mirror of
https://github.com/Sea-Haven-Industries/open-swe.git
synced 2026-09-30 19:43:15 +00:00
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: 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.
73 lines
1.7 KiB
TOML
73 lines
1.7 KiB
TOML
[project]
|
|
name = "open-swe-agent"
|
|
version = "0.1.0"
|
|
description = "Open SWE Agent - Python agent for automating software engineering tasks"
|
|
readme = "README.md"
|
|
requires-python = ">=3.11"
|
|
license = { text = "MIT" }
|
|
dependencies = [
|
|
"deepagents==0.6.8",
|
|
"fastapi>=0.136.3",
|
|
"uvicorn>=0.48.0",
|
|
"httpx>=0.28.1",
|
|
"PyJWT>=2.13.0",
|
|
"cryptography>=48.0.1",
|
|
"langgraph-sdk>=0.4.2",
|
|
"langchain>=1.3.9",
|
|
"langgraph>=1.1.10",
|
|
"markdownify>=1.2.2",
|
|
"langchain-anthropic>=1.4.6",
|
|
"langchain-aws>=0.2.0",
|
|
"langgraph-cli[inmem]>=0.4.30",
|
|
"langsmith==0.8.18",
|
|
"langchain-openai>=1.2.2",
|
|
"langchain-fireworks>=1.4.2",
|
|
# langchain-fireworks 1.4.2 pins a pre-release fireworks-ai; opt in explicitly so uv resolves it.
|
|
"fireworks-ai>=1.2.0a71",
|
|
"langchain-daytona>=0.0.5",
|
|
"langchain-modal>=0.0.3",
|
|
"langchain-runloop>=0.0.4",
|
|
"exa-py>=2.13.0",
|
|
"langchain-google-genai>=4.2.4",
|
|
"langchain-mcp-adapters>=0.2.2",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=9.0.3",
|
|
"pytest-asyncio>=1.4.0",
|
|
"ruff>=0.15.15",
|
|
"Pygments>=2.20.0",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.metadata]
|
|
allow-direct-references = true
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["agent"]
|
|
|
|
[tool.ruff]
|
|
line-length = 100
|
|
target-version = "py311"
|
|
|
|
[tool.ruff.lint]
|
|
select = [
|
|
"E", # pycodestyle errors
|
|
"W", # pycodestyle warnings
|
|
"F", # Pyflakes
|
|
"I", # isort
|
|
"B", # flake8-bugbear
|
|
"C4", # flake8-comprehensions
|
|
"UP", # pyupgrade
|
|
]
|
|
ignore = [
|
|
"E501", # line too long (handled by formatter)
|
|
]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
testpaths = ["tests"]
|