claim-then-post with post-then-flag per run_id), DeferredErrorModel
for graph-factory resilience, ToolRetryMiddleware for task subagents,
TimeoutWrapupMiddleware for all three graphs
- #1697: lazy-load __init__.py for agent.middleware, agent.tools,
agent.dashboard (PEP 562); defer heavy imports (exa_py in web_search,
agent.webapp in request_pr_review, deepagents in sandbox.py); add
ttl_cache.py with stale-while-revalidate for tool loaders
Refs: #137
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* fix: restore RepairOrphaned middleware export and repoint model fake to deferred_model boundary
* fix: restore RepairOrphanedToolCallsMiddleware, fix E2E model-fake patch, drop dead ttl_cache
- Re-add RepairOrphanedToolCallsMiddleware to the lazy middleware __init__
(_MIDDLEWARE_MODULES, __all__, TYPE_CHECKING) so agent.reviewer can import it.
- Reroute E2E model patching to deferred_model.make_model so make_model_or_defer
(used by all three graph factories) returns the scripted fake instead of
building a real model with fake credentials.
- Drop unused agent/utils/ttl_cache.py — no agent module imports it.
- Fix import ordering in agent/reviewer.py and agent/analyzer.py (ruff I001).
- Format tests/test_dispatch.py.
* fix: claim-then-post run-level failure dedup; stop permanent suppression
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
2026-07-09 17:11:25 -04:00
| `5f7f5fbd` | #1697 | fix: Reduce graph import and loader startup latency (#1697 ) | Landed | import-hygiene refactor; cross-cutting, references many deferred upstream-only modules | durable-dispatch |
feat: port plan-review & workflow-approval UX (#159)
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* fix: carry workflows:write on the standing proxy token
Complete the half-ported upstream 216cf181 cascade. The port dropped
_run_with_workflow_token from the guard but missed the paired github_app
change, so an approved .github/workflows push ran with the base token
(no workflows:write) and GitHub 403'd it.
Add workflows:write to BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS and delete the
now-orphaned WORKFLOW_RUNTIME_PROXY_TOKEN_PERMISSIONS constant; update the
github_app and proxy_auth tests to match. The HITL approval gate in
workflow_push_guard.py is unchanged — this only lets the standing token
push once a human approves.
* fix: restore transient workflow-token elevation (revert standing workflows:write)
The standing GitHub-App proxy token (BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS) is
ALWAYS-ON, so carrying workflows:write on it made the fork's HITL workflow-push
guard the sole control over unapproved workflow pushes. The guard's git-push
parser has gaps (obfuscated-expansion push, `gh api` REST contents PUT,
fully-qualified cross-branch refspecs); with a permanently workflows-scoped
token those gaps become live unapproved-workflow-push exploits (1 critical, 2
high — security review BLOCK on #159).
Restore dev's transient-elevation model:
- Drop workflows:write from BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS; re-add the
WORKFLOW_RUNTIME_PROXY_TOKEN_PERMISSIONS constant (base + workflows:write).
- Re-introduce _run_with_workflow_token in the guard: it mints the
workflows-scoped token via refresh_proxy_token around the approved,
guard-normalized fixed_command, then downscopes to RUNTIME then BASE in a
finally. Route the approval branch through it.
- Restore the dev token/elevation tests.
The standing token no longer carries workflows:write, so the three parser
bypasses hit GitHub 403 again; an approved push still succeeds because the
elevation grants workflows:write only around the normalized command. Keeps all
of #159's diff-preview / approval-URL / Slack-card guard additions.
* fix: reject protocol-relative path from sanitizeAuthRedirect (open redirect)
sanitizeAuthRedirect returned parsed.pathname+search+hash, which `new URL` can
resolve to a protocol-relative `//host` (e.g. input `/..//evil.com` normalizes
same-origin, passing the origin check, but yields a path starting with `//`).
ClientRedirect / login.tsx feed that path to window.location.replace, so it
navigates cross-origin — an open redirect. Reject any resolved path that is not
a single-leading-slash path (`^/[^/]`), falling back to the default. Adds
coverage for `/..//evil.com`, `/.//evil.com`, and `//evil.com`.
* fix: log SECURITY error when workflow-token downscope fails
The elevate->push->downscope finally block was silent on failure. If both
refresh_proxy_token calls fail, the sandbox retains workflows:write for the
rest of the run with no signal. Log a SECURITY error on the partial and full
downscope-failure paths so the retention is observable.
Addresses the GPT-4.1 cross-family review of the token-scope remediation.
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
2026-07-09 16:03:13 -04:00
| `216cf181` | #1699 | fix: keep workflow HITL without token downscoping (#1699 ) | Landed | DIVERGES-FROM-UPSTREAM: fork deliberately does NOT adopt #1699 's standing-token workflows:write broadening. Security review (#159 ) BLOCKed it — the standing ALWAYS-ON proxy token carrying workflows:write turns the HITL guard's git-push-parser gaps (obfuscated-expansion push, `gh api` REST contents PUT, cross-branch refspecs) into live unapproved-workflow-push exploits. Fork keeps BASE without workflows:write and restores the transient per-approval elevation (_run_with_workflow_token mints WORKFLOW_RUNTIME_PROXY_TOKEN_PERMISSIONS around the approved, guard-normalized fixed_command, then downscopes to RUNTIME then BASE): the token scope is the backstop the parser relies on, so a bypass hits GitHub 403. HITL diff-preview/approval-URL/Slack-card additions from #159 retained; token-model divergence only. | plan-approval |
| `3dbc0282` | #1676 | fix: preserve plan redirects after login (#1676 ) | Landed | FLAG-HUMAN: follow-on to landed #1668 refining sanitize_redirect_to (open-redirect auth surface); not a dup | plan-approval |
2026-07-10 14:05:20 -04:00
| `c75cbb1f` | #1677 | feat: re-add Fable 5 with an admin toggle to disable it (#1677 ) | Landed | Ported + Bedrock-converted onto dev via feat/readd-fable5-bedrock; anthropic: Fable ID mapped to bedrock_converse:us.anthropic.claude-fable-5. | fable-admin-toggle |
feat: port plan-review & workflow-approval UX (#159)
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* fix: carry workflows:write on the standing proxy token
Complete the half-ported upstream 216cf181 cascade. The port dropped
_run_with_workflow_token from the guard but missed the paired github_app
change, so an approved .github/workflows push ran with the base token
(no workflows:write) and GitHub 403'd it.
Add workflows:write to BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS and delete the
now-orphaned WORKFLOW_RUNTIME_PROXY_TOKEN_PERMISSIONS constant; update the
github_app and proxy_auth tests to match. The HITL approval gate in
workflow_push_guard.py is unchanged — this only lets the standing token
push once a human approves.
* fix: restore transient workflow-token elevation (revert standing workflows:write)
The standing GitHub-App proxy token (BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS) is
ALWAYS-ON, so carrying workflows:write on it made the fork's HITL workflow-push
guard the sole control over unapproved workflow pushes. The guard's git-push
parser has gaps (obfuscated-expansion push, `gh api` REST contents PUT,
fully-qualified cross-branch refspecs); with a permanently workflows-scoped
token those gaps become live unapproved-workflow-push exploits (1 critical, 2
high — security review BLOCK on #159).
Restore dev's transient-elevation model:
- Drop workflows:write from BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS; re-add the
WORKFLOW_RUNTIME_PROXY_TOKEN_PERMISSIONS constant (base + workflows:write).
- Re-introduce _run_with_workflow_token in the guard: it mints the
workflows-scoped token via refresh_proxy_token around the approved,
guard-normalized fixed_command, then downscopes to RUNTIME then BASE in a
finally. Route the approval branch through it.
- Restore the dev token/elevation tests.
The standing token no longer carries workflows:write, so the three parser
bypasses hit GitHub 403 again; an approved push still succeeds because the
elevation grants workflows:write only around the normalized command. Keeps all
of #159's diff-preview / approval-URL / Slack-card guard additions.
* fix: reject protocol-relative path from sanitizeAuthRedirect (open redirect)
sanitizeAuthRedirect returned parsed.pathname+search+hash, which `new URL` can
resolve to a protocol-relative `//host` (e.g. input `/..//evil.com` normalizes
same-origin, passing the origin check, but yields a path starting with `//`).
ClientRedirect / login.tsx feed that path to window.location.replace, so it
navigates cross-origin — an open redirect. Reject any resolved path that is not
a single-leading-slash path (`^/[^/]`), falling back to the default. Adds
coverage for `/..//evil.com`, `/.//evil.com`, and `//evil.com`.
* fix: log SECURITY error when workflow-token downscope fails
The elevate->push->downscope finally block was silent on failure. If both
refresh_proxy_token calls fail, the sandbox retains workflows:write for the
rest of the run with no signal. Log a SECURITY error on the partial and full
downscope-failure paths so the retention is observable.
Addresses the GPT-4.1 cross-family review of the token-scope remediation.
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
2026-07-09 16:03:13 -04:00
| `bb104d93` | #1679 | fix: submit plan comments with cmd enter (#1679 ) | Landed | applies clean but edits fork-diverged PlanReview.tsx (#130 ); needs UI/e2e validation — separate PR | plan-approval |
2026-07-10 13:17:03 -04:00
| `feb7ac98` | #1689 | feat(web): surface thread sandbox ID with touch-friendly menu (#1689 ) | Landed | Ported to dev via feat/thread-sandbox-id-sidebar. | dashboard-ui |
2026-07-08 19:02:09 -04:00
| `7f7af715` | #1684 | feat: auto-load scoped AGENTS on reads (#1684 ) | Landed | ported in #129 (SubdirAgentsReadMiddleware) | subdir-agents |
| `88b62322` | #1685 | feat: add platform issue reporting tool (#1685 ) | Landed | ported in #129 (report_platform_issue tool) | small-tools |
feat: port plan-review & workflow-approval UX (#159)
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* fix: carry workflows:write on the standing proxy token
Complete the half-ported upstream 216cf181 cascade. The port dropped
_run_with_workflow_token from the guard but missed the paired github_app
change, so an approved .github/workflows push ran with the base token
(no workflows:write) and GitHub 403'd it.
Add workflows:write to BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS and delete the
now-orphaned WORKFLOW_RUNTIME_PROXY_TOKEN_PERMISSIONS constant; update the
github_app and proxy_auth tests to match. The HITL approval gate in
workflow_push_guard.py is unchanged — this only lets the standing token
push once a human approves.
* fix: restore transient workflow-token elevation (revert standing workflows:write)
The standing GitHub-App proxy token (BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS) is
ALWAYS-ON, so carrying workflows:write on it made the fork's HITL workflow-push
guard the sole control over unapproved workflow pushes. The guard's git-push
parser has gaps (obfuscated-expansion push, `gh api` REST contents PUT,
fully-qualified cross-branch refspecs); with a permanently workflows-scoped
token those gaps become live unapproved-workflow-push exploits (1 critical, 2
high — security review BLOCK on #159).
Restore dev's transient-elevation model:
- Drop workflows:write from BASE_RUNTIME_PROXY_TOKEN_PERMISSIONS; re-add the
WORKFLOW_RUNTIME_PROXY_TOKEN_PERMISSIONS constant (base + workflows:write).
- Re-introduce _run_with_workflow_token in the guard: it mints the
workflows-scoped token via refresh_proxy_token around the approved,
guard-normalized fixed_command, then downscopes to RUNTIME then BASE in a
finally. Route the approval branch through it.
- Restore the dev token/elevation tests.
The standing token no longer carries workflows:write, so the three parser
bypasses hit GitHub 403 again; an approved push still succeeds because the
elevation grants workflows:write only around the normalized command. Keeps all
of #159's diff-preview / approval-URL / Slack-card guard additions.
* fix: reject protocol-relative path from sanitizeAuthRedirect (open redirect)
sanitizeAuthRedirect returned parsed.pathname+search+hash, which `new URL` can
resolve to a protocol-relative `//host` (e.g. input `/..//evil.com` normalizes
same-origin, passing the origin check, but yields a path starting with `//`).
ClientRedirect / login.tsx feed that path to window.location.replace, so it
navigates cross-origin — an open redirect. Reject any resolved path that is not
a single-leading-slash path (`^/[^/]`), falling back to the default. Adds
coverage for `/..//evil.com`, `/.//evil.com`, and `//evil.com`.
* fix: log SECURITY error when workflow-token downscope fails
The elevate->push->downscope finally block was silent on failure. If both
refresh_proxy_token calls fail, the sandbox retains workflows:write for the
rest of the run with no signal. Log a SECURITY error on the partial and full
downscope-failure paths so the retention is observable.
Addresses the GPT-4.1 cross-family review of the token-scope remediation.
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
2026-07-09 16:03:13 -04:00
| `90cb6caa` | #1681 | feat: terse Slack replies, share long content via plan-review page (#1681 ) | Landed | terse Slack + long-content-via-plan-page; conflicts w/ fork prompt + diverged plan stack | plan-approval |
2026-07-03 11:46:00 -04:00
| `c3292d82` | #1611 | bake sfw binary into sandbox image | Won't merge | already in dev | |
| `48bf712b` | #1609 | show message timestamps | Won't merge | already in dev | |
| `85c0f63e` | #1620 | clickable shared PR header | Won't merge | already in dev | |
| `db2ae58e` | #1643 | pre-bundle shiki/@pierre deps | Won't merge | already in dev | |
| `1d9da064` | #1662 | bump astral-sh/setup-uv | Won't merge | dev ahead (v8.2.0, `checkout@v7` ) | |
| `83cb40a0` | #1616 | update langsmith sdk to 0.9.3 | Won't merge | regression — dev has 0.9.6 | |
| `e5a29eca` | #1613 | plan links in PR descriptions | Won't merge | regression — dev has async plan-ref | |
| `e1d85526` | #1645 | switch ui to pnpm | Won't merge | tooling — fork keeps bun | |
2026-07-08 19:02:09 -04:00
| `5dc360d8` | #1619 | bump langgraph-checkpoint 4.1.0→4.1.1 | Won't merge | already in dev — uv.lock already resolves langgraph-checkpoint 4.1.1 | |
| `89f886e2` | #1642 | request actions read for sandbox logs | Won't merge | already in dev — actions:read in RUNTIME_PROXY_TOKEN_PERMISSIONS + identical prompt line | |
| `ab4eea4b` | #1663 | chore(deps): bump the major group across 1 directory with 3 updates (#1663 ) | Won't merge | already in dev — CI already on checkout@v7/setup -node@v6/upload -artifact@v7 | |
| `2bf207fb` | #1664 | chore(deps): bump python in the minor-and-patch group (#1664 ) | Won't merge | already in dev — Dockerfile already at python 3.14.6-slim-trixie | |
| `13b40113` | #1666 | chore(deps): bump cryptography from 48.0.1 to 49.0.0 in the major group (#1666 ) | Won't merge | already in dev — same 48->49 cryptography bump dev did via #105 | |
| `290d0fee` | #1669 | chore(deps): update langgraph-cli[inmem] requirement (#1669 ) | Won't merge | already in dev — langgraph-cli[inmem] at 0.4.30 | |
| `73a9e8b5` | #1693 | chore(deps): bump the minor-and-patch group across 1 directory with 19 updates (#1693 ) | Won't merge | dev at-or-ahead on 17/19; group fights dev's pinned langsmith==0.9.7 (#115 ) and carries an upstream plan-route test | |
| `9cd7e464` | #1700 | Fix workflow approval visibility (#1700 ) | Won't merge | superseded — dev's list_workflow_approvals_for_thread already enforces owner-only 403 | |
| `fd2541ce` | #1705 | fix: drop orphaned function_call items with stale OpenAI reasoning (#1705 ) | Won't merge | N/A — edits sanitize_openai_responses.py which dev deleted in the Bedrock/Fireworks migration (#62 ) | |
2026-07-03 11:46:00 -04:00
| `4cd5fa5c` | #1629 | avoid recapping Slack replies | Deferred | | slack-tooling |
| `baf0c248` | #1617 | filter & grouping menu in threads sidebar | Deferred | ~998 LOC | own branch |
| `f29868ff` | #1615 | recover thread work as patch | Deferred | ~495 LOC | own branch |
| `8e0788dc` | #1631 | show queued dashboard follow-ups | Deferred | | own branch |
| `9c601ca1` | #1648 | add Stagehand-powered browser subagent | Deferred | | own branch |
| `8c944381` | #1622 | restore forced tool call | Deferred | | own branch |
2026-07-08 19:02:09 -04:00
| `27f987dc` | #1686 | refactor: remove dead sync-interface compatibility code (#1686 ) | Deferred | chain head: dead-code removal (get_sandbox_backend_sync); pointless alone | sandbox-refactor |
| `2503a2f4` | #1687 | refactor(open-swe): provision LangSmith sandboxes natively async (#1687 ) | Deferred | FLAG-HUMAN: load-bearing async pivot of create_sandbox + _configure_github_proxy (GitHub-App auth surface) | sandbox-refactor |
| `2529b109` | #1690 | fix: checkpoint per-run graph setup (#1690 ) | Deferred | per-run graph-setup checkpoint; built on async server.py; entangled | sandbox-refactor |
| `c0a7e93e` | #1691 | fix: reconnect sandbox backend on resumed runs (#1691 ) | Deferred | reconnect proxy (has_backend/reconnect); assumes async create_sandbox | sandbox-refactor |
| `4f8bc2dd` | #1692 | refactor: simplify open-swe agent sandbox lifecycle (#1692 ) | Deferred | FLAG-HUMAN: structural rewrite of ensure_sandbox_for_thread (drops __creating__ 4-case sentinel) | sandbox-refactor |
| `48217b68` | #1489 | feat(open-swe): add E2B sandbox provider (#1489 ) | Deferred | additive E2B provider; separable but ships on the async sandbox.py base | sandbox-refactor |
| `67abf5b0` | #1659 | fix: surface attributed PR creation failures (#1659 ) | Deferred | PR-attribution-failure guard (new mw, safe imports); heavy conflict on diverged open_pull_request.py | pr-attribution |
| `304032fa` | #1680 | chore: clarify question answering prompt (#1680 ) | Deferred | reword Slack info-only answer guidance; conflicts w/ fork's customized Slack prompt | prompt-tweaks |
| `5003c953` | #1683 | feat: open Linear-triggered PRs as the triggering user (#1683 ) | Deferred | FLAG-HUMAN: adds linear to resolve_github_token per-user OAuth branch (auth surface); depends on #1626 linear.py | linear-pr-as-user |
| `f53caff1` | #1701 | fix: fall back to core GitHub App scope when optional grants missing (#1701 ) | Deferred | FLAG-HUMAN: GitHub-App permission-ladder degrade (auth surface); heavy conflict on diverged github_app.py/_resolve_proxy_token | github-app-scope |
| `22e024cb` | #1704 | fix: link issue PRs and prompt repo conventions (#1704 ) | Deferred | issue/PR linking + repo-convention prompt; clean but prompt-conflict risk vs #113 | webhook-issue-linking |
feat: port model-fallback resilience from upstream (#1694, #1695) (#161)
* feat: port plan-review & workflow-approval UX (#135)
Port six upstream commits onto dev:
- c03a6be7 (already ported): keep plan guidance high-level
- 546042a4: add workflow approval UI with diff preview, approval URLs,
web review links, and polling for approval status during active runs
- 216cf181: remove workflow token elevation; approved pushes pass
through directly without proxy token rewriting
- 3dbc0282: preserve plan redirects after login by accepting relative
same-origin redirect_to values and rejecting blocked paths
- bb104d93: submit plan comments with cmd+enter
- 90cb6caa: terse Slack replies, shared content via save_plan outside
plan mode (PLAN_STATUS_SHARED), reject shared-content mutations
Refs: #135
* feat: port durable dispatch hardening and startup latency improvements
Port five upstream PRs onto dev:
- #1621 / #1658: durable dispatch with loopback webhook defense,
create_durable_run helper, _config_with_prepare_run_id, degradation
to None for relative/loopback completion webhook URLs
- #1696: run-level completion webhook deduplication (replace
claim-then-post with post-then-flag per run_id), DeferredErrorModel
for graph-factory resilience, ToolRetryMiddleware for task subagents,
TimeoutWrapupMiddleware for all three graphs
- #1697: lazy-load __init__.py for agent.middleware, agent.tools,
agent.dashboard (PEP 562); defer heavy imports (exa_py in web_search,
agent.webapp in request_pr_review, deepagents in sandbox.py); add
ttl_cache.py with stale-while-revalidate for tool loaders
Refs: #137
* fix: restore login page render and clear CI lint/format
The plan-review port removed the authRedirectUrl import from login.tsx
but left its call site, crashing the login page at runtime (blank page,
no 'Sign in to open-swe'). Pass the relative path straight to loginUrl,
matching the plan route and the backend relative-redirect handling.
Also drop an unused os import in the guard test and reformat
workflow_push_guard.py to satisfy ruff.
* feat: port model-fallback resilience from upstream (#1694, #1695)
- Add httpx.TransportError to the transient-exception set so
incomplete chunked reads on streamed responses trigger a
fallback instead of cancelling the run (#1694 / c9f6dd86).
- Rewrite fallback to alternate primary/fallback with exponential
backoff instead of a single failover, so the agent survives
multi-minute gateway outages spanning both providers (#1695 /
c9a9a7cd).
- Default backoff schedule (0, 5, 15, 30, 45) reaches past the
gateway's ~30s recovery window; jittered ±25%.
- On exhaustion, surface a terminal AIMessage explaining the
outage instead of crashing — progress is checkpointed so the
user can retrigger to continue.
- Preserve fork conventions: Bedrock ClientError retryability
check, sync wrap_model_call (using time.sleep instead of
asyncio.sleep), and existing access-error surfacing for
Anthropic, OpenAI, and Bedrock (botocore) provider errors.
- Update triage ledger (c9f6dd86, c9a9a7cd → landed) and
re-render triage.md.
Refs: #139
* fix: align workflow-push-guard tests with dev's transient-elevation impl
The dev merge auto-combined dev's elevation tests with the stale passthrough
tests inherited from the durable-dispatch branch; the passthrough tests
contradict dev's restored _run_with_workflow_token impl. Take dev's test file.
* fix: drop dead ttl_cache module; make fallback backoff jitter two-sided
ttl_cache.py was re-introduced via the dev merge but dev/#160 deliberately
removed it as dead code (no agent importer). Remove it to match dev.
Also make _jittered_delay symmetric (±25%) to match its docstring.
* chore(upstream-sync): triage 4 new upstream commits (#1708-#1713)
Synced ledger to upstream/main (71e3b818). New rows all deferred:
- #1708 add GPT-5.6 OpenAI models (FLAG-HUMAN: fork picker is Bedrock/Fireworks-only)
- #1709 stale admin model defaults after upgrades
- #1710 bump langchain-fireworks 1.4.4
- #1713 align reviewer eval with published findings
---------
Co-authored-by: amoussa1229 <166072409+amoussa1229@users.noreply.github.com>
Co-authored-by: Adam Moussa <adam@seahavenind.com>
2026-07-09 18:28:21 -04:00
| `27b0ddeb` | #1708 | feat: add GPT-5.6 OpenAI models (#1708 ) | Deferred | FLAG-HUMAN: adds OpenAI GPT-5.6 to the model picker; fork's picker is Bedrock/Fireworks-only — needs a product decision before adopting OpenAI models. Gateway (#155 ) can route OpenAI if adopted. | model-picker |
| `62e0ca2d` | #1709 | fix: stale admin model defaults after model upgrades (#1709 ) | Deferred | stale admin model-default cleanup in team_settings after model upgrades; applies to fork's default-model resolution. | model-picker |
| `138ab9ec` | #1710 | fix: bump langchain-fireworks to 1.4.4 (#1710 ) | Deferred | langchain-fireworks 1.4.4 bump; fork uses Fireworks as a primary provider — adopt with a lockfile refresh. | deps |
| `71e3b818` | #1713 | fix: align reviewer eval with published findings (#1713 ) | Deferred | reviewer-eval/judge alignment; touches reviewer.py + add_finding/publish_review which are fork-diverged — reconcile against fork's reviewer before porting. | reviewer-eval |
2026-07-10 12:31:32 -04:00
| `35659177` | #1718 | fix: sanitize orphaned OpenAI tool results (#1718 ) | Deferred | Correctness fix for orphaned OpenAI tool results before Responses API calls. Fork already wires SanitizeOpenAIResponsesMiddleware and uses OpenAI, so relevant - adopt, but the middleware file and pyproject conflict (fork copy diverged from an earlier pick); hand-resolve and refresh uv.lock. | openai-sanitize |
| `092abafa` | #1717 | fix: enforce terse Slack tool messages (#1717 ) | Deferred | Terse Slack tool-message UX fix. Impl (prompt.py + slack_thread_reply.py) auto-merges; only tests/test_github_comment_prompts.py conflicts against the fork prompt customizations - adopt and resolve that one test. | slack-terse |
| `92d63170` | #1720 | fix: separate review access from automatic reviews (#1720 ) | Deferred | Separates review access from automatic reviews; touches fork-diverged webapp.py + webhooks/github.py auto-review flow + review UI. Cherry-picks clean textually but is an access-control change on the fork-customized opened/ready_for_review auto-review surface - re-inspect semantics and get human sign-off before picking. | reviewer-access |
2026-07-11 10:35:55 -04:00
| `8356eb34` | #1726 | refactor: organize repository by domain (#1726 ) | Untriaged | | |
| `83abea26` | #1724 | fix: accept natural-language Slack plan approvals (#1724 ) | Untriaged | | |
| `129ddcf9` | #1728 | chore: include ripgrep in sandbox image (#1728 ) | Untriaged | | |
| `ddbe457b` | #1727 | fix: restore GPT-5.5 as default model (#1727 ) | Untriaged | | |
| `1ea03a43` | #1729 | feat: include Cargo in sandbox image (#1729 ) | Untriaged | | |
| `5136079d` | #1725 | chore: disable todos for GPT-5.6 Sol (#1725 ) | Untriaged | | |
| `09eaf94c` | #1730 | fix: let admins interrupt runaway agents (#1730 ) | Untriaged | | |
| `30832d29` | #1731 | fix: preserve OpenAI Responses tool history (#1731 ) | Untriaged | | |
2026-07-03 11:46:00 -04:00
_Maintenance: after a `git sync` , add new `dev..upstream/main` SHAs as **Untriaged** (edit `triage.jsonl` ) and bump "Last synced". A successful `git cherry-pick -x` auto-moves the row to **Landed** via the `post-commit` journal + `make triage-reconcile` ._
