1 files changed, 22 insertions, 0 deletions
diff --git a/llamachat/providers.py b/llamachat/providers.py
index a8b2350..23ad081 100644
--- a/llamachat/providers.py
+++ b/llamachat/providers.py
@@ -49,6 +49,12 @@ class Provider:
     # Provider-specific reasoning token budget. Currently SiliconFlow only;
     # ignored when unset so other endpoints do not receive an unknown key.
     thinking_budget: int | None = None
+    # Replay each assistant turn's reasoning_content on the next request.
+    # Interleaved-thinking providers (DeepSeek, SiliconFlow's GLM-4.7+) reject
+    # a tools request whose prior assistant turns omit it. Off by default:
+    # replaying thinking inflates context and the input bill for providers
+    # that neither need nor want it.
+    replay_reasoning: bool = False
 
     @property
     def is_local(self) -> bool:
@@ -189,6 +195,7 @@ def parse(values: dict, warnings: list[str] | None = None) -> dict[str, Provider
             price_in=_number(entry.get("price_in"), float),
             price_out=_number(entry.get("price_out"), float),
             thinking_budget=_number(entry.get("thinking_budget"), int),
+            replay_reasoning=bool(entry.get("replay_reasoning", False)),
         )
     return out
 
@@ -220,6 +227,21 @@ def split(model_id: str, table: dict[str, Provider]) -> tuple[str, str]:
     return LOCAL, model_id
 
 
+def replays_reasoning(model_id: str, table: dict[str, Provider], search_enabled: bool) -> bool:
+    """Whether a request to this model must replay reasoning_content.
+
+    Only true when search is enabled, because that is the only time the app
+    sends a `tools` key — the condition under which interleaved-thinking
+    providers demand the reasoning back. The caller still checks that a given
+    row has non-empty reasoning; a non-reasoning model has nothing to replay.
+    """
+    if not search_enabled:
+        return False
+    name, _ = split(model_id, table)
+    provider = table.get(name)
+    return bool(provider and provider.replay_reasoning)
+
+
 def apply_filter(provider: Provider, listed: list[str]) -> list[str]:
     """Keep models matching any of the provider's substrings.