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>		2026-06-24 12:58:10 -07:00
..
dashboard	feat: inline PR comments in the reviews UI (#1600)	2026-06-23 16:01:46 -07:00
integrations	feat: repo-scoped dynamic sandbox snapshots (#1595)	2026-06-23 12:24:11 -07:00
middleware	fix: repair orphaned tool calls before model calls (#1604)	2026-06-24 12:58:10 -07:00
skills	feat: outcomes dataset + bootstrap/continual split via skills (#1365)	2026-06-01 13:25:12 -07:00
tools	feat: plan mode with model-driven entry and collaborative review (#1580)	2026-06-23 12:06:58 -07:00
utils	perf: cut review-chat time-to-first-token (#1598)	2026-06-23 12:32:10 -07:00
analyzer.py	feat: route graphs to separate LangSmith tracing projects (#1508)	2026-06-11 17:57:16 -07:00
chat.py	feat: chat with your PR on the review page (#1534)	2026-06-15 17:17:30 -07:00
ci_autofix.py	feat: activate PR babysitting UI toggles for autofix and trigger mode (#1561)	2026-06-17 14:12:04 -07:00
ci_monitor.py	feat: CI auto-fix and PR babysitting for agent PRs (#1530)	2026-06-15 13:53:50 -07:00
encryption.py	feat: support TOKEN_ENCRYPTION_KEY rotation via MultiFernet [closes AB-2323] (#1275)	2026-05-08 14:29:23 -07:00
prompt.py	feat: plan mode with model-driven entry and collaborative review (#1580)	2026-06-23 12:06:58 -07:00
review_style_collector.py	feat: PR review page (#1495)	2026-06-11 16:11:10 -07:00
review_style_guidance.py	feat: tune reviewer for precision — web/wiki tools + recalibrated prompt (#1312)	2026-05-20 18:35:00 +00:00
reviewer.py	fix: repair orphaned tool calls before model calls (#1604)	2026-06-24 12:58:10 -07:00
reviewer_diff.py	fix: reviewer reviews full diff; fix review UI scroll + dark-mode composer (#1575)	2026-06-18 19:24:52 -07:00
reviewer_eval_store.py	feat: Run reviewer eval in a GitHub Action; dashboard becomes read-only (#1556)	2026-06-16 19:38:36 -07:00
reviewer_findings.py	fix: Reviews tab — anchored finding card, paginated list, file tree truncation (#1507)	2026-06-11 17:52:20 -07:00
reviewer_groups.py	fix: Simplify review explanation: full-width, plain prose, no diff links (#1547)	2026-06-16 15:32:24 -07:00
reviewer_publish.py	feat: surface sub-threshold findings in review summary with web app link (#1571)	2026-06-18 11:15:42 -07:00
reviewer_reconcile.py	feat: let reviewer set comment titles (#1356)	2026-05-28 16:04:38 -07:00
scheduler.py	feat: add scheduled web agents (#1422)	2026-06-05 02:20:24 +00:00
server.py	fix: repair orphaned tool calls before model calls (#1604)	2026-06-24 12:58:10 -07:00
webapp.py	refactor(open-swe): plain HTTP comments instead of Yjs/BlockNote collab (#1601)	2026-06-23 22:12:42 +00:00