docs(analytics): add classifier dimensions/filters and response warnings#60
docs(analytics): add classifier dimensions/filters and response warnings#60jtcies wants to merge 2 commits into
Conversation
Sync skills with query builder changes since 2026-06-17: - Document classifier_dimensions request field (group by dynamic classifier-produced labels like topic, sentiment, category) - Document classifier_filters request field (filter on classifier dimension values with eq/neq/in/not_in) - Document response warnings array for non-fatal filter issues - Add classifier constraints to schema skill (max 10 each, 31-day limit) - Add classifier entries to decision tree in main analytics skill Co-Authored-By: Joseph Ciesielski <joseph.ciesielski@openrouter.ai>
Original prompt from Joseph
|
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
![perry-the-pr-maintainer[bot]](https://avatars.githubusercontent.com/in/3387167?s=60&v=4){kind=small}
There was a problem hiding this comment.
Perry's Review
Adds full documentation for classifier_dimensions and classifier_filters request fields, the data.warnings response field, and related schema/decision-tree references across three analytics skill files.
Verdict: ✅ LGTM
Details
Risk: 🟢 Low — docs-only changes to three SKILL.md files; no executable code, no API changes
CI: no blocking failures ✅ (only the in-progress perry review check pending)
Findings (see inline comments for full context):
- 🟡
skills/openrouter-analytics-query/SKILL.md:184— response field table omits clf_dimension_name/clf_dimension_value key names
Security: no concerns — pure documentation, no credentials, no code paths touched
Test coverage: N/A — documentation changes
Unresolved threads: none
Review metadata
Scope: first review (full)
Review: tier=small · model=unknown · score=1.0
…table Co-Authored-By: Joseph Ciesielski <joseph.ciesielski@openrouter.ai>
There was a problem hiding this comment.
Perry's Review
Adds classifier dimensions/filters documentation to three analytics skill SKILL.md files, and documents response warnings.
Verdict: ✅ LGTM
Details
Risk: 🟢 Low — docs-only changes
CI: all passing ✅
Findings (see inline comments for full context):
- Prior suggestion at
skills/openrouter-analytics-query/SKILL.md— resolved in this push
Security: no concerns — classifier_id ownership validated server-side per docs; no code touched
Test coverage: N/A — documentation only
Unresolved threads: none (prior suggestion addressed in e6e51c1)
Scope: incremental — 1 new line since prior review
Review: tier=small · model=claude-sonnet-latest · score=1.0
| | Field | Description | | ||
| |---|---| | ||
| | `data.data` | Array of result rows. Each row has keys for requested metrics, dimensions, and `date__<granularity>` (when granularity is set, e.g. `date__day`, `date__hour`) | | ||
| | `data.data` | Array of result rows. Each row has keys for requested metrics, dimensions, and `date__<granularity>` (when granularity is set). For `classifier_dimensions` queries with a single `dimension_name`, a column is aliased to that name (e.g., `category`). With multiple names or no `dimension_names`, rows include `clf_dimension_name` and `clf_dimension_value` columns. | |
There was a problem hiding this comment.
Prior suggestion resolved — the data.data row now documents both column shapes: single dimension_name → column aliased to that name (e.g. category); multiple names or omitted → generic clf_dimension_name / clf_dimension_value columns. This matches the detail already present in the Classifier Dimensions section.
Reviewed at e6e51c1
1 participant
Summary
Syncs analytics skills with query builder changes landed since the last sync (2026-06-17). The main addition is the classifier dimensions/filters feature —
classifier_dimensionsandclassifier_filtersare new optional request fields onPOST /api/v1/analytics/querythat allow grouping by and filtering on dynamic, user-defined classification labels (topic, sentiment, category, etc.) from thegeneration_classificationstable.Key changes across three skill files:
classifier_dimensions,classifier_filters), including schema tables, constraints (31-day limit, operator restrictions), and column aliasing behavior. Also documents the newdata.warningsresponse field for non-fatal filter resolution issues.Link to Devin session: https://openrouter.devinenterprise.com/sessions/2cb9ce3993bd43ffa3772ac9ebd18d5a
Requested by: @jtcies