jpmschweitzer/odysseus
1
0
Fork 0
mirror of https://github.com/pewdiepie-archdaemon/odysseus.git synced 2026-11-02 03:02:28 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix(email): route summaries through shared LLM adapter (#5841)

Browse Source 
* fix(email): route summaries through shared llm adapter

* chore(ci): refresh PR checks

* fix(email): preserve scheduled summary safeguards

---------

Co-authored-by: Matyas Fenyves <16389204+uhhgoat@users.noreply.github.com>
This commit is contained in:
Matyas Gosztonyi
2026-08-08 23:06:41 +02:00
committed by GitHub
co-authored by Matyas Fenyves
parent e4fa4ae5dd
commit 42da399b4d
7 changed files with 670 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files
routes/email_helpers.py
+120
View File
@@ -247,6 +247,7 @@ import re as _re_reply
_REPLY_OPEN_RE = _re_reply.compile(r"<<<\s*(?:REPLY|SUMMARY|OUTPUT)\s*>>+", _re_reply.I)
_REPLY_CLOSE_RE = _re_reply.compile(r"<<<\s*END\s*>>+", _re_reply.I)
_REPLY_ROLE_MARKER_RE = _re_reply.compile(r"</?\|(?:assistant|assistan|user|system|tool)\|>?|</\|end\|>?", _re_reply.I)
_SUMMARY_BULLET_RE = _re_reply.compile(r"^(?:[-*\u2022]\s+|\d+[.)]\s+)")
def _extract_reply(text: str) -> str:
@@ -277,6 +278,125 @@ def _extract_reply(text: str) -> str:
return _strip_think(t).strip()
def _build_email_summary_messages(sender: str, subject: str, body_for_llm: str) -> list[dict[str, str]]:
return [
{
"role": "system",
"content": (
"You are an email summarizer. Format: 1-3 short bullet points "
"(use '- '). Cover: main point, action items, deadlines. If the "
"email has attachments (marked '--- ATTACHMENTS ---'), USE THEIR "
"CONTENTS - pull invoice totals, deadlines, key clauses, concrete "
"numbers/dates from PDFs/docs into the bullets. Be terse.\n\n"
"OUTPUT FORMAT: Put ONLY the bullet points between these exact "
"markers, each on its own line:\n"
"<<<SUMMARY>>>\n"
"- ...\n"
"<<<END>>>\n"
"Any reasoning must come BEFORE <<<SUMMARY>>> (ideally inside "
"<think>...</think>). Only the text between the markers is kept."
),
},
{
"role": "user",
"content": (
f"From: {sender}\nSubject: {subject}\n\n{body_for_llm[:12000]}"
"\n\n---\n\nSummarize the email. Output the bullets between "
"<<<SUMMARY>>> and <<<END>>>."
),
},
]
async def _generate_email_summary(
url: str,
model: str,
sender: str,
subject: str,
body_for_llm: str,
*,
headers: dict | None = None,
max_tokens: int = 8192,
timeout: int = 180,
) -> str:
"""Generate an interactive email summary through the shared LLM adapter."""
from src.llm_core import llm_call_async
raw = await llm_call_async(
url=url,
model=model,
messages=_build_email_summary_messages(sender, subject, body_for_llm),
temperature=0.3,
max_tokens=max_tokens,
headers=headers,
timeout=timeout,
workload="foreground",
)
return _normalize_email_summary(raw)
async def _generate_scheduled_email_summary(
url: str,
model: str,
sender: str,
subject: str,
body_for_llm: str,
*,
headers: dict | None = None,
owner: str | None = None,
max_tokens: int = 8192,
timeout: int = 180,
) -> str:
"""Generate a scheduled summary through the background task candidate chain."""
from src.task_endpoint import task_llm_call_async
raw = await task_llm_call_async(
messages=_build_email_summary_messages(sender, subject, body_for_llm),
fallback_url=url,
fallback_model=model,
fallback_headers=headers,
owner=owner,
temperature=0.3,
max_tokens=max_tokens,
timeout=timeout,
)
return _normalize_email_summary(raw)
def _normalize_email_summary(raw) -> str:
"""Extract a stable cache/UI summary from provider output."""
raw_text = raw or ""
if _REPLY_OPEN_RE.search(raw_text):
summary = _extract_reply(raw_text)
if summary:
return summary
cleaned = _strip_think(raw_text).strip()
bullets = [
line.strip()
for line in cleaned.splitlines()
if _SUMMARY_BULLET_RE.match(line.strip())
]
if bullets:
return "\n".join(bullets)
return cleaned.strip()
EMAIL_SUMMARY_ERROR_CODE = "email_summary_unavailable"
EMAIL_SUMMARY_ERROR_MESSAGE = "Failed to summarize"
def _email_summary_failure_log_detail(exc: BaseException) -> str:
"""Return useful provider-failure metadata without echoing exception text."""
detail = f"type={type(exc).__name__}"
status = getattr(exc, "status_code", None)
if status is None:
status = getattr(getattr(exc, "response", None), "status_code", None)
if isinstance(status, int):
detail += f" status={status}"
return detail
def _apply_email_style_mechanics(text: str) -> str:
"""Enforce deterministic writing-style mechanics that models often miss."""
if not text:
routes/email_pollers.py
+23 -9
View File
@@ -40,6 +40,7 @@ from routes.email_helpers import (
_pre_retrieve_context,
_attach_compose_uploads, _cleanup_compose_uploads, _q,
SCHEDULED_DB, _EMAIL_REPLY_SYS_PROMPT_BASE, _email_cache_owner_clause,
_generate_scheduled_email_summary, _email_summary_failure_log_detail,
)
logger = logging.getLogger(__name__)
@@ -653,6 +654,7 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
no_msgid = 0
examined = 0
_summaries_created = 0
_summary_failed = 0
_events_created = 0
_replies_drafted = 0
_reply_failed = 0
@@ -785,16 +787,17 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
if need_sum:
try:
summary = await task_llm_call_async(
messages=[
{"role": "system", "content": "You are an email summarizer. Format: 1-3 short bullet points (use '- '). Cover: main point, action items, deadlines. If the email has attachments (marked '--- ATTACHMENTS ---'), USE THEIR CONTENTS — pull out invoice totals, deadlines, key clauses, any concrete numbers/dates in PDFs/docs, and reflect them in the bullets. Be terse.\n\nOUTPUT FORMAT: Put ONLY the bullet points between these exact markers, each on its own line:\n<<<SUMMARY>>>\n- ...\n<<<END>>>\nAny reasoning or planning must come BEFORE <<<SUMMARY>>> (ideally inside <think>...</think>). Only the text between the markers is kept."},
{"role": "user", "content": f"From: {sender}\nSubject: {subject}\n\n{body_for_llm[:12000]}\n\n---\n\nSummarize the email. Output the bullets between <<<SUMMARY>>> and <<<END>>>."},
],
fallback_url=url, fallback_model=model, fallback_headers=headers,
summary = await _generate_scheduled_email_summary(
url=url,
model=model,
sender=sender,
subject=subject,
body_for_llm=body_for_llm,
headers=req_headers,
owner=account_owner or None,
temperature=0.3, max_tokens=16384, timeout=240,
max_tokens=16384,
timeout=240,
)
summary = _extract_reply((summary or "").strip())
if summary:
_c = _sql3.connect(SCHEDULED_DB)
_c.execute("""
@@ -808,10 +811,19 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
_summaries_created += 1
_uid_text = uid.decode() if isinstance(uid, bytes) else str(uid)
_detail_lines.append(f"summary · {_folder}#{_uid_text} · {subject or '(no subject)'} — {sender or '(unknown sender)'}")
else:
_summary_failed += 1
_uid_text = uid.decode() if isinstance(uid, bytes) else str(uid)
_detail_lines.append(f"summary empty · {_folder}#{_uid_text} · {subject or '(no subject)'} — {sender or '(unknown sender)'}")
except Exception as e:
_summary_failed += 1
_uid_text = uid.decode() if isinstance(uid, bytes) else str(uid)
_detail_lines.append(f"summary failed · {_folder}#{_uid_text} · {subject or '(no subject)'} — {sender or '(unknown sender)'}")
logger.warning(f"Auto-summary {uid} failed: {e}")
logger.warning(
"Auto-summary uid=%s failed %s",
_uid_text,
_email_summary_failure_log_detail(e),
)
if need_reply:
await _emit_progress(progress_cb, f"Drafting reply {processed + 1}/{_max_process} · checked {examined}/{len(uid_list)}")
@@ -1320,6 +1332,8 @@ async def _auto_summarize_pass_single(days_back: int = 1, account_id: str | None
parts.append(f"processed {processed} new")
if auto_sum:
parts.append(f"summarized {_summaries_created}")
if _summary_failed:
parts.append(f"{_summary_failed} summary failed")
if auto_reply_draft:
parts.append(f"drafted {_replies_drafted} repl" + ("y" if _replies_drafted == 1 else "ies"))
if _reply_failed:
routes/email_routes.py
+47 -47
View File
@@ -57,7 +57,8 @@ from routes.email_helpers import (
_extract_attachment_to_disk, _extract_html, _extract_text,
_fetch_sender_thread_context, _pre_retrieve_context,
_EMAIL_REPLY_SYS_PROMPT_BASE, _POOL_HOOKS,
_friendly_email_auth_error,
_friendly_email_auth_error, _email_summary_failure_log_detail,
_generate_email_summary, EMAIL_SUMMARY_ERROR_CODE, EMAIL_SUMMARY_ERROR_MESSAGE,
SendEmailRequest, ExtractStyleRequest,
ATTACHMENTS_DIR, COMPOSE_UPLOADS_DIR, SCHEDULED_DB,
attachment_extract_dir, _email_cache_owner_clause, email_translation_body_hash,
@@ -4766,8 +4767,6 @@ def setup_email_routes():
"""Generate a quick AI summary of an email body."""
try:
from src.endpoint_resolver import resolve_endpoint
from src.llm_core import _uses_max_completion_tokens, _restricts_temperature
import requests as _req
body = data.get("body", "")
subject = data.get("subject", "")
@@ -4778,7 +4777,11 @@ def setup_email_routes():
if account_id:
_assert_owns_account(account_id, owner)
if not body:
return {"success": False, "error": "No body provided"}
return {
"success": False,
"error": "No body provided",
"error_code": "email_summary_missing_body",
}
# If we know which UID this is, fetch the raw message and pull
# attachment text so the summary can reference invoice totals,
@@ -4807,53 +4810,43 @@ def setup_email_routes():
if not url:
url, model, headers = resolve_endpoint("default", owner=owner)
if not url or not model:
return {"success": False, "error": "No LLM endpoint configured"}
return {
"success": False,
"error": "No model configured for email summaries",
"error_code": "email_summary_not_configured",
}
req_headers = {"Content-Type": "application/json"}
if headers:
req_headers.update(headers)
tok_key = "max_completion_tokens" if _uses_max_completion_tokens(model) else "max_tokens"
payload = {
"model": model,
"messages": [
{"role": "system", "content": "You are an email summarizer. Format: 1-3 short bullet points (use '- '). Cover: main point, action items, deadlines. If the email has attachments (marked '--- ATTACHMENTS ---'), USE THEIR CONTENTS — pull invoice totals, deadlines, key clauses, concrete numbers/dates from PDFs/docs into the bullets. Be terse.\n\nOUTPUT FORMAT: Put ONLY the bullet points between these exact markers, each on its own line:\n<<<SUMMARY>>>\n- ...\n<<<END>>>\nAny reasoning must come BEFORE <<<SUMMARY>>> (ideally inside <think>...</think>). Only the text between the markers is kept."},
{"role": "user", "content": f"From: {sender}\nSubject: {subject}\n\n{body_for_llm[:12000]}\n\n---\n\nSummarize the email. Output the bullets between <<<SUMMARY>>> and <<<END>>>."},
],
tok_key: 8192,
"temperature": 0.3,
"stream": False,
}
# Reasoning models (o1/o3/o4/gpt-5) reject an explicit temperature.
if _restricts_temperature(model):
payload.pop("temperature", None)
resp = await asyncio.to_thread(
_req.post, url, json=payload, headers=req_headers, timeout=180
)
if not resp.ok:
return {"success": False, "error": f"LLM HTTP {resp.status_code}"}
rdata = resp.json()
msg = (rdata.get("choices") or [{}])[0].get("message", {})
content = (msg.get("content") or "").strip()
content = _extract_reply(content)
try:
content = await _generate_email_summary(
url=url,
model=model,
sender=sender,
subject=subject,
body_for_llm=body_for_llm,
headers=req_headers,
max_tokens=8192,
timeout=180,
)
except Exception as e:
logger.warning(
"Email summary LLM call failed %s",
_email_summary_failure_log_detail(e),
)
return {
"success": False,
"error": EMAIL_SUMMARY_ERROR_MESSAGE,
"error_code": EMAIL_SUMMARY_ERROR_CODE,
}
if not content:
# Model put everything in reasoning_content — extract bullet points
rc = (msg.get("reasoning_content") or "").strip()
# Find bullet-point style output (lines starting with -, •, *, or numbered)
bullet_lines = []
for line in rc.split("\n"):
stripped = line.strip()
if re.match(r"^[-•*]\s+|^\d+[.)]\s+", stripped):
bullet_lines.append(stripped)
if bullet_lines:
content = "\n".join(bullet_lines)
else:
# Last resort: take the last paragraph
paragraphs = [p.strip() for p in rc.split("\n\n") if p.strip()]
content = paragraphs[-1] if paragraphs else rc[:500]
if not content:
return {"success": False, "error": "Empty response from model"}
return {
"success": False,
"error": "The model returned an empty summary",
"error_code": "email_summary_empty",
}
# Cache the summary if we have a message_id
mid = data.get("message_id", "")
@@ -4876,8 +4869,15 @@ def setup_email_routes():
return {"success": True, "summary": content, "model_used": model}
except Exception as e:
logger.error(f"Failed to summarize: {e}")
return {"success": False, "error": "Mail operation failed"}
logger.error(
"Email summary route failed %s",
_email_summary_failure_log_detail(e),
)
return {
"success": False,
"error": EMAIL_SUMMARY_ERROR_MESSAGE,
"error_code": EMAIL_SUMMARY_ERROR_CODE,
}
@router.post("/translate")
async def translate_email(data: dict, owner: str = Depends(require_owner)):