feat: agent run loop, Generate[T], reflect-derived schemas

Phase 5:
- agent/: model + system prompt + toolboxes composition; bounded
  tool-dispatch loop (default 10 steps); panic-proof tool execution;
  unknown-tool and duplicate-name handling; history continuation; step
  observers; partial results on ErrMaxSteps/errors (ADR-0012)
- llm.SchemaFor[T]: strict-compatible JSON schemas from Go types
  (nullable pointers, description/enum tags, recursion rejected)
- majordomo.Generate[T]: typed structured output with fence-stripping
  decode and model-naming errors
- README agents/structured-output sections + matrix synced

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

docs/adr/0012-agent-loop.md

@@ -0,0 +1,53 @@
+# ADR-0012: Agent run loop
+
+**Status:** Accepted — 2026-06-10
+
+## Context
+
+Agents are the consumer-facing composition: Model + system prompt +
+toolboxes (+ skills), run as a tool-dispatch loop. mort's agents need
+multi-step tool use, bounded loops, per-step observation (tracing/usage
+recording), conversation continuation, and a loop that survives every tool
+failure.
+
+## Decision
+
+- `agent.New(model, system, opts...)` with options WithToolbox, WithTools,
+  WithSkill, WithMaxSteps (default 10), WithRequestOptions (per-step
+  generation knobs), WithStepObserver. `AddSkill`/`AddToolbox` extend an
+  agent after construction (configure-then-share concurrency contract).
+- `Run(ctx, input, opts...)`: history seeds via WithHistory (a previous
+  `Result.Messages` round-trips), per-run request options, per-run OnStep
+  callbacks. The loop: Generate with the merged toolset → no tool calls =
+  final answer → otherwise execute calls sequentially, append the
+  assistant turn + one RoleTool message, repeat.
+- **Never panics, never stalls on tool failure:** handlers run through
+  `llm.ExecuteTool` (panic-recovering, errors → IsError results); unknown
+  tool names come back as IsError results the model can react to; observer
+  panics are swallowed. Only model errors (already retried/failed-over by
+  the chain) and ctx cancellation abort the run — and even then the
+  partial `Result` (transcript, steps, usage) is returned alongside the
+  error, as it is on ErrMaxSteps.
+- **Duplicate tool names across toolboxes/skills fail loudly at Run** —
+  a silently shadowed tool is a debugging trap.
+- Skills compose additively (the `agent.Skill` interface lives in this
+  package so agent does not import skill): `Instructions()` append to the
+  system prompt in attachment order; `Tools()` join the merged toolset.
+- **Intermediate-step streaming = step observers** (agent-level and
+  per-run), invoked synchronously after every step with the response and
+  tool results. Token-level streaming inside the loop was deliberately
+  deferred: tool-heavy steps end on buffered tool calls anyway, and mort's
+  observers (trace/usage recorders) want completed steps. `Model.Stream`
+  remains available for direct streaming outside the loop.
+- `Generate[T]` + `llm.SchemaFor[T]` give typed structured output:
+  reflect-derived schemas (strict-compatible: all properties required,
+  additionalProperties:false, pointers → nullable anyOf), markdown-fence
+  stripping as a decode fallback, errors that name the serving model.
+
+## Consequences
+
+- An agent over a failover chain inherits retry/backoff/media
+  normalization transparently — no agent-level error handling for
+  transient provider trouble.
+- Sequential tool execution is deterministic and trace-friendly; parallel
+  dispatch can be added later behind an option without API change.

docs/adr/README.md

@@ -15,3 +15,4 @@ One decision per file, append-only; supersede rather than rewrite.
 | [0009](0009-multimodal-strategy.md) | Multimodal strategy — normalize per target, enforce at provider | Accepted |
 | [0010](0010-tools-structured-output-mapping.md) | Tools and structured output — canonical shape, native mappings | Accepted |
 | [0011](0011-google-provider.md) | Google provider on the official Gen AI SDK | Accepted |
+| [0012](0012-agent-loop.md) | Agent run loop | Accepted |