rbrooks/Quest-Board
Watch
1
0
Fork
You've already forked Quest-Board
 0
Code Issues 58 Pull requests 7 Projects Releases 76 Packages Wiki Activity Actions

feat(webapp): campaign names go to the transcriber as hotwords by default (#1315) #1316

Merged
claude-bot merged 2 commits from feat/1315-hotwords-default into main 2026-11-02 18:49:16 +00:00
Conversation 0 Commits 2 Files changed 8 +90 -30
claude-bot commented 2026-11-02 17:31:38 +00:00
Collaborator
Copy link

This is part of #1315, the owner's answer to Q203 after #506's measurement (PR #1313).

  • Default: QB_ASR_VOCABULARY_STYLE now defaults to hotwords. On a realistic 100-name list, hotwords got 89–90% of names right against 80–82% for initial_prompt; at 24 names the two were the same.
  • Older servers: a server that doesn't declare hotwords gets initial_prompt.
    • As the default, that fallback is quiet, logged at info.
    • An operator who sets hotwords explicitly still gets the warning. "Explicitly" means the env var is present, which is how compose passes .env.
  • Exactly one field is still ever sent. Both at once gave a 500 in the measurement.
  • Opting out: QB_ASR_VOCABULARY_STYLE=initial_prompt keeps the old behaviour.
  • Tests, .env.example, docs/OPERATIONS.md and a changelog fragment are updated.

Checked on docker-test:

  • lint is clean;
  • the changelog check passes;
  • every transcription, vocabulary, capability and provider test (-k over those words): 723 passed, 13 skipped.

Before 4.7.0 ships, #1315's dev check still has to run: one real session's kept audio, transcribed with each style and scored for names, without touching that session.

🤖 Generated with Claude Code

This is part of #1315, the owner's answer to Q203 after #506's measurement (PR #1313). - **Default:** `QB_ASR_VOCABULARY_STYLE` now defaults to `hotwords`. On a realistic 100-name list, hotwords got 89–90% of names right against 80–82% for `initial_prompt`; at 24 names the two were the same. - **Older servers:** a server that doesn't declare hotwords gets `initial_prompt`. - As the default, that fallback is quiet, logged at info. - An operator who sets `hotwords` explicitly still gets the warning. "Explicitly" means the env var is present, which is how compose passes `.env`. - **Exactly one field** is still ever sent. Both at once gave a 500 in the measurement. - **Opting out:** `QB_ASR_VOCABULARY_STYLE=initial_prompt` keeps the old behaviour. - Tests, `.env.example`, `docs/OPERATIONS.md` and a changelog fragment are updated. **Checked on docker-test:** - lint is clean; - the changelog check passes; - every transcription, vocabulary, capability and provider test (`-k` over those words): 723 passed, 13 skipped. **Before 4.7.0 ships**, #1315's dev check still has to run: one real session's kept audio, transcribed with each style and scored for names, without touching that session. 🤖 Generated with [Claude Code](https://claude.com/claude-code)
The owner's call on #506's measurement (Q203): on a 100-name list
hotwords got 89-90% of names right against 80-82% for initial_prompt.
QB_ASR_VOCABULARY_STYLE now defaults to hotwords; a server that does not
declare them gets the prompt, quietly, and an operator who set hotwords
on purpose still gets the warning. initial_prompt keeps the old way.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
test: the vocabulary tests expect hotwords from a server that offers them (#1315)
All checks were successful
CI / Summarisation accuracy eval harness (stub provider) (pull_request) Successful in 59s
Details
CI / Backend lint (ruff) (pull_request) Successful in 1m0s
Details
CI / Does this change touch the recording path? (pull_request) Successful in 18s
Details
CI / Bot/backend version sync (pull_request) Successful in 31s
Details
CI / Feedback site tests (pull_request) Successful in 48s
Details
CI / Which journeys does this change need? (pull_request) Successful in 20s
Details
CI / Bot tests and audit (pull_request) Successful in 3m29s
Details
CI / Frontend (shard 2/2) (pull_request) Successful in 7m18s
Details
CI / Docker image build (pull_request) Successful in 7m7s
Details
CI / Synthetic session harness (no GPU, no LLM) (pull_request) Successful in 8m43s
Details
CI / Frontend (shard 1/2) (pull_request) Successful in 19m56s
Details
CI / Backend migration, tests, and audit (pull_request) Successful in 35m51s
Details
CI / End-to-end journeys (desktop) (pull_request) Successful in 28m21s
Details
361eef36c3 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Sign in to join this conversation.
Reviewers
No reviewers
Labels
Clear labels   
backend
Issue related to the backend

  
bot
Issue related to the bot

  
bug
Something is not working

  
duplicate
This issue or pull request already exists

  
enhancement
New feature

  
frontend
Issue related to the frontend

  
help wanted
Need some help

  
invalid
Something is wrong

  
question
More information is needed

  
recording
Issue related to the recording system

  
security
Security hardening / vulnerability work

  
wontfix
This won't be fixed

No labels
backend
bot
bug
duplicate
enhancement
frontend
help wanted
invalid
question
recording
security
wontfix
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set

Reference
rbrooks/Quest-Board!1316
No description provided.