fix(anthropic): merge parallel tool results, ordinal stream tool indices, array system content, strict stream decode

Review round 1 fixes (1 Critical + 5 Important) on the anthropic
adapter/translator.

- CRITICAL: consecutive role:"tool" messages each became their own
  Anthropic user turn. Anthropic requires alternating user/assistant
  turns and 400s on two consecutive same-role messages; parallel tool
  calls (one assistant message with N tool_calls followed by N
  role:"tool" messages) are the standard agentic transcript shape.
  anthropicRequestFromOpenAI now accumulates consecutive tool messages
  into one Anthropic user turn carrying all of their tool_result
  blocks (anthropicToolResultBlock replaces anthropicToolResultMessage).
  Added chat_parallel_tool_results fixture.
- Streaming tool_calls[].index passed Anthropic's raw content-block
  index through, so a tool_use block after a text block emitted
  index:1 instead of the required contiguous 0-based ordinal.
  anthropicStreamState now tracks a per-stream tool-call ordinal
  counter plus a content-block-index -> ordinal map, populated on
  content_block_start and consulted on input_json_delta. Added the
  stream_text_then_tool fixture (text block at index 0, tool_use at
  index 1) proving the emitted index is 0.
- A system message with array-form content ([{"type":"text",...}])
  was silently dropped (only a string content was handled). Added
  systemTextFromContentParts: text parts join with "\n"; a non-text
  part returns a *translateError instead of being dropped. Added
  chat_system_array_content (success) and
  chat_system_array_content_error fixtures.
- Malformed JSON on a recognized stream event (message_start,
  content_block_start, content_block_delta, message_delta) was
  swallowed as (nil, nil), which could silently corrupt a client's
  reassembled tool-call arguments. All four now return an error
  wrapping errUpstream; forwardStream already propagates that and
  withholds the terminal [DONE]. The unrecognized-event-type and
  error-event branches are unchanged. Added
  TestAnthropicStreamState_MalformedEventReturnsError.
- providerAdapter.injectAuth's doc comment claimed a universal
  empty-key no-op; updated to state the per-type divergence
  (openai-type: keyless is a no-op; anthropic-type: the constructor
  rejects an empty key, so injectAuth is never called with one).
- Added case-insensitive-Content-Type coverage for both adapters'
  streaming-vs-JSON gate (previously untested): one subtest each in
  provider_openai_test.go / provider_anthropic_test.go using a fake
  upstream that sends "Text/Event-Stream; charset=utf-8", asserting
  the streaming path (not the JSON fallback) is taken.

Gate: go test ./... -count=1 and -race both green; gofmt, go vet,
fieldalignment, golangci-lint (incl. gosec), govulncheck all clean.

providers.go

@@ -91,8 +91,12 @@ type providerAdapter interface {
 	// trimmed.
 	base() string
 	// injectAuth sets whatever headers r needs to authenticate against the
-	// provider. It is a no-op when the provider's resolved API key is
-	// empty — a keyless upstream is a valid configuration, not an error.
+	// provider. Behavior is type-specific: an openai-type adapter treats
+	// a resolved-empty API key as a valid keyless upstream, so injectAuth
+	// is a no-op in that case. An anthropic-type adapter's constructor
+	// rejects an empty key outright (ruling c), so its injectAuth always
+	// sets auth headers — there is no keyless case for it to be a no-op
+	// over.
 	injectAuth(r *http.Request)
 	// chatCompletion proxies req to the provider's chat completions
 	// endpoint and writes the (possibly streamed) response to w. req has