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/agent-runner-execution.ts

@@ -125,6 +125,14 @@ export async function runAgentTurnWithFallback(params: {
           resolveAgentIdFromSessionKey(params.followupRun.run.sessionKey),
         ),
         run: (provider, model) => {
+          // Notify that model selection is complete (including after fallback).
+          // This allows responsePrefix template interpolation with the actual model.
+          params.opts?.onModelSelected?.({
+            provider,
+            model,
+            thinkLevel: params.followupRun.run.thinkLevel,
+          });
+
           if (isCliProvider(provider, params.followupRun.run.config)) {
             const startedAt = Date.now();
             emitAgentEvent({