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>

README.md

@@ -200,13 +200,46 @@ resp, _ := m.Generate(ctx, req, majordomo.WithSchema(schemaJSON, "answer"))
 ```
 
 Maps to OpenAI `response_format: json_schema`, Anthropic
-`output_config.format`, and Ollama `format`. A generic `Generate[T]` helper
-(schema from your struct, unmarshal into it) lands with the agent phase.
+`output_config.format`, Ollama `format`, and Google `responseJsonSchema`.
 
-## Agents & skills *(pending — Phases 5–6)*
+The typed helper derives the schema from your struct (all fields required,
+`additionalProperties:false`, pointers nullable; `description:"..."` and
+`enum:"a,b,c"` tags supported) and unmarshals the result:
 
-Agents = model + system prompt + toolboxes, running a tool-dispatch loop;
-skills = reusable instruction+tool bundles attachable to any agent.
+```go
+type Verdict struct {
+    Guilty bool   `json:"guilty"`
+    Why    string `json:"why" description:"one-sentence rationale"`
+}
+v, err := majordomo.Generate[Verdict](ctx, m, req)
+```
+
+## Agents
+
+An agent is a model + system prompt + toolboxes, run as a tool-dispatch
+loop until the model answers (or `MaxSteps`):
+
+```go
+import "gitea.stevedudenhoeffer.com/steve/majordomo/agent"
+
+a := agent.New(m, "You are a research assistant.",
+    agent.WithToolbox(searchTools),
+    agent.WithMaxSteps(8),
+    agent.WithStepObserver(func(s agent.Step) { log.Printf("step %d", s.Index) }),
+)
+res, err := a.Run(ctx, "What changed in Go 1.26?")
+// res.Output, res.Steps, res.Usage; res.Messages round-trips via
+// agent.WithHistory for conversation continuation.
+```
+
+The loop never panics: tool handler errors and panics become error results
+the model can react to; unknown tools likewise; duplicate tool names across
+toolboxes fail loudly. On `agent.ErrMaxSteps` (and on model errors) the
+partial result with the full transcript is still returned.
+
+## Skills *(pending — Phase 6)*
+
+Skills = reusable instruction+tool bundles attachable to any agent.
 
 ## Feature/provider support matrix
 
@@ -229,8 +262,8 @@ Notes: Ollama has no native tool_choice — `"none"` drops the tools;
 
 Cross-cutting: Parse grammar ✅ · aliases/tiers ✅ · failover chains ✅ ·
 health tracking/backoff ✅ · LLM_* env DSNs ✅ · media pipeline ✅
-(per-target normalization in chains) · agent loop pending · skills pending
-· `Generate[T]` pending.
+(per-target normalization in chains) · agent loop ✅ · `Generate[T]` +
+schema derivation ✅ · skills pending.
 
 ## Development