[instructions] Sync instruction files with release v0.79.8

.github/aw/experiments.md

@@ -64,8 +64,8 @@ experiments:
     variants: [concise, detailed, step_by_step]
     weight: [2, 1, 1]           # 50% concise, 25% detailed, 25% step_by_step
     description: "Verbosity A/B test"
-    metric: "effective_tokens"
-    hypothesis: "H0: no change in effective_tokens. H1: concise reduces by >=15%"
+    metric: "ai_credits"
+    hypothesis: "H0: no change in ai_credits. H1: concise reduces by >=15%"
     guardrail_metrics:
       - name: success_rate
         threshold: ">=0.95"

.github/aw/syntax-agentic.md

@@ -25,10 +25,8 @@ description: Agentic workflow specific frontmatter fields for GitHub Agentic Wor
   - Bot must be active (installed) on repository to trigger workflow
 - **`strict:`** - Enable enhanced validation for production workflows (boolean, defaults to `true`)
   - Must be `true`
-- **`max-runs:`** - Maximum number of LLM invocations allowed per workflow run (integer or numeric string, minimum: 1)
-  - Top-level field mapped to `apiProxy.maxRuns`
-  - Supported by all engines
 - **`max-turns:`** - AWF turn cap applied consistently across all agentic engines (integer or expression, e.g. `${{ inputs.max-turns }}`). The engine-level `engine.max-turns` is a deprecated alias kept for backward compatibility — prefer this top-level field. Not supported by the `gemini` engine.
+- **`max-runs:`** - Deprecated legacy alias for the AWF invocation cap (`apiProxy.maxRuns`, defaults to `500` when omitted). Use `max-turns` instead; run `gh aw fix` to migrate.
 - **`max-ai-credits:`** - Per-run AI Credits (AIC) budget enforced by the AWF firewall (integer or `K`/`M` short-form string like `100M`; default `1000`). Set a negative value to disable enforcement and token steering. See [token-optimization.md](token-optimization.md).
 - **`max-daily-ai-credits:`** - Per-user 24-hour AI Credits (AIC) guardrail: activation blocks execution once the triggering user's aggregated AI Credits for this workflow over the last 24h exceed the threshold (integer or `K`/`M` short-form string, or `-1`). Enabled by default with a system default threshold; set `-1` to disable or an explicit value to override. See [token-optimization.md](token-optimization.md).
 - **`user-rate-limit:`** - Rate limiting configuration to prevent users from triggering the workflow too frequently (object)

.github/aw/token-optimization.md

@@ -409,6 +409,8 @@ max-ai-credits: 100M        # per-run cap (short-form string)
 max-daily-ai-credits: 500M  # per-user 24h cap; -1 disables
 ```
 
+For custom or private models, the top-level **`models:`** frontmatter field supplies pricing in the same structure as `models.json` (keyed `providers.<provider>.models.<model>.cost` with `input`/`output`/`cache_read`/`cache_write` per-token costs). Entries are merged with the built-in `models.json` at runtime — they override matching models and fill gaps for unknown ones — so AI Credit accounting stays accurate for models gh-aw does not price by default.
+
 ---
 
 ## Additional Resources