feat: add dynamic template variables to messages.responsePrefix (#923)

Adds support for template variables in `messages.responsePrefix` that
resolve dynamically at runtime with the actual model used (including
after fallback).

Supported variables (case-insensitive):
- {model} - short model name (e.g., "claude-opus-4-5", "gpt-4o")
- {modelFull} - full model identifier (e.g., "anthropic/claude-opus-4-5")
- {provider} - provider name (e.g., "anthropic", "openai")
- {thinkingLevel} or {think} - thinking level ("high", "low", "off")
- {identity.name} or {identityName} - agent identity name

Example: "[{model} | think:{thinkingLevel}]" → "[claude-opus-4-5 | think:high]"

Variables show the actual model used after fallback, not the intended
model. Unresolved variables remain as literal text.

Implementation:
- New module: src/auto-reply/reply/response-prefix-template.ts
- Template interpolation in normalize-reply.ts via context provider
- onModelSelected callback in agent-runner-execution.ts
- Updated all 6 provider message handlers (web, signal, discord,
  telegram, slack, imessage)
- 27 unit tests covering all variables and edge cases
- Documentation in docs/gateway/configuration.md and JSDoc

Fixes #923

src/auto-reply/reply/reply-dispatcher.ts

@@ -1,6 +1,7 @@
 import type { HumanDelayConfig } from "../../config/types.js";
 import type { GetReplyOptions, ReplyPayload } from "../types.js";
 import { normalizeReplyPayload } from "./normalize-reply.js";
+import type { ResponsePrefixContext } from "./response-prefix-template.js";
 import type { TypingController } from "./typing.js";
 
 export type ReplyDispatchKind = "tool" | "block" | "final";
@@ -33,6 +34,11 @@ const sleep = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));
 export type ReplyDispatcherOptions = {
   deliver: ReplyDispatchDeliverer;
   responsePrefix?: string;
+  /** Static context for response prefix template interpolation. */
+  responsePrefixContext?: ResponsePrefixContext;
+  /** Dynamic context provider for response prefix template interpolation.
+   * Called at normalization time, after model selection is complete. */
+  responsePrefixContextProvider?: () => ResponsePrefixContext;
   onHeartbeatStrip?: () => void;
   onIdle?: () => void;
   onError?: ReplyDispatchErrorHandler;
@@ -61,10 +67,17 @@ export type ReplyDispatcher = {
 
 function normalizeReplyPayloadInternal(
   payload: ReplyPayload,
-  opts: Pick<ReplyDispatcherOptions, "responsePrefix" | "onHeartbeatStrip">,
+  opts: Pick<
+    ReplyDispatcherOptions,
+    "responsePrefix" | "responsePrefixContext" | "responsePrefixContextProvider" | "onHeartbeatStrip"
+  >,
 ): ReplyPayload | null {
+  // Prefer dynamic context provider over static context
+  const prefixContext = opts.responsePrefixContextProvider?.() ?? opts.responsePrefixContext;
+
   return normalizeReplyPayload(payload, {
     responsePrefix: opts.responsePrefix,
+    responsePrefixContext: prefixContext,
     onHeartbeatStrip: opts.onHeartbeatStrip,
   });
 }