feat: conversion-driven extensions — resolvers, DefineTool, hooks, ops controls

Phase 9a (ADR-0014): Registry.RegisterResolver for dynamic tiers;
DefineTool[Args] typed tools; Usage cache/reasoning detail fields wired
through anthropic/openai/google; WithPromptCaching (Anthropic
cache_control); agent supervision hooks (WithMaxStepsFunc, WithSteer,
WithCompactor, WithToolErrorLimits + ErrToolLoop); health
Bench/Unbench/Snapshot; ChainConfig.Observer failover events.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

docs/adr/0014-conversion-driven-extensions.md

@@ -0,0 +1,50 @@
+# ADR-0014: Conversion-driven extensions (resolvers, typed tools, hooks, ops controls)
+
+**Status:** Accepted — 2026-06-10
+
+## Context
+
+Executing the mort conversion (docs/mort-migration.md) surfaced seven
+capabilities mort's orchestration layer needs from its model substrate.
+Each is general-purpose — none encodes anything mort-specific — and each
+was promised in the migration blueprint.
+
+## Decision
+
+1. **`Registry.RegisterResolver`** — dynamic alias resolution for DB/
+   config-backed tiers. Checked after static aliases (static wins), in
+   registration order, without holding the registry lock (resolvers do
+   I/O); output expands recursively under the existing cycle guard.
+2. **`DefineTool[Args]`** — typed tools: parameters from `SchemaFor[Args]`,
+   arguments unmarshaled before the handler. Schema failure panics
+   (startup-time programming error, mirroring NewToolbox).
+3. **`Usage` detail fields** — CacheReadTokens / CacheWriteTokens /
+   ReasoningTokens, populated where providers report them (Anthropic cache
+   fields; OpenAI prompt/completion detail objects; Google cached-content
+   + thoughts). Input/Output remain totals; details are portions.
+4. **`WithPromptCaching`** — Anthropic top-level `cache_control`
+   auto-placement; a no-op for providers that cache implicitly or not at
+   all.
+5. **Agent loop hooks** — `WithMaxStepsFunc` (dynamic ceiling, consulted
+   every step, for supervisor budget adjustment), `WithSteer` (per-run
+   message injection drained before each step), `WithCompactor`
+   (pre-Generate transcript transformation; errors fall back to the
+   original — losing a request to a broken summarizer is worse than a long
+   prompt), `WithToolErrorLimits` (consecutive all-error steps and
+   identical-call repeats end the run with `ErrToolLoop` + partial result).
+   The canonical transcript in `Result.Messages` is always the
+   uncompacted truth; compaction affects only what is sent.
+6. **Manual health controls** — `Tracker.Bench/Unbench/Snapshot` for
+   ops surfaces (".failover bench" commands, dashboards).
+7. **`ChainConfig.Observer`** — one synchronous callback per failover
+   decision (failed attempt with classification, bench, benched-skip).
+   This is a hook, not an observability stack; persistence/metrics remain
+   the consumer's business (anti-creep guardrail intact).
+
+## Consequences
+
+- mort's tier resolver, `.failover` admin surface, failover-event log,
+  run-critic budget control, steering, and compaction all rebase onto
+  public API.
+- The agent loop gains supervision points without changing its
+  never-panic, partial-result-on-error contract.

docs/adr/README.md

@@ -17,3 +17,4 @@ One decision per file, append-only; supersede rather than rewrite.
 | [0011](0011-google-provider.md) | Google provider on the official Gen AI SDK | Accepted |
 | [0012](0012-agent-loop.md) | Agent run loop | Accepted |
 | [0013](0013-skill-model.md) | Skill model — additive instruction+tool bundles | Accepted |
+| [0014](0014-conversion-driven-extensions.md) | Conversion-driven extensions (resolvers, typed tools, hooks, ops controls) | Accepted |