fix(projekt-matching): break infinite alert loop (issue 2)

Root cause chain (evidence: 25+ failed traces on nproj/3022414):
straight quote in page text ends the guided-decoding JSON string
early -> grammar deadlock -> whitespace loop until context/token
limit -> chat_json fails 3x (~35 min) -> IMAP conn idles out ->
move_to_trash raises -> mail never trashed -> reprocessed forever.

- ingest/mailer: MailBox.ensure_alive() reconnect before finalize;
  move_to_trash failure falls back to flag_checked, run continues
- stages: page_text() feeds only div.content minus skill-tag cloud
  to the LLM and maps quote chars to apostrophes (the actual
  degeneration trigger, live-verified: extract now OK in 21 s)
- llm: requirements maxItems 40; max_tokens 8192 caps degenerate
  runs at ~100 s instead of ~10 min

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

projekt-matching/projektmatch/ingest.py

@@ -119,6 +119,10 @@ def run_ingest(cfg, mailbox=None, dispatch=None, espo=None, resolve=None):
                             or f"unbekannter Status: {result.get('status')!r}")
                     results.append(result)
                     summary[result["status"]] += 1
+                try:
+                    box.ensure_alive()  # Flow-2-Dispatches können >30 min dauern — Server-Idle-Timeout
+                except Exception:      # noqa: BLE001
+                    pass               # Alert/Trash unten haben eigene Fallbacks
                 failed = [r for r in results if r["status"] == "failed"]
                 if failed:
                     lines = "\n\n".join(
@@ -134,7 +138,14 @@ def run_ingest(cfg, mailbox=None, dispatch=None, espo=None, resolve=None):
                             "werden:\n\n" + lines + "\n")
                     except Exception:          # noqa: BLE001
                         summary["alertFailed"] = summary.get("alertFailed", 0) + 1
-                box.move_to_trash(uid)
+                try:
+                    box.move_to_trash(uid)
+                except Exception:              # noqa: BLE001
+                    summary["trashFailed"] = summary.get("trashFailed", 0) + 1
+                    try:
+                        box.flag_checked(uid)  # nie erneut verarbeiten — Terminal-Zustand
+                    except Exception:          # noqa: BLE001
+                        pass                   # nächster Lauf räumt auf
             return summary
         finally:
             box.close()

projekt-matching/projektmatch/llm.py

@@ -1,7 +1,9 @@
 """vLLM (OpenAI-compatible) calls with response_format json_schema + German prompts.
 
-max_tokens stays UNSET so nothing can truncate the final answer (65k
-context window). Thinking is DISABLED via chat_template_kwargs: with the
+max_tokens is capped at 8192: every valid answer fits comfortably, and an
+uncapped run lets a degenerate generation grind for ~10 min before failing
+(observed live: 100+-requirement JSON, broken at ~char 1725, 3 retries =
+~35 min per cycle). Thinking is DISABLED via chat_template_kwargs: with the
 vLLM qwen3 reasoning parser active, json_schema guided decoding plus
 thinking degenerates — the run burns the entire context window
 (finish_reason "length", ~63k completion tokens) and returns empty or
@@ -34,6 +36,7 @@ EXTRACT_SCHEMA = {
         "contactPerson": {"type": ["string", "null"]},
         "requirements": {
             "type": "array",
+            "maxItems": 40,
             "items": {
                 "type": "object",
                 "properties": {
@@ -139,6 +142,7 @@ z. B. vLLM, TGI, Triton" ab).
 
 def _post(base, model, messages, schema):
     body = {"model": model, "messages": messages, "temperature": 0.1,
+            "max_tokens": 8192,
             "chat_template_kwargs": {"enable_thinking": False},
             "response_format": {"type": "json_schema", "json_schema": {
                 "name": "out", "schema": schema}}}

projekt-matching/projektmatch/mailer.py

@@ -16,12 +16,31 @@ KEYWORD = "$ProjektChecked"
 
 class MailBox:
     def __init__(self, user, password, conn=None):
-        self.conn = conn or imaplib.IMAP4_SSL(IMAP_HOST, IMAP_PORT)
-        if conn is None:
-            self.conn.login(user, password)
+        self.user, self.password = user, password
+        self.conn = conn or self._connect()
         self.conn.select("INBOX")
         self._trash = None
 
+    def _connect(self):
+        conn = imaplib.IMAP4_SSL(IMAP_HOST, IMAP_PORT)
+        conn.login(self.user, self.password)
+        return conn
+
+    def ensure_alive(self):
+        """Reconnect if the server dropped the connection (idle timeout)."""
+        try:
+            typ, _ = self.conn.noop()
+            if typ == "OK":
+                return
+        except Exception:      # noqa: BLE001
+            pass
+        try:
+            self.conn.logout()
+        except Exception:      # noqa: BLE001
+            pass
+        self.conn = self._connect()
+        self.conn.select("INBOX")
+
     def unchecked_uids(self):
         typ, data = self.conn.uid("SEARCH", None, f"UNKEYWORD {KEYWORD}")
         if typ != "OK" or not data or not data[0]:

projekt-matching/projektmatch/stages.py

@@ -20,6 +20,7 @@ TEAM_BY_OFFER = {"Projekt": "DesTEngS",
                  "Arbeitnehmer-Angebot": "Arbeitnehmer",
                  "ANÜ": "ANÜ"}
 MIN_PAGE_CHARS = 200
+QUOTES = str.maketrans({c: "'" for c in "„“”\"«»‹›"})
 
 
 def run_stage(name, fn, ctx, cfg, **kw):
@@ -32,6 +33,25 @@ def run_stage(name, fn, ctx, cfg, **kw):
         return ctx
 
 
+def page_text(html):
+    """Project text for the LLM: header + description, WITHOUT the skill-tag
+    cloud (div.project-body-badges, ~100 entries on some pages — blows the
+    requirements list up until the model emits broken JSON) and without
+    site chrome. Falls back to whole-page text if div.content is missing."""
+    soup = BeautifulSoup(html, "html.parser")
+    for tag in soup(["script", "style", "noscript"]):
+        tag.decompose()
+    root = soup.find("div", class_="content") or soup
+    for tag in root.find_all(class_="project-body-badges"):
+        tag.decompose()
+    # Anführungszeichen -> Apostroph: ein wörtlich übernommenes " beendet den
+    # JSON-String vorzeitig und treibt guided decoding in eine Whitespace-
+    # Endlosschleife (finish_reason "length", live verifiziert an nproj/3022414)
+    return "\n".join(line for line in
+                     root.get_text("\n", strip=True).splitlines()
+                     if line.strip()).translate(QUOTES)
+
+
 def stage_fetch(ctx, cfg):
     last = None
     for attempt in range(3):
@@ -39,12 +59,7 @@ def stage_fetch(ctx, cfg):
             resp = requests.get(ctx["canonical"], timeout=30,
                                 headers={"User-Agent": BROWSER_UA})
             resp.raise_for_status()
-            soup = BeautifulSoup(resp.text, "html.parser")
-            for tag in soup(["script", "style", "noscript"]):
-                tag.decompose()
-            text = "\n".join(line for line in
-                             soup.get_text("\n", strip=True).splitlines()
-                             if line.strip())
+            text = page_text(resp.text)
             if len(text) < MIN_PAGE_CHARS:
                 raise ValueError(
                     f"Seitentext zu kurz ({len(text)} Zeichen) — "