open-swe/tests/test_sanitize_thinking_blocks.py
Adam Moussa a4ed19ba61
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: migrate model providers to Bedrock (Claude) + Fireworks (everything else) (#62)
* 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.
2026-06-29 15:57:19 -04:00

103 lines
3.9 KiB
Python

from __future__ import annotations
from unittest.mock import MagicMock
import pytest
from langchain_anthropic import ChatAnthropic
from langchain_aws import ChatBedrockConverse
from langchain_core.messages import AIMessage, HumanMessage
from agent.middleware.sanitize_thinking_blocks import SanitizeThinkingBlocksMiddleware
def _make_request(messages: list[object], model: object | None = None) -> MagicMock:
request = MagicMock()
request.model = model or MagicMock(spec=ChatAnthropic)
request.messages = messages
return request
class TestSanitizeThinkingBlocksMiddleware:
def test_drops_empty_thinking_block_for_anthropic(self) -> None:
message = AIMessage(
content=[
{"type": "thinking", "signature": "abc", "thinking": ""},
{"type": "text", "text": "ok"},
]
)
request = _make_request([message])
response = MagicMock()
def handler(req: object) -> object:
assert req is request
return response
result = SanitizeThinkingBlocksMiddleware().wrap_model_call(request, handler)
assert result is response
assert message.content == [{"type": "text", "text": "ok"}]
def test_preserves_non_empty_thinking_block_for_anthropic(self) -> None:
thinking_block = {"type": "thinking", "signature": "abc", "thinking": "reasoning"}
text_block = {"type": "text", "text": "ok"}
message = AIMessage(content=[thinking_block, text_block])
request = _make_request([message])
SanitizeThinkingBlocksMiddleware().wrap_model_call(request, lambda req: MagicMock())
assert message.content == [thinking_block, text_block]
@pytest.mark.asyncio
async def test_async_drops_missing_thinking_block_for_anthropic(self) -> None:
message = AIMessage(
content=[
{"type": "thinking", "signature": "abc"},
{"type": "text", "text": "ok"},
]
)
request = _make_request([HumanMessage(content="hi"), message])
response = MagicMock()
async def handler(req: object) -> object:
assert req is request
return response
result = await SanitizeThinkingBlocksMiddleware().awrap_model_call(request, handler)
assert result is response
assert message.content == [{"type": "text", "text": "ok"}]
def test_drops_empty_reasoning_content_block_for_bedrock(self) -> None:
message = AIMessage(
content=[
{"type": "reasoning_content", "reasoning_content": {"text": "", "signature": ""}},
{"type": "text", "text": "ok"},
]
)
request = _make_request([message], model=MagicMock(spec=ChatBedrockConverse))
SanitizeThinkingBlocksMiddleware().wrap_model_call(request, lambda req: MagicMock())
assert message.content == [{"type": "text", "text": "ok"}]
def test_preserves_non_empty_reasoning_content_block_for_bedrock(self) -> None:
reasoning_block = {
"type": "reasoning_content",
"reasoning_content": {"text": "because", "signature": "sig"},
}
text_block = {"type": "text", "text": "ok"}
message = AIMessage(content=[reasoning_block, text_block])
request = _make_request([message], model=MagicMock(spec=ChatBedrockConverse))
SanitizeThinkingBlocksMiddleware().wrap_model_call(request, lambda req: MagicMock())
assert message.content == [reasoning_block, text_block]
def test_ignores_non_anthropic_models(self) -> None:
thinking_block = {"type": "thinking", "signature": "abc", "thinking": ""}
message = AIMessage(content=[thinking_block, {"type": "text", "text": "ok"}])
request = _make_request([message], model=MagicMock())
SanitizeThinkingBlocksMiddleware().wrap_model_call(request, lambda req: MagicMock())
assert message.content == [thinking_block, {"type": "text", "text": "ok"}]