docs: truth up README, changelog, security notes, and tool descriptions#23
Merged
Conversation
The severity formula's thread-depth term was dead in production: thread bodies were never fetched, so thread_count was always 0 and min(0*10, 50) contributed nothing. Use the list API's threads count field instead (no extra API calls) and treat 0/missing as the baseline 1. Also: - Clamp recency so an unparseable created_at can't produce NaN scores and future-dated tickets can't pin severity to 100 - Strip PII-redaction placeholders before n-gram tokenization so 'email redacted' can't surface as an emerging theme - Delete the unreachable thread-body fetch path (includeThreads was never set by any caller; last present at d5f985f) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- One failing ProductLift portal no longer drops every portal's data; failures surface as named-portal warnings in the response - Total fetch failure (all sources) returns isError instead of an empty analysis that reads as success, and is never cached - Replace the module-global PII category log with an explicit per-request sink; concurrent tool calls no longer interleave audit metadata - get_feature_requests reports pii_scrubbing_applied and pii_categories_redacted, and stops sending commenter names (role only) - A malformed PRODUCTLIFT_PORTALS degrades to zero portals with the error surfaced in tool descriptions instead of killing the server - Label feature requests with their actual source portal - Guard themes.config.json loading with an actionable error - Scrub upstream error text in warnings; collapse whitespace in quotes - preview_only now describes exactly what is fetched and sent Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
…exes Pure move plus dedup; no behavior change. analyzeFeedback output verified byte-for-byte identical on a fixed dataset across this change. - New src/format.ts holds the PII-scrubbing formatters, quote extraction, agent-response detection, and detail trimming (index.ts is untestable by import: it exits without env and connects a transport at load) - New helpers replace duplicated blocks in index.ts: toErrorResult (4 identical catch bodies), buildLookupMaps, signalTypeOf, capTitles; get_feature_requests reuses filterClientsByPortal - Theme keyword regexes compile once per analyzeFeedback run instead of per data point x theme x keyword; matchesTheme keeps its signature and semantics (multi-word substring, word-boundary singles, escaping, no g flag) - New guardrail tests for parsePortalConfigs env parsing and the format layer (24 new tests; 64 total) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- README: 11 categories (was 9), example output matches actual category values and evidence_summary format, size estimates match the tool schema, methodology claim no longer implies automatic reading, top_voted_limit semantics documented (per portal, plus recent), score-normalization caveat added, commenter-name exclusion listed - CHANGELOG: record the qs 6.15.2 advisory patch (#16) and the 1.2.0 bin/npx removal the release notes omitted - SECURITY: document over-redaction of long digit runs as a known limitation; commenter names covered - Tool descriptions: synthesize vs plan selection guidance, methodology pointer on synthesize_feedback, per-portal top_voted_limit wording - methodology v2.1: thread count clarified as total including agent replies; normalization caveat added Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Transitive dep of @modelcontextprotocol/sdk; npm audit flagged the 4.12.x line high (GHSA-xrhx-7g5j-rcj5 and related). Lockfile-only. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
# Conflicts: # CHANGELOG.md
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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.
Stacked on #22; merge that first. Aligns every public claim with what the code actually does, following the audit. No behavior changes except tool description strings and the methodology resource text (bumped to v2.1).
themes.config.jsonships 11 categories, not 9 (16 themes was already correct). The example output now shows real category values (core,billing) and the actualevidence_summaryformat. Size estimates match the tool schema text. The methodology paragraph no longer claims Claude reads the resource automatically; responses link to it and instruct use whenkpi_contextis present, but reading depends on the client.top_voted_limitis documented as per portal with recent requests always included. Added the score-normalization caveat (scores are relative to one call; compare rankings, not raw scores) and the commenter-name exclusion row.qs6.15.0 → 6.15.2 advisory patch that landed in chore: patch qs advisory + add example output #16 without an entry, and corrects the omission that v1.2.0 removed thebin/npx pm-copilotpath added in 1.1.0.synthesize_feedbackpoints at the methodology resource and notes per-call score normalization.Verification: build and 64 tests green; description strings render correctly in
npm run tool -- --list.🤖 Generated with Claude Code