fix(reviewer): ask DeepSeek for low reasoning effort in the Auto-Review guardian

CW-7450 item 2. consult_reviewer sent reasoning_effort None, temperature
0.0 and a 4,096-token cap. On DeepSeek no reasoning field means the server
default applies: thinking on, effort high. Temperature has no effect in
thinking mode. High-effort reasoning plus the verdict had to fit in 4,096
tokens together. When it did not, the incomplete stop mapped to
Unavailable and auto-approval stalled.

On the DeepSeek provider the guardian now sends reasoning_effort "low",
which DEEPSEEK_EFFORT_ALIASES maps to the lowest tier that is not off.
Every DeepSeek-provider catalog row (deepseek-flash, deepseek-v4-pro,
deepseek-v4-flash, deepseek-v4-flash-vision-exp) publishes "low" in its
effort options. Other providers keep None. Sending "low" everywhere would
fail the route's reasoning_options check where "low" is not listed (for
example OpenRouter, Together and Fireworks deepseek-v4-pro), and the
guardian would fail closed there.

Drafted by Codewhale running DeepSeek-V4.1-Flash-1017; it flagged the
cross-provider risk itself. Claude narrowed the change to DeepSeek.

Gates: `scripts/dev-test.sh tui reviewer auto_review guardian`: 92 passed,
0 failed; CI-form clippy -p codewhale-tui --all-targets --all-features
-D warnings clean; rustfmt clean; sync-changelog run.

Refs CW-7450

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01NBKbhx19BRbZtvWK8rVKjz

CHANGELOG.md

@@ -73,6 +73,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   thinking, because that returns a 400.
 - A DeepSeek Chat response that ends with `insufficient_system_resource` or
   `aborted` is now treated as incomplete, not as a finished answer.
+- On DeepSeek, the Auto-Review guardian now asks for low reasoning effort.
+  It used to leave thinking at DeepSeek's default (high), so the reasoning
+  could use up the guardian's 4,096-token answer budget, report the review
+  as unavailable, and stall auto-approval.
 - Durability and blocking-call fixes from the #6553 and #6555 audits:
   - On Windows the updater syncs the staged binary, tries an atomic replace
     first, and reports where the previous binary is if restoring it fails.

crates/tui/CHANGELOG.md

@@ -73,6 +73,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   thinking, because that returns a 400.
 - A DeepSeek Chat response that ends with `insufficient_system_resource` or
   `aborted` is now treated as incomplete, not as a finished answer.
+- On DeepSeek, the Auto-Review guardian now asks for low reasoning effort.
+  It used to leave thinking at DeepSeek's default (high), so the reasoning
+  could use up the guardian's 4,096-token answer budget, report the review
+  as unavailable, and stall auto-approval.
 - Durability and blocking-call fixes from the #6553 and #6555 audits:
   - On Windows the updater syncs the staged binary, tries an atomic replace
     first, and reports where the previous binary is if restoring it fails.

crates/tui/src/core/engine/reviewer.rs

@@ -119,6 +119,8 @@ pub(crate) async fn consult_reviewer(
             None,
         );
     }
+    let deepseek = client.provider_name() == crate::config::ProviderKind::Deepseek.as_str();
+    let reasoning_effort = deepseek.then(|| "low".to_string());
     let request = MessageRequest {
         model: client.model().to_string(),
         messages: vec![Message {
@@ -134,7 +136,7 @@ pub(crate) async fn consult_reviewer(
         tool_choice: None,
         metadata: None,
         thinking: None,
-        reasoning_effort: None,
+        reasoning_effort,
         stream: Some(false),
         temperature: Some(0.0),
         top_p: None,