feat(asr-pipeline): merge PR #1 webauth/CSRF/locking hardening and web_password fallback
Build image / build (push) Canceled after 0s
Build ASR Pipeline / image (push) Canceled after 0s

This commit is contained in:
Codex
2026-11-02 06:37:33 -08:00
parent 9debd1c47d
commit 3c70861463
44 changed files with 4354 additions and 333 deletions
@@ -337,6 +337,18 @@ def normalize_chunks(chunks, cleaned_parts: list[str], flags: list[dict],
}
def scrub_internal_wording(text: str) -> str:
"""Keep pipeline jargon out of text a person will read."""
for src, dst in (
("卡片未提供", "记录未写明"),
("卡片提及", "录音中提到"),
("事实卡片", "整理要点"),
("粗整理草稿", "整理稿"),
):
text = text.replace(src, dst)
return text
def extract_evidence(parts: list[str], usage: Usage) -> str:
jobs = [prompts.EVIDENCE_PROMPT.format(chunk_id=i, body=body)
for i, body in enumerate(parts)]
@@ -347,7 +359,7 @@ def extract_evidence(parts: list[str], usage: Usage) -> str:
max_tokens=1400, usage=usage)
except PartialFailure as pf:
outs = pf.outputs
return "\n".join(x for x in outs if x.strip())
return scrub_internal_wording("\n".join(x for x in outs if x.strip()))
# ------------------------------------------------------------------ S4
@@ -386,7 +398,7 @@ def write_draft(cleaned: str, meta: dict, context: str, date: str,
speaker_note=prompts.SPEAKER_NOTE.get(backend, ""),
context=ctx, date=date, source_detail=detail,
transcript=transcript_path, extra_fm=extra, body=cleaned)
return chat(CFG.draft_model, prompt, max_tokens=12000, usage=usage)
return scrub_internal_wording(chat(CFG.draft_model, prompt, max_tokens=12000, usage=usage))
# ------------------------------------------------------------------ driver