Fix hotspots findings groupBy#470
Merged
Merged
Conversation
|
CodeAnt AI is reviewing your PR. |
📝 WalkthroughWalkthroughThis PR enables the ChangesFindings Grouping Support
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)
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 |
codeant-ai
Bot
added
the
size:L
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds support for grouping hotspots by "findings" in the @relayburn/sdk and its Node.js bindings. It updates the HotspotsGroupBy enum in both Rust and TypeScript, handles the new option in the query execution logic, defines default finding kinds, and adds corresponding unit and conformance tests. There are no review comments, and I have no feedback to provide.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
|
CodeAnt AI finished reviewing your PR. |
![cubic-dev-ai[bot]](https://avatars.githubusercontent.com/in/1082092?s=60&v=4){kind=small}
|
CodeAnt AI is running Incremental review |
codeant-ai
Bot
added
size:L
|
CodeAnt AI Incremental review completed. |
![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
🤖 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 `@crates/relayburn-sdk/src/query_verbs.rs`:
- Around line 3177-3183: HotspotsGroupBy::Findings leaks project/provider scope
because run_hotspots_findings builds side_q without q.project/provider filters
and detect_observed_bloat processes all tool_result_events; fix by updating
run_hotspots_findings to include q.project and the provider allow-list from q
(or from the same filter used for turns) when constructing side_q before calling
query_user_turns and query_tool_result_events, and ensure the tool_result_events
returned are either queried with those filters or post-filtered to only events
whose session_id (or other session identifier) is present in the turns slice;
also update detect_observed_bloat to iterate only over tool_result_events that
are intersected with the provided turns (e.g., filter by session_id in turns) so
findings cannot reference sessions outside the caller’s requested
turns/provider/project scope.
🪄 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: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: 78cc2e90-f4ce-4650-afdd-4db1b1363382
📒 Files selected for processing (6)
CHANGELOG.mdcrates/relayburn-sdk-node/src/lib.rscrates/relayburn-sdk/src/query_verbs.rspackages/sdk-node/CHANGELOG.mdpackages/sdk-node/src/index.d.tspackages/sdk-node/test/conformance.test.js
Comment on lines
+3177
to
+3183
| if matches!(opts.group_by, Some(HotspotsGroupBy::Findings)) { | ||
| let patterns = match opts.patterns { | ||
| Some(patterns) if !patterns.is_empty() => patterns, | ||
| _ => default_hotspots_finding_kinds(), | ||
| }; | ||
| return run_hotspots_findings(self, &turns, &pricing, patterns, &q); | ||
| } |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Inspect the new route into the findings pipeline.
rg -n -C4 'run_hotspots_findings|group_by.*Findings|query_user_turns|query_tool_result_events' crates/relayburn-sdk/src/query_verbs.rs
# Inspect whether the tool-output-bloat detector explicitly scopes side data
# back to the passed `turns` / selected session ids.
rg -n -C6 'fn detect_tool_output_bloat|struct DetectToolOutputBloatOptions|tool_result_events|user_turns|turns' crates packages --glob '!**/target/**'Repository: AgentWorkforce/burn
Length of output: 50377
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# Show the full run_hotspots_findings block around where side_q/session_q are built and queries are executed.
sed -n '3400,3560p' crates/relayburn-sdk/src/query_verbs.rs
# Locate and show detect_tool_output_bloat implementation + relevant option struct usage.
fd detect_tool_output_bloat crates/relayburn-sdk -a 2>/dev/null || true
rg -n "fn detect_tool_output_bloat|struct DetectToolOutputBloatOptions|DetectToolOutputBloatOptions" crates/relayburn-sdk/src crates -S --glob '!**/target/**'
# If detect_tool_output_bloat is in another file, print the function body area.
# Try common file targets first; otherwise we rely on next sed once we know the path from rg output.
# (We keep this command robust by grepping the first match path from rg.)
FILE="$(rg -l "fn detect_tool_output_bloat" crates/relayburn-sdk/src crates --glob '!**/target/**' | head -n 1 || true)"
if [ -n "$FILE" ]; then
echo "---- detect_tool_output_bloat in: $FILE ----"
sed -n '1,240p' "$FILE" | head -n 60
# Print around the function definition (roughly)
START="$(rg -n "fn detect_tool_output_bloat" "$FILE" -S --glob '!**/target/**' | head -n 1 | cut -d: -f1)"
if [ -n "$START" ]; then
S=$((START-60)); E=$((START+220));
sed -n "${S},${E}p" "$FILE"
fi
fi
# Also locate LedgerHandle::hotspots scoping logic (project/provider allow-list) and show how it constructs q/session_q.
rg -n "LedgerHandle::hotspots|fn hotspots\\(|HotspotsOptions|project|provider" crates/relayburn-sdk/src/query_verbs.rs crates/relayburn-sdk/src -S --glob '!**/target/**'Repository: AgentWorkforce/burn
Length of output: 10977
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# 1) Inspect how the hotspots entrypoint constructs the Query `q` (provider/project/session scoping).
rg -n "fn hotspots\\(|HotspotsOptions|struct HotspotsOptions|Query \\{" crates/relayburn-sdk/src/query_verbs.rs
HS_LINE="$(rg -n "fn hotspots\\(" crates/relayburn-sdk/src/query_verbs.rs | head -n 1 | cut -d: -f1)"
echo "hotspots fn at line: $HS_LINE"
sed -n "$((HS_LINE-80)),$((HS_LINE+220))p" crates/relayburn-sdk/src/query_verbs.rs
# Narrow to the part where Query q is built (look for `let q = Query {`)
Q_LINE="$(rg -n "let q = Query \\{" crates/relayburn-sdk/src/query_verbs.rs | head -n 1 | cut -d: -f1 || true)"
if [ -n "${Q_LINE:-}" ]; then
echo "q construction at line: $Q_LINE"
sed -n "$((Q_LINE-40)),$((Q_LINE+140))p" crates/relayburn-sdk/src/query_verbs.rs
fi
# 2) Inspect detect_tool_output_bloat implementation for session scoping against passed `turns`.
TOB_FILE="crates/relayburn-sdk/src/analyze/tool_output_bloat.rs"
TOB_LINE="$(rg -n "pub fn detect_tool_output_bloat" "$TOB_FILE" | head -n 1 | cut -d: -f1)"
echo "detect_tool_output_bloat at line: $TOB_LINE"
sed -n "$((TOB_LINE-40)),$((TOB_LINE+260))p" "$TOB_FILE"
# Look for explicit filtering to sessions present in `turns`.
rg -n "session_ids|session_id.*turns|keep|turns.*session_id|in_turns|HashSet" "$TOB_FILE" | head -n 80Repository: AgentWorkforce/burn
Length of output: 30801
🏁 Script executed:
#!/bin/bash
set -euo pipefail
TOB="crates/relayburn-sdk/src/analyze/tool_output_bloat.rs"
# Extract the observed-bloat path where tool_result_events/user_turns/turns are combined and (hopefully) filtered to turns.session_id set.
rg -n "detect_observed_bloat|struct DetectObservedBloatOptions|user_turns|turns: &|tool_result_events" "$TOB" | head -n 80
OBS_LINE="$(rg -n "fn detect_observed_bloat" "$TOB" | head -n 1 | cut -d: -f1)"
echo "detect_observed_bloat at: $OBS_LINE"
sed -n "$((OBS_LINE-60)),$((OBS_LINE+260))p" "$TOB"
# Find where it builds/uses `sessions` / filters by session_id.
rg -n "sessions: HashSet|HashSet<String>|session_id.*in|contains\\(&.*session_id|turns\\.iter\\(\\)\\.map\\(|e\\.session_id" "$TOB" | head -n 120
# Also inspect the detect_patterns implementation to see if extra user_turns_by_session sessions are ignored.
RG_BASE="crates/relayburn-sdk/src/analyze"
rg -n "fn detect_patterns|user_turns_by_session|content_by_session|tool_result_events" "$RG_BASE" | head -n 80
PATTERN_FILE="$(rg -l "fn detect_patterns" "$RG_BASE" | head -n 1)"
echo "detect_patterns file: $PATTERN_FILE"
PAT_LINE="$(rg -n "fn detect_patterns" "$PATTERN_FILE" | head -n 1 | cut -d: -f1)"
sed -n "$((PAT_LINE-80)),$((PAT_LINE+260))p" "$PATTERN_FILE"
# See how DetectPatternsOptions is applied (particularly how it uses user_turns_by_session).
rg -n "DetectPatternsOptions\\s*\\{|user_turns_by_session:|user_turns_by_session\\.get|user_turns_by_session\\[|get\\(&.*session_id" "$PATTERN_FILE" | head -n 120Repository: AgentWorkforce/burn
Length of output: 37696
🏁 Script executed:
#!/bin/bash
set -euo pipefail
TOB="crates/relayburn-sdk/src/analyze/tool_output_bloat.rs"
# Show build_lookup implementation (likely around line ~273 from prior output)
BL_LINE="$(rg -n "fn build_lookup" "$TOB" | head -n 1 | cut -d: -f1)"
echo "build_lookup at line: $BL_LINE"
sed -n "$((BL_LINE-30)),$((BL_LINE+220))p" "$TOB"
# Also inspect any helper that might filter by session ids from opts.turns.
rg -n "build_lookup|approx_tokens_by_use_id|tool_use_lookup|turns\\b|session_id.*turns" "$TOB" | head -n 120Repository: AgentWorkforce/burn
Length of output: 11587
🏁 Script executed:
#!/bin/bash
set -euo pipefail
# 1) Inspect Query definition + Default fields to know which scoping gets dropped by `..Default::default()`.
rg -n "struct Query\\s*\\{" crates/relayburn-sdk/src/query_verbs.rs crates/relayburn-sdk/src -S --glob '!**/target/**' | head -n 20
QDEF="$(rg -n "struct Query\\s*\\{" crates/relayburn-sdk/src -S --glob '!**/target/**' | head -n 1 | cut -d: -f1)"
echo "First Query struct match line: $QDEF"
FILE="$(rg -l "struct Query\\s*\\{" crates/relayburn-sdk/src -S --glob '!**/target/**' | head -n 1)"
echo "Query struct file: $FILE"
sed -n '1,220p' "$FILE"
# 2) Inspect build_query to see what q contains (esp. project) and how provider is represented.
rg -n "fn build_query\\(" crates/relayburn-sdk/src/query_verbs.rs crates/relayburn-sdk/src -S --glob '!**/target/**'
BQ_FILE="$(rg -l "fn build_query\\(" crates/relayburn-sdk/src -S --glob '!**/target/**' | head -n 1)"
BQ_LINE="$(rg -n "fn build_query\\(" "$BQ_FILE" -S --glob '!**/target/**' | head -n 1 | cut -d: -f1)"
echo "build_query at $BQ_FILE:$BQ_LINE"
sed -n "$((BQ_LINE-40)),$((BQ_LINE+160))p" "$BQ_FILE"
# 3) Inspect normalize_provider_filter / provider-related logic presence in Query.
rg -n "normalize_provider_filter|provider.*Query|Query.*provider|provider:" crates/relayburn-sdk/src/query_verbs.rs crates/relayburn-sdk/src -S --glob '!**/target/**' | head -n 80Repository: AgentWorkforce/burn
Length of output: 13762
Fix project/provider scoping leak in HotspotsGroupBy::Findings (tool-output-bloat runs on unscoped side data)
In crates/relayburn-sdk/src/query_verbs.rs run_hotspots_findings builds side_q from only session_id/since/enrichment and uses it to query query_user_turns + query_tool_result_events, dropping q.project and any provider allow-list logic (provider filtering is applied only to the turns slice). As a result, groupBy: Findings can pull tool-result evidence outside the caller’s requested project/provider slice.
Additionally, crates/relayburn-sdk/src/analyze/tool_output_bloat.rs’s detect_observed_bloat iterates over all passed tool_result_events without intersecting them to the provided turns sessions, so the findings can reference sessions not present in the turns slice.
🤖 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 `@crates/relayburn-sdk/src/query_verbs.rs` around lines 3177 - 3183,
HotspotsGroupBy::Findings leaks project/provider scope because
run_hotspots_findings builds side_q without q.project/provider filters and
detect_observed_bloat processes all tool_result_events; fix by updating
run_hotspots_findings to include q.project and the provider allow-list from q
(or from the same filter used for turns) when constructing side_q before calling
query_user_turns and query_tool_result_events, and ensure the tool_result_events
returned are either queried with those filters or post-filtered to only events
whose session_id (or other session identifier) is present in the turns slice;
also update detect_observed_bloat to iterate only over tool_result_events that
are intersected with the provided turns (e.g., filter by session_id in turns) so
findings cannot reference sessions outside the caller’s requested
turns/provider/project scope.
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.
User description
Fixes #467
Summary
findingsas aHotspotsGroupByvalue in the Rust SDK and napi binding.hotspots({ groupBy: "findings" })through the existing findings analyzer, using all detector kinds by default and honoring explicitpatternsfilters.@relayburn/sdktypings, enum constants, conformance coverage, and changelogs.Verification
cargo test -p relayburn-sdk hotspots_group_by_findingscargo check --workspacecargo test --workspacepnpm --filter @relayburn/sdk testhotspots({ ledgerHome: "tests/fixtures/cli-golden/ledger", groupBy: "findings" })againstpackages/sdk-node/src/index.darwin-arm64.nodeCodeAnt-AI Description
Allow
hotspotsto return findings results forgroupBy: "findings"What Changed
hotspots({ groupBy: "findings" })now returns the findings result instead of rejecting the optionHotspotsGroupByvalues now includefindingsImpact
✅ Fewer hotspots option errors✅ Clearer findings reports✅ Safer findings grouping in SDK apps💡 Usage Guide
Checking Your Pull Request
Every time you make a pull request, our system automatically looks through it. We check for security issues, mistakes in how you're setting up your infrastructure, and common code problems. We do this to make sure your changes are solid and won't cause any trouble later.
Talking to CodeAnt AI
Got a question or need a hand with something in your pull request? You can easily get in touch with CodeAnt AI right here. Just type the following in a comment on your pull request, and replace "Your question here" with whatever you want to ask:
This lets you have a chat with CodeAnt AI about your pull request, making it easier to understand and improve your code.
Example
Preserve Org Learnings with CodeAnt
You can record team preferences so CodeAnt AI applies them in future reviews. Reply directly to the specific CodeAnt AI suggestion (in the same thread) and replace "Your feedback here" with your input:
This helps CodeAnt AI learn and adapt to your team's coding style and standards.
Example
Retrigger review
Ask CodeAnt AI to review the PR again, by typing:
Check Your Repository Health
To analyze the health of your code repository, visit our dashboard at https://app.codeant.ai. This tool helps you identify potential issues and areas for improvement in your codebase, ensuring your repository maintains high standards of code health.