From 0875fe7ac0cbc1ae7b157a0b250dcf09a6df1f63 Mon Sep 17 00:00:00 2001
From: mARTin-B78 <mail@martin-bierschenk.de>
Date: Tue, 9 Jun 2026 15:02:45 +0200
Subject: [PATCH] llm: catch all exceptions, validate response, show
 transcription preview (v1.9.9)

- llm.py: catch OSError/TimeoutError (socket.timeout is NOT a URLError subclass)
  and bare Exception so no path kills the background thread silently
- daemon.py: catch unexpected exceptions from llm.chat and surface them as
  overlay errors instead of silent thread death
- daemon.py: reject LLM responses that are >80 % whitespace (cold-start
  model returning spaces/blank lines gets discarded, not typed)
- daemon.py: show transcribed text in overlay immediately before thinking
  animation so user can see what was heard while LLM processes

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 linux/blitztext/daemon.py | 24 ++++++++++++++++++++++++
 linux/blitztext/llm.py    |  7 +++++++
 2 files changed, 31 insertions(+)

diff --git a/linux/blitztext/daemon.py b/linux/blitztext/daemon.py
index 51b3087..df1a4fa 100644
--- a/linux/blitztext/daemon.py
+++ b/linux/blitztext/daemon.py
@@ -510,6 +510,9 @@ class Daemon:
                     return
                 self._emit("busy", label, "Rewriting…")
                 self._dnotify(f"⌛ {label}", "Rewriting…")
+                # Show the transcribed text immediately so the user sees what was heard.
+                if self.text_cb:
+                    self.text_cb(f"📝 {text}")
                 # Stream the rewrite into the overlay so you watch the model write
                 # (the bubble updates token-by-token). The delivered text is still
                 # the complete result, typed once the rewrite finishes.
@@ -559,6 +562,27 @@ class Daemon:
                     self._emit("error", label, str(exc))
                     self._dnotify("Rewrite failed", str(exc), "critical")
                     log(f"ERROR ({label} rewrite): {exc}")
+                    if self.text_cb:
+                        self.text_cb(f"✗ {exc}")
+                    return
+                except Exception as exc:  # noqa: BLE001 - guard against any uncaught error
+                    msg = f"LLM error: {exc}"
+                    self._emit("error", label, msg)
+                    log(f"ERROR ({label} rewrite unexpected): {exc}")
+                    if self.text_cb:
+                        self.text_cb(f"✗ {msg}")
+                    return
+
+                # Sanity-check: reject responses that are >80 % whitespace —
+                # a model that's cold-starting or misconfigured sometimes streams
+                # spaces or blank lines instead of real output.
+                non_ws = sum(1 for c in text if not c.isspace())
+                if non_ws < max(1, len(text) * 0.20):
+                    msg = "LLM returned mostly whitespace — discarded"
+                    self._emit("error", label, msg)
+                    log(f"ERROR ({label}): {msg} (len={len(text)})")
+                    if self.text_cb:
+                        self.text_cb(f"✗ {msg}")
                     return
 
             if not text:
diff --git a/linux/blitztext/llm.py b/linux/blitztext/llm.py
index 3a25b4d..0cdc295 100644
--- a/linux/blitztext/llm.py
+++ b/linux/blitztext/llm.py
@@ -93,6 +93,13 @@ def chat(
         raise LLMError(f"Connection failed: {exc.reason}") from exc
     except (KeyError, IndexError, TypeError) as exc:
         raise LLMError(f"Unexpected response: {exc}") from exc
+    except (TimeoutError, OSError) as exc:
+        # socket.timeout (subclass of OSError / TimeoutError) fires when the server
+        # stops sending data mid-stream. Not wrapped in URLError — must be caught
+        # separately or it would propagate uncaught and kill the background thread.
+        raise LLMError(f"Request timed out or connection lost: {exc}") from exc
+    except Exception as exc:  # noqa: BLE001
+        raise LLMError(f"Unexpected error: {exc}") from exc
 
     content = (content or "").strip()
     if not content: