Repository navigation
docs(tasks): the duplicate check's reply chain counts +2 - #305
Merged
Merged
Conversation
leemour
added a commit
to WireCatLabs/cli-core
that referenced
this pull request
Oct 17, 2026
…1497) ## Task The owner chose to lower the reply-chain weight in the task duplicate check after the second labelled set of real-chat pairs. ## Why [cli-testing performance/tasks/duplicates, "Follow-up: a second labelled set"](https://github.com/WireCatLabs/cli-testing/blob/main/performance/tasks/duplicates/README.md) labelled 213 pairs from real chats. Among the pairs shown as "maybe" or "likely", the ones with a reply chain were wrong 11 times in 13. At +2, shown-pair precision rose on both sets: 52% → 57% on the old set and 43% → 47% on the new one, losing one true pair on each. ## What - `TASK_SIMILARITY_WEIGHTS.reply.yes` goes from +6 to +2, with its reason updated. - Other weights and the bands are unchanged. "4–14 days apart" is left for a separate check. - `docs/dev/tasks-plan.md` gets the new weight in its weights table. - One line under Unreleased → Fixed. - Tests: - the weight table and the reply-chain scores move to the new values; - "a reply that asks for something new" now stays "different", not "maybe"; - the review-list tests relied on +6 to flag a bare "any news?" reply, so their reminders now name the invoice and amount. ## Testing - `pnpm typecheck`: passes. - `pnpm lint`: no errors (the 69 warnings were already there). - `pnpm test`: 5155 passed, 4 skipped. - `pnpm docs:check`: ok. `pnpm standard:docs`: no changes. Draft docs PR (merge after the release): WireCatLabs/cli-docs#305. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
…cond labelled set Weights table and the real-chats paragraph, in en/ru/es. Merge after the cli-core release that carries WireCatLabs/cli-core#1497. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
leemour
force-pushed
the
docs/dup-reply-chain-weight
branch
from
October 18, 2026 01:59
d51df82 to
8b80526
Compare
leemour
marked this pull request as ready for review
October 18, 2026 02:11
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.
Task
Document the reply-chain weight change from WireCatLabs/cli-core#1497.
Why
Among the pairs shown as "maybe" or "likely" in 213 labelled real-chat pairs, the ones in one reply chain were wrong 11 times in 13. The weight goes from +6 to +2. Source: cli-testing, "Follow-up: a second labelled set".
What
In
content/docs/tasks-architecture{,.ru,.es}.mdx:Merge
Draft. Merge after the cli-core release that carries #1497.
🤖 Generated with Claude Code