F5: web search/fetch on the Kimi services (kimi-cli parity)

web_search now speaks the Kimi search service (kimi-cli tools/web/search.py,
wire-verified against api.kimi.com):
- POST {coding_base}/search with {text_query, limit 1-20 (default 5),
  enable_page_crawling, timeout_seconds: 30}, OAuth bearer +
  X-Msh-Tool-Call-Id; results render in kimi-cli's Title/Date/URL/Summary
  schema with result URLs as citations.
- The old implementation called the xAI Responses API with a search model;
  that client is fully replaced and the entire model-based config surface
  is excised root-and-branch: web_search_model config keys/env/CLI plumbing,
  resolve_web_search_sampling_config, toolset web_search SamplerConfig,
  RemoteSettings.web_search_model, default_web_search_model.
- Enablement is now purely structural: the service exists only on the Kimi
  Code subscription channel, so OAuth sessions get Enabled and API-key-only
  sessions get Disabled (tool absent) — per PRD F5.

web_fetch gains the Kimi fetch service as its primary path (kimi-cli
tools/web/fetch.py): POST {coding_base}/fetch with {url}, Accept:
text/markdown, OAuth bearer + X-Msh-Tool-Call-Id; the 200 body is the
extracted markdown (still overflow-budgeted). Any service failure falls
back to the existing local pipeline (SSRF guards, cache, extraction).
The tool gate defaults ON now (kimi-cli always offers FetchURL) and the
egress User-Agent no longer claims grok-agent/x.ai.

Verified end-to-end against the scripted mock service: a headless session
drove web_search (limit/crawling/call-id observed on the wire) then
web_fetch (Accept + call-id observed) to completion.

crates/codegen/kigi-tui/src/acp/mod.rs

@@ -159,7 +159,6 @@ pub async fn connect(cancel: &CancellationToken, flags: ConnectFlags) -> Result<
         cwd: None,
         is_headless: false,
         cli_subagents: Some(flags.subagents),
-        cli_web_search_model: None,
         cli_session_summary_model: None,
         cli_experimental_memory: flags.experimental_memory,
         cli_no_memory: flags.no_memory,

crates/codegen/kigi-tui/src/app/dispatch/settings/setters.rs

@@ -1730,9 +1730,9 @@ pub(in crate::app::dispatch) fn clear_fork_secondary_model(app: &mut AppView) ->
     }]
 }
 
-// `web_search_model`, `session_summary_model`, and
-// `default_reasoning_effort` setters were removed alongside their
-// registry entries. Mirror fields and TOML schema stay for compat.
+// `session_summary_model` and `default_reasoning_effort` setters were
+// removed alongside their registry entries. Mirror fields and TOML
+// schema stay for compat.
 
 // ---------------------------------------------------------------------------
 // max_thoughts_width — Int-valued setting. Registry surface is `i64`;

crates/codegen/kigi-tui/src/views/settings_modal.rs

@@ -5668,9 +5668,8 @@ mod tests {
                 "plan_mode",
                 // SHELL-owned default_model (Models category).
                 "default_model",
-                // Models category. `default_reasoning_effort`,
-                // `web_search_model`, and `session_summary_model` are
-                // not exposed in the modal.
+                // Models category. `default_reasoning_effort` and
+                // `session_summary_model` are not exposed in the modal.
                 "fork_secondary_model",
                 // `auto_compact_threshold_percent` (Session category) is
                 // not exposed in the modal.