feat(provider): add native Anthropic Messages API adapter (Phase 2)

Adds internal/provider/anthropic, the first genuinely new provider.Provider
implementation on top of Phase 1's provider-neutral tool-use loop, alongside
(not replacing) the existing Docker/CLI-subprocess ContainerRunner path for
the "claude" agent type:

- internal/provider/anthropic: translates the neutral ChatRequest/ChatResponse
  shape to/from Anthropic's Messages API content-block format (system as a
  top-level field, tool_use/tool_result blocks, no "tool" role -- tool
  results become user-role messages), with a per-model-prefix pricing table
  for CostUSD
- internal/retry: IsRateLimitError additively extended to recognize
  Anthropic's rate_limit_error/overloaded_error/529 shapes
- internal/config: RunnersConfig.Anthropic/AnthropicEnabled() gate
- internal/cli/serve.go, run.go: register runners["anthropic"] as a
  NativeRunner when [providers.anthropic].api_key is set and enabled --
  tracked as a distinct executions.agent="anthropic" budget bucket, separate
  from the CLI-subprocess "claude" runner even though both bill the same
  Anthropic account

go build/vet/test -race all pass. No live Anthropic API key is available in
this environment, so verification is via fake-httptest-server adapter tests
(12 cases, incl. multi-turn tool_result round-trip and rate-limit error
matching) plus a Pool/NativeRunner routing test proving agent.type:
"anthropic" actually reaches the new provider. Live end-to-end verification
against the real API is a follow-up once a key is configured.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V1moSNCJRcP6kykA4tyUSs

1 files changed, 22 insertions, 11 deletions

diff --git a/internal/config/config.go b/internal/config/config.go
index 640e933..de087d6 100644
--- a/internal/config/config.go
+++ b/internal/config/config.go
@@ -25,12 +25,12 @@ type Project struct {
 // uses this client. It defaults to true when Endpoint is set; users with a
 // slow or low-quality local model can disable it.
 type LocalModel struct {
-	Endpoint           string  `toml:"endpoint"`              // e.g. "http://localhost:11434/v1"
-	Model              string  `toml:"model"`                 // e.g. "llama3.1:8b"
-	TimeoutSeconds     int     `toml:"timeout_seconds"`       // default 60
-	DefaultTemperature float64 `toml:"default_temperature"`   // default 0.2
-	APIKey             string  `toml:"api_key"`               // optional bearer token
-	PreferForElaborate *bool   `toml:"prefer_for_elaborate"`  // pointer so default-true survives parse
+	Endpoint           string  `toml:"endpoint"`             // e.g. "http://localhost:11434/v1"
+	Model              string  `toml:"model"`                // e.g. "llama3.1:8b"
+	TimeoutSeconds     int     `toml:"timeout_seconds"`      // default 60
+	DefaultTemperature float64 `toml:"default_temperature"`  // default 0.2
+	APIKey             string  `toml:"api_key"`              // optional bearer token
+	PreferForElaborate *bool   `toml:"prefer_for_elaborate"` // pointer so default-true survives parse
 }
 
 // UseForElaborate returns true when elaboration should try this local model
@@ -56,20 +56,31 @@ type RunnersConfig struct {
 	Gemini    *bool `toml:"gemini"`
 	Local     *bool `toml:"local"`
 	Container *bool `toml:"container"`
+	// Anthropic gates the native provider.Provider-backed NativeRunner
+	// registered under agent type "anthropic" (internal/provider/anthropic).
+	// It is distinct from Claude, which gates the Docker/CLI-subprocess
+	// ContainerRunner for agent type "claude" — the two are separate
+	// execution paths (and separate budget buckets) even though both bill
+	// the same Anthropic account. Also requires [providers.anthropic].api_key
+	// to be set; Anthropic = true with no configured key has no effect.
+	Anthropic *bool `toml:"anthropic"`
 }
 
 func (r RunnersConfig) ClaudeEnabled() bool    { return r.Claude == nil || *r.Claude }
 func (r RunnersConfig) GeminiEnabled() bool    { return r.Gemini == nil || *r.Gemini }
 func (r RunnersConfig) LocalEnabled() bool     { return r.Local == nil || *r.Local }
 func (r RunnersConfig) ContainerEnabled() bool { return r.Container == nil || *r.Container }
+func (r RunnersConfig) AnthropicEnabled() bool { return r.Anthropic == nil || *r.Anthropic }
 
 // ProviderConfig configures a native (or OpenAI-compatible) LLM provider
 // backend for the multi-provider harness — see docs/api-keys-setup.md. Phase
-// 1 only adds this type so config has somewhere for it to land; it is not yet
-// read by runner construction (no native provider adapters exist yet besides
-// the openaicompat one LocalModel already configures). Keyed by provider name
-// in the [providers.<name>] TOML table, e.g. [providers.groq],
-// [providers.anthropic].
+// 1 added this type so config had somewhere for it to land, without being
+// read by runner construction. Phase 2 is the first consumer:
+// [providers.anthropic] (APIKey + optional Endpoint/DefaultModel/
+// TimeoutSeconds) wires internal/provider/anthropic.New into a NativeRunner
+// registered under agent type "anthropic" — see internal/cli/serve.go and
+// internal/cli/run.go. Keyed by provider name in the [providers.<name>] TOML
+// table, e.g. [providers.groq], [providers.anthropic].
 type ProviderConfig struct {
 	Endpoint       string `toml:"endpoint"`
 	APIKey         string `toml:"api_key"`