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-shell/src/session/acp_session_impl/model_switch.rs

@@ -53,6 +53,7 @@ impl SessionActor {
                 temperature: sampling_config.temperature,
                 top_p: sampling_config.top_p,
                 api_backend: sampling_config.api_backend.clone(),
+                chat_compat: sampling_config.chat_compat,
                 extra_headers: sampling_config.extra_headers.clone(),
                 context_window: new_context_window,
                 reasoning_effort: sampling_config.reasoning_effort,

crates/codegen/kigi-shell/src/session/acp_session_impl/sampler_turn.rs

@@ -260,6 +260,7 @@ impl SessionActor {
                 temperature: None,
                 top_p: None,
                 api_backend: Default::default(),
+                chat_compat: Default::default(),
                 extra_headers: Default::default(),
                 context_window: std::num::NonZeroU64::new(256_000).unwrap(),
                 reasoning_effort: None,
@@ -312,6 +313,7 @@ impl SessionActor {
             top_p: cfg.top_p,
             api_backend: cfg.api_backend,
             auth_scheme,
+            chat_compat: cfg.chat_compat,
             extra_headers,
             context_window: cfg.context_window.get(),
             reasoning_effort: cfg.reasoning_effort,

crates/codegen/kigi-shell/src/session/acp_session_impl/spawn.rs

@@ -346,6 +346,7 @@ pub(crate) async fn spawn_session_actor(
         temperature: sampling_config.temperature,
         top_p: sampling_config.top_p,
         api_backend: sampling_config.api_backend.clone(),
+        chat_compat: sampling_config.chat_compat,
         extra_headers: sampling_config.extra_headers.clone(),
         context_window: context_window_override.unwrap_or(baseline_context_window),
         reasoning_effort: sampling_config.reasoning_effort,