Till JS 8adef1b39c fix(shared-llm): fall back to message.reasoning when content is empty ... Reasoning-style models (Gemma 4 E4B is the first one we use, but DeepSeek R1, Gemini 2.5 thinking, etc. behave the same way) split their output into two fields: - message.content — the final answer - message.reasoning — the chain-of-thought leading up to it When the model is given too few max_tokens to finish reasoning AND emit content, the response comes back with content="" and reasoning populated with the half-finished thought. Verified empirically with gemma4:e4b and `max_tokens: 10` on a "Sage Hi auf Deutsch in einem Wort" prompt — content was "" while reasoning had "Here's a thinking process to..." (cut off mid-thought). For the title task this rarely matters because the system prompt is directive enough to skip the thinking phase (verified: same gemma4: e4b returns clean 7-token titles like "Sonnenstrahlen genießen heute" with the standard system prompt + max_tokens 32). But it's a real failure mode for any future task that uses a less-directive prompt or hits a longer reasoning chain. Defensive fix: prefer message.content first, fall back to message.reasoning if content is empty. The fallback is a string-or- nothing operation, no semantic interpretation — if the reasoning field happens to contain a usable answer fragment, the caller's cleanup chain (e.g. generateTitleTask's strip-quotes-and-dots pipeline) will normalize it. If it's truly half-finished thought, the caller's runRules fallback still kicks in via the existing empty-result detection. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>		2026-04-09 16:29:22 +02:00
..
src	fix(shared-llm): fall back to message.reasoning when content is empty	2026-04-09 16:29:22 +02:00
package.json	feat(shared-llm): Phase 4 — persistent LLM task queue	2026-04-09 01:51:20 +02:00
tsconfig.json	fix(mana/web): unwrap $state proxy in workbench-scenes Dexie writes	2026-04-09 00:44:00 +02:00