Commit Graph

3 Commits

Author SHA1 Message Date
Brummel bb584b6ea0 Refactor: Remove unused Whisper variants
This commit removes the `whisper_variant` and `whisper_hotwords_variant`
fields from the `run_id` generation and the `print_meta_summary`
function.

These variants are no longer used as the project is shifting focus to
LLM-based generation. The `run_full_case.rs` example has also been
updated to reflect this change.
2026-04-30 16:56:12 +02:00
Brummel ff53d8bd1b experiments: pre-LLM gazetteer pass in run_llm_only + new prompt variants
The previous run_llm_only only applied the gazetteer post-LLM, which
silently underestimated the production pipeline: tokens like Inoxaparin
or Klappenvizien are caught pre-LLM in production, but the test tool
left them in the LLM input. Adding `gazetteer.replace()` to each
recording before render_prompt mirrors transcribe/worker.rs:138 exactly,
making sandbox results faithful to production behavior.

New prompt variants kept for the iteration record:
- v3_treue_konsolidiert.txt — the winning variant now in
  server/src/analyze/prompt.rs; redundancies eliminated where they were
  not load-bearing
- v4_treue_kompakt.txt — rejected variant (3/3 unmarked Hypotonie
  hallucinations); kept so future iterations don't repeat the
  experiment

baseline.txt now mirrors the current server prompt (was a stale
pre-v2 snapshot), so future sandbox runs against `baseline.txt`
compare against what is actually shipping.
2026-04-27 23:27:18 +02:00
Brummel 10d0a6ba94 Add experiments sandbox: prompt iteration tooling
Nested Cargo-Workspace unter experiments/ als Pfad-Dependency auf
../server. Reproduziert die Production-Pipeline 1:1 durch direkte
Wiederverwendung der Server-Module (transcribe::whisper, analyze::llm,
gazetteer, ffmpeg-Remux) — kein eigenes HTTP-Re-Implementieren, kein
Drift-Risiko zur Live-Pipeline.

Drei bin-Targets:
- run_full_case: volle Pipeline (ffmpeg → whisper → pre-gazetteer → llm
  → post-gazetteer), n Runs einer Variante
- run_llm_only: schneller LLM-Iterations-Pfad auf existierenden,
  gazetteer-bereinigten Transkripten — spart Whisper-Calls
- diff_runs: qualitativer Vergleich zwischen zwei Run-Verzeichnissen

Repo-Hygiene: case_*/ (Patientendaten, Symlinks zu tmpdata) und _data/
(Run-Outputs) sind komplett gitignored. Nur Code und fall-übergreifende
Prompt-Hypothesen (prompts/) werden versioniert.

Erste Prompt-Varianten zur Treue-Klausel und Konflikt-Auflösung:
prompts/llm/v1_treue.txt, v2_treue.txt.
2026-04-27 22:43:02 +02:00