open-swe/agent/middleware
Adam Moussa 179867d120
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.
2026-07-09 15:40:58 -04:00
..
__init__.py feat: port LangSmith LLM Gateway routing from upstream (#1671, #1673, #1674, #1678) (#155) 2026-07-09 14:44:15 -04:00
check_message_queue.py chore: sync upstream/main, defer #1621 modular webhooks (#81) 2026-06-30 16:45:19 -04:00
ensure_no_empty_msg.py chore: sync upstream/main, defer #1621 modular webhooks (#81) 2026-06-30 16:45:19 -04:00
exclude_tools.py feat: add reviewer graph + eval target wiring (#1241) 2026-05-06 10:15:58 -07:00
model_fallback.py feat: migrate model providers to Bedrock (Claude) + Fireworks (everything else) (#62) 2026-06-29 15:57:19 -04:00
notify_step_limit.py fix: notify users via Slack when agent hits model call step limit (#1204) 2026-05-01 14:24:25 -07:00
plan_mode.py chore: sync upstream/main, defer #1621 modular webhooks (#81) 2026-06-30 16:45:19 -04:00
refresh_github_proxy.py fix: refresh sandbox GitHub proxy token before mid-run expiry (#1496) 2026-06-11 10:59:21 -07:00
refresh_slack_status.py feat: add Slack reaction tool (#1650) 2026-07-03 15:38:56 -04:00
repair_orphaned_tool_calls.py fix: repair orphaned tool calls before model calls (#1604) 2026-06-24 12:58:10 -07:00
sandbox_circuit_breaker.py fix: recover from mid-run sandbox death (#1274) 2026-05-08 12:55:36 -07:00
sanitize_fireworks_messages.py feat: port LangSmith LLM Gateway routing from upstream (#1671, #1673, #1674, #1678) (#155) 2026-07-09 14:44:15 -04:00
sanitize_openai_responses.py feat: port LangSmith LLM Gateway routing from upstream (#1671, #1673, #1674, #1678) (#155) 2026-07-09 14:44:15 -04:00
sanitize_thinking_blocks.py feat: migrate model providers to Bedrock (Claude) + Fireworks (everything else) (#62) 2026-06-29 15:57:19 -04:00
sanitize_tool_inputs.py fix: coerce malformed integer strings in read_file offset/limit params (#1216) 2026-05-01 14:29:48 -07:00
settle_review_check.py fix: settle incomplete review check as neutral, not failure (#1501) 2026-06-11 13:03:34 -07:00
subdir_agents.py feat: re-land scoped AGENTS auto-load (#1684) + platform issue reporting tool (#1685) (#129) 2026-07-08 18:52:01 -04:00
tool_artifact.py feat(open-swe): stream agent chat via @langchain/react v2 protocol (#1475) 2026-06-11 09:54:35 -07:00
tool_error_handler.py fix: keep sandbox backend stable across recovery (#1294)w 2026-05-11 16:03:38 -07:00
workflow_push_guard.py fix: restore transient workflow-token elevation (revert standing workflows:write) 2026-07-09 15:40:58 -04:00