Commit graph

4 commits

Author SHA1 Message Date
7b26ab9516
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.)
2026-06-29 15:34:06 -04:00
1c93e5c62b
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
2026-06-29 14:57:14 -04:00
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>
2026-06-11 09:54:35 -07:00
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.
2026-05-08 15:35:13 -07:00