Feat/youtube transcripts UI#26
Merged
Merged
Conversation
|
Warning Review limit reached
More reviews will be available in 49 minutes and 53 seconds. Learn how PR review limits work. Your organization has run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After more reviews become available, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available. Please see our Fair Usage Limits Policy for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (2)
WalkthroughThis PR adds comprehensive project documentation (README), detailed planning for a new Deep Search Agent feature (PHASE 11 in implementationPlan.MD), and a minor formatting adjustment to a frontend API helper function. The changes are primarily documentation and planning with no implementation code. ChangesProject Documentation
Deep Search Agent Feature Plan
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 3 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. 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: 5
🤖 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 `@implementationPlan.MD`:
- Around line 617-621: The memory text format for Deep Search should include a
source tag like YouTube does; update the embedding text in the save_deep_search
flow to use a prefixed format so memory entries are filterable by source.
Specifically, change where service.save_deep_search builds the memory text
(currently f"{query}\n\n{summary}") to use a tagged pattern such as "[Deep
Search] {query}: {summary}" before creating memory_entries and storing the
returned memory_entry_id; ensure any tests or consumers expecting the old string
are adjusted accordingly.
- Around line 632-642: Add explicit LLM synthesis error handling inside
deepsearch_agent_node: wrap the OpenRouter/LLM call (using
settings.deepsearch_model) in a try/except that catches timeouts,
rate-limit/errors from the client, and malformed/parseable responses (including
JSON decode errors), apply an optional retry/backoff if appropriate, and on
persistent failure return a descriptive ToolMessage that explains the problem
without exposing raw exception traces; continue to validate the LLM output with
DeepSearchPayload and if validation fails fall back to the raw concatenation
strategy described (instead of crashing), and ensure any internal exceptions are
logged internally but not leaked to the returned ToolMessage.
- Around line 617-630: The save_deep_search flow currently inserts into
deep_searches then calls the embedding + inserts into memory_entries and updates
deep_searches.memory_entry_id; decide and implement one consistent strategy:
either wrap the multi-step work in a DB transaction so any failure in embedding
or memory_entries insertion rolls back the initial deep_searches INSERT, or
adopt the resilient YouTube pattern (preferred) where embedding/memory
cross-indexing failures are non-fatal—log the error with context (include
deep_search id, query, and the exception), leave the deep_searchs row committed
with memory_entry_id NULL, and continue; likewise, in update_deep_search when
summary changes, if memory_entry_id is NULL attempt to create a new memory entry
(and set memory_entry_id), and if that fails log and keep the deep_search
updated without a memory_entry_id; ensure all log messages reference
save_deep_search and update_deep_search and include the memory_entries and
memory_entry_id context so the failure is visible for debugging.
- Around line 598-609: The frontend enforces title <=200 and summary <=10,000
but the backend schemas lack these limits; update the Pydantic models in
schemas.py (e.g., the DeepSearchCreate/DeepSearchUpdate or equivalent model used
for deep search input) to declare title: str = Field(..., max_length=200) and
summary: str = Field(..., max_length=10000) and/or add `@validator` methods to
enforce/strip length and raise ValidationError, ensuring the service layer uses
those schemas for create/update requests so direct API calls cannot bypass the
limits.
In `@README.md`:
- Line 191: Update the README table row that references `/api/v1/youtube` to
capitalize the service name "YouTube" in the Notes/description column (e.g.,
change "Saved video transcripts" to "Saved YouTube video transcripts" or
otherwise replace any lowercase "youtube" with "YouTube") so the endpoint
reference is consistent with the existing "YouTube agent" phrasing.
🪄 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: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: 721d1dc8-b193-48ca-8fe1-af3f0576de56
📒 Files selected for processing (3)
README.mdfrontend/lib/api.tsimplementationPlan.MD
- README: capitalize 'YouTube' in /api/v1/youtube endpoint description - Plan: update deep search memory text to tagged format '[Deep Search] query: summary' - Plan: add Pydantic field length limits (title <=200, summary <=10000) to DeepSearchCreate/Patch schemas - Plan: adopt resilient non-fatal save strategy (YouTube pattern) for memory cross-indexing failures - Plan: expand deepsearch_agent_node error handling to cover LLM timeouts, rate-limits, JSONDecodeError, and log-without-leak rule
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 by CodeRabbit
Documentation
Style