Add blueprint generation CLI#378
Merged
Merged
Conversation
📝 WalkthroughWalkthroughA new ChangesBlueprint Generation CLI Feature
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
tests/test_cli_synthetic.py (1)
93-122: ⚡ Quick winAssert the full CLI-to-request mapping here.
This test only locks down the two model names. The new command also maps providers, temperatures, domains, settings, and
--no-grounding, so a wiring regression in those flags would still pass.Possible test expansion
[ "generate-blueprints", "Generate anticoagulation decision cases.", "--count", "1", + "--domain", + "cardiovascular", + "--setting", + "outpatient", "--planner-provider", "openrouter", "--planner-model", "planner-model", + "--planner-temperature", + "0.25", "--blueprint-provider", "openrouter", "--blueprint-model", "blueprint-model", + "--blueprint-temperature", + "0.4", + "--no-grounding", ], ) @@ assert captured[0][0].target_count == 1 + assert captured[0][0].domains == ["cardiovascular"] + assert captured[0][0].settings == ["outpatient"] + assert captured[0][0].required_grounding is False + assert captured[0][0].policy_for(GenerationRole.PLANNER).provider == "openrouter" assert captured[0][0].policy_for(GenerationRole.PLANNER).model == "planner-model" + assert captured[0][0].policy_for(GenerationRole.PLANNER).temperature == 0.25 assert ( + captured[0][0].policy_for(GenerationRole.BLUEPRINT_GENERATOR).provider + == "openrouter" + ) + assert ( captured[0][0].policy_for(GenerationRole.BLUEPRINT_GENERATOR).model == "blueprint-model" ) + assert ( + captured[0][0].policy_for(GenerationRole.BLUEPRINT_GENERATOR).temperature + == 0.4 + )🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tests/test_cli_synthetic.py` around lines 93 - 122, The test currently only asserts planner/blueprint model names; extend the assertions on the captured request (captured[0][0]) to verify the full CLI->request mapping: assert planner provider and blueprint provider values, any temperature fields for planner and blueprint, the domain/intent flag, any settings dict or options passed, and that the no-grounding flag maps to the request.no_grounding (or equivalent) boolean; keep the existing checks for target_count, policy_for(GenerationRole.PLANNER).model and policy_for(GenerationRole.BLUEPRINT_GENERATOR).model and the DatasetStore type to ensure complete coverage of the new flags and wiring.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/casecrawler/cli.py`:
- Around line 967-998: Move the construction of the BlueprintGenerationRequest
into the try/except block so any validation errors raised while building the
request are caught and converted to a click.ClickException; specifically, wrap
the instantiation of BlueprintGenerationRequest (the req variable) together with
DatasetStore() creation and the call to
blueprint_pipeline_module.BlueprintPipeline().generate(...) inside the existing
try, and leave the except ValueError as exc: raise
click.ClickException(str(exc)) from exc to preserve user-facing CLI error
handling.
---
Nitpick comments:
In `@tests/test_cli_synthetic.py`:
- Around line 93-122: The test currently only asserts planner/blueprint model
names; extend the assertions on the captured request (captured[0][0]) to verify
the full CLI->request mapping: assert planner provider and blueprint provider
values, any temperature fields for planner and blueprint, the domain/intent
flag, any settings dict or options passed, and that the no-grounding flag maps
to the request.no_grounding (or equivalent) boolean; keep the existing checks
for target_count, policy_for(GenerationRole.PLANNER).model and
policy_for(GenerationRole.BLUEPRINT_GENERATOR).model and the DatasetStore type
to ensure complete coverage of the new flags and wiring.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: ace66915-098e-469c-b58b-74f7ad6cf847
📒 Files selected for processing (2)
src/casecrawler/cli.pytests/test_cli_synthetic.py
Comment on lines
+967
to
+998
| req = BlueprintGenerationRequest( | ||
| request=request_text, | ||
| target_count=count, | ||
| domains=list(domains), | ||
| settings=list(settings), | ||
| required_grounding=not no_grounding, | ||
| role_policies=[ | ||
| GenerationRolePolicy( | ||
| role=GenerationRole.PLANNER, | ||
| provider=planner_provider, | ||
| model=planner_model, | ||
| temperature=planner_temperature, | ||
| ), | ||
| GenerationRolePolicy( | ||
| role=GenerationRole.BLUEPRINT_GENERATOR, | ||
| provider=blueprint_provider, | ||
| model=blueprint_model, | ||
| temperature=blueprint_temperature, | ||
| ), | ||
| ], | ||
| ) | ||
| try: | ||
| store = DatasetStore() | ||
| result = asyncio.run( | ||
| blueprint_pipeline_module.BlueprintPipeline().generate( | ||
| req, | ||
| dataset_id=resolved_dataset_id, | ||
| store=store, | ||
| ) | ||
| ) | ||
| except ValueError as exc: | ||
| raise click.ClickException(str(exc)) from exc |
There was a problem hiding this comment.
Wrap request validation in the ClickException boundary.
Lines 967-987 build BlueprintGenerationRequest before the try, so any model-validation failure there escapes as a raw exception instead of the user-facing CLI error this command uses for the pipeline call.
Proposed fix
- resolved_dataset_id = dataset_id or f"blueprint-ds-{uuid4()}"
- req = BlueprintGenerationRequest(
- request=request_text,
- target_count=count,
- domains=list(domains),
- settings=list(settings),
- required_grounding=not no_grounding,
- role_policies=[
- GenerationRolePolicy(
- role=GenerationRole.PLANNER,
- provider=planner_provider,
- model=planner_model,
- temperature=planner_temperature,
- ),
- GenerationRolePolicy(
- role=GenerationRole.BLUEPRINT_GENERATOR,
- provider=blueprint_provider,
- model=blueprint_model,
- temperature=blueprint_temperature,
- ),
- ],
- )
+ resolved_dataset_id = dataset_id or f"blueprint-ds-{uuid4()}"
try:
+ req = BlueprintGenerationRequest(
+ request=request_text,
+ target_count=count,
+ domains=list(domains),
+ settings=list(settings),
+ required_grounding=not no_grounding,
+ role_policies=[
+ GenerationRolePolicy(
+ role=GenerationRole.PLANNER,
+ provider=planner_provider,
+ model=planner_model,
+ temperature=planner_temperature,
+ ),
+ GenerationRolePolicy(
+ role=GenerationRole.BLUEPRINT_GENERATOR,
+ provider=blueprint_provider,
+ model=blueprint_model,
+ temperature=blueprint_temperature,
+ ),
+ ],
+ )
store = DatasetStore()
result = asyncio.run(
blueprint_pipeline_module.BlueprintPipeline().generate(📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| req = BlueprintGenerationRequest( | |
| request=request_text, | |
| target_count=count, | |
| domains=list(domains), | |
| settings=list(settings), | |
| required_grounding=not no_grounding, | |
| role_policies=[ | |
| GenerationRolePolicy( | |
| role=GenerationRole.PLANNER, | |
| provider=planner_provider, | |
| model=planner_model, | |
| temperature=planner_temperature, | |
| ), | |
| GenerationRolePolicy( | |
| role=GenerationRole.BLUEPRINT_GENERATOR, | |
| provider=blueprint_provider, | |
| model=blueprint_model, | |
| temperature=blueprint_temperature, | |
| ), | |
| ], | |
| ) | |
| try: | |
| store = DatasetStore() | |
| result = asyncio.run( | |
| blueprint_pipeline_module.BlueprintPipeline().generate( | |
| req, | |
| dataset_id=resolved_dataset_id, | |
| store=store, | |
| ) | |
| ) | |
| except ValueError as exc: | |
| raise click.ClickException(str(exc)) from exc | |
| try: | |
| req = BlueprintGenerationRequest( | |
| request=request_text, | |
| target_count=count, | |
| domains=list(domains), | |
| settings=list(settings), | |
| required_grounding=not no_grounding, | |
| role_policies=[ | |
| GenerationRolePolicy( | |
| role=GenerationRole.PLANNER, | |
| provider=planner_provider, | |
| model=planner_model, | |
| temperature=planner_temperature, | |
| ), | |
| GenerationRolePolicy( | |
| role=GenerationRole.BLUEPRINT_GENERATOR, | |
| provider=blueprint_provider, | |
| model=blueprint_model, | |
| temperature=blueprint_temperature, | |
| ), | |
| ], | |
| ) | |
| store = DatasetStore() | |
| result = asyncio.run( | |
| blueprint_pipeline_module.BlueprintPipeline().generate( | |
| req, | |
| dataset_id=resolved_dataset_id, | |
| store=store, | |
| ) | |
| ) | |
| except ValueError as exc: | |
| raise click.ClickException(str(exc)) from exc |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In `@src/casecrawler/cli.py` around lines 967 - 998, Move the construction of the
BlueprintGenerationRequest into the try/except block so any validation errors
raised while building the request are caught and converted to a
click.ClickException; specifically, wrap the instantiation of
BlueprintGenerationRequest (the req variable) together with DatasetStore()
creation and the call to
blueprint_pipeline_module.BlueprintPipeline().generate(...) inside the existing
try, and leave the except ValueError as exc: raise
click.ClickException(str(exc)) from exc to preserve user-facing CLI error
handling.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
casecrawler generate-blueprintsfor model-driven BlueprintGenerationRequest workflowsTests
Summary by CodeRabbit
generate-blueprintsCLI command to generate clinical blueprints with customizable parameters including request text, generation count, dataset persistence, domains, settings, model providers/models/temperatures, and optional grounding control.