open-swe/tests/test_team_settings_org_guidelines.py

118 lines
3.7 KiB
Python
Raw Normal View History

from __future__ import annotations
from unittest.mock import AsyncMock, patch
import pytest
from pydantic import ValidationError
from agent.dashboard.team_settings import (
ORG_GUIDELINES_MAX_CHARS,
TeamSettingsUpdate,
get_org_review_guidelines,
feat: chat with your PR on the review page (#1534) * feat: chat with your PR on the review page Add a sandbox-less `chat` graph that answers questions about a single PR from its diff, the published review findings, and read-only GitHub access. - agent/chat.py: deepagents graph, no sandbox (default StateBackend, file mutation + execute tools excluded). PR context is seeded as virtual files under /pr/; a repo-scoped App token is resolved in-graph. - tools: read_repo_file, search_repo_code, list_review_findings. - dashboard/review_chat_api.py + routes: per-user chat thread, LangGraph stream/commands/state/history proxy pinned to the chat assistant, seeds diff/findings/overview on first run. Gated by repo access. - UI: Chat tab wired to a chat-scoped StreamProvider (replaces Coming Soon). * feat: admin setting for review-chat default model Add a 'Open SWE Review Chat' default to team settings (default_chat_model / default_chat_reasoning_effort). get_team_default_model("chat") inherits the Agent default when unset; the chat graph resolves through it. Admin RolePicker gains an 'Agent default' inherit option that clears the override. * feat: multi-conversation review chat (tabs, new chat, history) Replace the single per-PR chat thread with multiple per-user conversations: - threads minted client-side; first message persists with a title derived from the prompt. - list + delete endpoints; chat panel gets a tab strip (history), new-chat (+), close (x), refresh, an intro greeting, and suggested prompts. - get_review_chat now returns availability only (ids are client-minted). * ui fixes * ui: review-chat history dropdown, full-width AI replies, resizable side panel * fix(review-chat): enforce per-user thread ownership on proxy endpoints; reseed PR context on head change --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-15 17:17:30 -07:00
get_team_default_model,
)
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
_AGENT_PAIR = ("bedrock_converse:us.anthropic.claude-opus-4-8", "high")
_CHAT_PAIR = ("fireworks:accounts/fireworks/models/kimi-k2p7-code", "low")
feat: chat with your PR on the review page (#1534) * feat: chat with your PR on the review page Add a sandbox-less `chat` graph that answers questions about a single PR from its diff, the published review findings, and read-only GitHub access. - agent/chat.py: deepagents graph, no sandbox (default StateBackend, file mutation + execute tools excluded). PR context is seeded as virtual files under /pr/; a repo-scoped App token is resolved in-graph. - tools: read_repo_file, search_repo_code, list_review_findings. - dashboard/review_chat_api.py + routes: per-user chat thread, LangGraph stream/commands/state/history proxy pinned to the chat assistant, seeds diff/findings/overview on first run. Gated by repo access. - UI: Chat tab wired to a chat-scoped StreamProvider (replaces Coming Soon). * feat: admin setting for review-chat default model Add a 'Open SWE Review Chat' default to team settings (default_chat_model / default_chat_reasoning_effort). get_team_default_model("chat") inherits the Agent default when unset; the chat graph resolves through it. Admin RolePicker gains an 'Agent default' inherit option that clears the override. * feat: multi-conversation review chat (tabs, new chat, history) Replace the single per-PR chat thread with multiple per-user conversations: - threads minted client-side; first message persists with a title derived from the prompt. - list + delete endpoints; chat panel gets a tab strip (history), new-chat (+), close (x), refresh, an intro greeting, and suggested prompts. - get_review_chat now returns availability only (ids are client-minted). * ui fixes * ui: review-chat history dropdown, full-width AI replies, resizable side panel * fix(review-chat): enforce per-user thread ownership on proxy endpoints; reseed PR context on head change --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-15 17:17:30 -07:00
def test_org_guidelines_blank_normalizes_to_none() -> None:
assert TeamSettingsUpdate(org_guidelines=" ").org_guidelines is None
assert TeamSettingsUpdate(org_guidelines=None).org_guidelines is None
def test_org_guidelines_trimmed() -> None:
update = TeamSettingsUpdate(org_guidelines=" Flag CI gate removals.\n")
assert update.org_guidelines == "Flag CI gate removals."
def test_org_guidelines_rejects_oversized() -> None:
with pytest.raises(ValidationError):
TeamSettingsUpdate(org_guidelines="x" * (ORG_GUIDELINES_MAX_CHARS + 1))
@pytest.mark.asyncio
async def test_get_org_review_guidelines_returns_trimmed_text() -> None:
with patch(
"agent.dashboard.team_settings.get_team_settings",
new_callable=AsyncMock,
return_value={"org_guidelines": " Always check auth.\n"},
):
assert await get_org_review_guidelines() == "Always check auth."
@pytest.mark.asyncio
async def test_get_org_review_guidelines_returns_none_when_unset() -> None:
with patch(
"agent.dashboard.team_settings.get_team_settings",
new_callable=AsyncMock,
return_value={"org_guidelines": None},
):
assert await get_org_review_guidelines() is None
feat: chat with your PR on the review page (#1534) * feat: chat with your PR on the review page Add a sandbox-less `chat` graph that answers questions about a single PR from its diff, the published review findings, and read-only GitHub access. - agent/chat.py: deepagents graph, no sandbox (default StateBackend, file mutation + execute tools excluded). PR context is seeded as virtual files under /pr/; a repo-scoped App token is resolved in-graph. - tools: read_repo_file, search_repo_code, list_review_findings. - dashboard/review_chat_api.py + routes: per-user chat thread, LangGraph stream/commands/state/history proxy pinned to the chat assistant, seeds diff/findings/overview on first run. Gated by repo access. - UI: Chat tab wired to a chat-scoped StreamProvider (replaces Coming Soon). * feat: admin setting for review-chat default model Add a 'Open SWE Review Chat' default to team settings (default_chat_model / default_chat_reasoning_effort). get_team_default_model("chat") inherits the Agent default when unset; the chat graph resolves through it. Admin RolePicker gains an 'Agent default' inherit option that clears the override. * feat: multi-conversation review chat (tabs, new chat, history) Replace the single per-PR chat thread with multiple per-user conversations: - threads minted client-side; first message persists with a title derived from the prompt. - list + delete endpoints; chat panel gets a tab strip (history), new-chat (+), close (x), refresh, an intro greeting, and suggested prompts. - get_review_chat now returns availability only (ids are client-minted). * ui fixes * ui: review-chat history dropdown, full-width AI replies, resizable side panel * fix(review-chat): enforce per-user thread ownership on proxy endpoints; reseed PR context on head change --------- Co-authored-by: open-swe[bot] <open-swe@users.noreply.github.com>
2026-06-15 17:17:30 -07:00
def _settings(**overrides: object) -> dict[str, object]:
base = {
"default_agent_model": _AGENT_PAIR[0],
"default_agent_reasoning_effort": _AGENT_PAIR[1],
"default_chat_model": None,
"default_chat_reasoning_effort": None,
}
base.update(overrides)
return base
@pytest.mark.asyncio
async def test_chat_default_inherits_agent_when_unset() -> None:
with patch(
"agent.dashboard.team_settings.get_team_settings",
new_callable=AsyncMock,
return_value=_settings(),
):
assert await get_team_default_model("chat") == _AGENT_PAIR
@pytest.mark.asyncio
async def test_chat_default_uses_chat_model_when_set() -> None:
with patch(
"agent.dashboard.team_settings.get_team_settings",
new_callable=AsyncMock,
return_value=_settings(
default_chat_model=_CHAT_PAIR[0],
default_chat_reasoning_effort=_CHAT_PAIR[1],
),
):
assert await get_team_default_model("chat") == _CHAT_PAIR
@pytest.mark.asyncio
async def test_chat_default_inherits_agent_when_chat_model_invalid() -> None:
with patch(
"agent.dashboard.team_settings.get_team_settings",
new_callable=AsyncMock,
return_value=_settings(
default_chat_model="bogus:model",
default_chat_reasoning_effort="high",
),
):
assert await get_team_default_model("chat") == _AGENT_PAIR
def test_team_settings_update_accepts_chat_pair() -> None:
update = TeamSettingsUpdate(
default_chat_model=_CHAT_PAIR[0],
default_chat_reasoning_effort=_CHAT_PAIR[1],
)
assert update.default_chat_model == _CHAT_PAIR[0]
assert update.default_chat_reasoning_effort == _CHAT_PAIR[1]
def test_team_settings_update_rejects_chat_effort_without_model() -> None:
with pytest.raises(ValidationError):
TeamSettingsUpdate(default_chat_reasoning_effort="high")
def test_team_settings_update_rejects_unsupported_chat_effort() -> None:
with pytest.raises(ValidationError):
TeamSettingsUpdate(default_chat_model=_CHAT_PAIR[0], default_chat_reasoning_effort="max")