Add DeepSeek platform + ChatCompletions dialect system (provider 3)

The 6th registry row: id "deepseek", DEEPSEEK_API_KEY > auth.json
"deepseek" scope, base https://api.deepseek.com (chat rides
{base}/chat/completions per official docs) with KIGI_DEEPSEEK_BASE_URL
override, enrichment-backed metadata (1M context, 384k output cap,
high/max effort menu).

Structural fix the cycle exposed: kigi's Kimi-specific body adaptation
ran UNCONDITIONALLY on every ChatCompletions request. New ChatCompat
dialect, declared per platform row and threaded through SamplerConfig,
ClientDefaults, and the session-persisted SamplingConfig (serde-default
Kimi keeps restored pre-field sessions and BYOK endpoints byte-identical;
production persist seams copy it; subagents inherit it):
- Kimi: full legacy pipeline (dispatch ≡ legacy pinned)
- DeepSeek: thinking:{type, reasoning_effort} per api-docs.deepseek.com
  (server maps low/medium→high, xhigh→max itself; none disables; absent
  leaves the server default)
- Passthrough: OpenAI-style reasoning_effort scalar untouched (unblocks
  Groq and the rest of the OpenAI-compatible list)

Review-confirmed release blocker fixed: kigi replays Kimi's
reasoning_content (and its private model_id) on input assistant
messages — Kimi consumes these, but DeepSeek documents input
reasoning_content as prefix-mode-only (historically a 400) and other
providers don't know either field. The DeepSeek and Passthrough arms now
strip both; Kimi's own pipeline is untouched. Pinned on both message
shapes.

crates/codegen/kigi-chat-state/src/actor/state.rs

@@ -272,6 +272,7 @@ mod tests {
             temperature: None,
             top_p: None,
             api_backend: Default::default(),
+            chat_compat: Default::default(),
             extra_headers: Default::default(),
             context_window: std::num::NonZeroU64::new(128_000).unwrap(),
             reasoning_effort: None,

crates/codegen/kigi-chat-state/src/actor/tests.rs

@@ -23,6 +23,7 @@ fn test_config_with_window(context_window: u64) -> SamplingConfig {
         temperature: None,
         top_p: None,
         api_backend: Default::default(),
+        chat_compat: Default::default(),
         extra_headers: Default::default(),
         context_window: NonZeroU64::new(context_window)
             .expect("test context_window must be non-zero"),
@@ -913,6 +914,7 @@ async fn update_sampling_config_is_queryable() {
         temperature: Some(0.5),
         top_p: None,
         api_backend: Default::default(),
+        chat_compat: Default::default(),
         extra_headers: Default::default(),
         context_window: NonZeroU64::new(200_000).unwrap(),
         reasoning_effort: None,
@@ -1298,6 +1300,7 @@ async fn build_request_uses_sampling_config() {
         temperature: Some(0.7),
         top_p: Some(0.9),
         api_backend: Default::default(),
+        chat_compat: Default::default(),
         extra_headers: Default::default(),
         context_window: NonZeroU64::new(128_000).unwrap(),
         reasoning_effort: None,
@@ -3401,6 +3404,7 @@ async fn sampling_config_survives_compaction_replacement() {
         temperature: Some(0.7),
         top_p: Some(0.95),
         api_backend: ApiBackend::Responses,
+        chat_compat: Default::default(),
         extra_headers: Default::default(),
         context_window: NonZeroU64::new(500_000).unwrap(),
         reasoning_effort: None,
@@ -3481,6 +3485,7 @@ async fn model_metadata_lost_after_compaction_then_recovered_on_next_turn() {
         temperature: Some(0.7),
         top_p: Some(0.95),
         api_backend: Default::default(),
+        chat_compat: Default::default(),
         extra_headers: Default::default(),
         context_window: NonZeroU64::new(500_000).unwrap(),
         reasoning_effort: None,
@@ -3569,6 +3574,7 @@ async fn context_window_downgrade_triggers_auto_compact() {
         temperature: Some(0.7),
         top_p: Some(0.95),
         api_backend: ApiBackend::Responses,
+        chat_compat: Default::default(),
         extra_headers: Default::default(),
         context_window: NonZeroU64::new(500_000).unwrap(),
         reasoning_effort: None,

crates/codegen/kigi-chat-state/src/commands.rs

@@ -370,6 +370,7 @@ mod tests {
                 temperature: None,
                 top_p: None,
                 api_backend: Default::default(),
+                chat_compat: Default::default(),
                 extra_headers: Default::default(),
                 context_window: std::num::NonZeroU64::new(128_000).unwrap(),
                 reasoning_effort: None,

crates/codegen/kigi-chat-state/src/types.rs

@@ -178,6 +178,7 @@ mod tests {
                 temperature: None,
                 top_p: None,
                 api_backend: Default::default(),
+                chat_compat: Default::default(),
                 extra_headers: Default::default(),
                 context_window: NonZeroU64::new(128_000).unwrap(),
                 reasoning_effort: None,
@@ -221,6 +222,7 @@ mod tests {
                 temperature: Some(0.7),
                 top_p: None,
                 api_backend: Default::default(),
+                chat_compat: Default::default(),
                 extra_headers: Default::default(),
                 context_window: NonZeroU64::new(128_000).unwrap(),
                 reasoning_effort: None,