fix: recover from llama.cpp context overflow and reqwest SSE decode failures

Extend auto-compaction error detection to handle additional error patterns
from llama.cpp backends: 'Context size has been exceeded',
'exceed_context_size_error', 'exceeds the available context size'. Also
recover from reqwest 'error decoding response body' errors — some
llama.cpp instances return a non-SSE plaintext HTTP 500 on context overflow,
causing the SSE deserializer to fail.

Add dynamic threshold adaptation: parse server-reported context window
size from error messages (e.g., '(81920 tokens)') and set the auto-
compaction trigger at 70% of that value. This replaces the need for a
hardcoded threshold, adapting automatically to any backend's limits.

This patch was developed with assistance from OpenCode and local Qwen 3.6
API server.

rust/crates/runtime/src/conversation.rs

@@ -204,6 +204,13 @@ where
         self
     }
 
+    /// Update the auto-compaction threshold after construction. This allows the
+    /// caller to tune the threshold based on runtime information (e.g., the
+    /// server-returned context window size from a 400 error).
+    pub fn set_auto_compaction_input_tokens_threshold(&mut self, threshold: u32) {
+        self.auto_compaction_input_tokens_threshold = threshold;
+    }
+
     #[must_use]
     pub fn with_hook_abort_signal(mut self, hook_abort_signal: HookAbortSignal) -> Self {
         self.hook_abort_signal = hook_abort_signal;