[proxy] LLM parsers, pricing, and builtin middlewares (OpenAI, Anthropic, Vertex AI, AWS Bedrock)

Request/response parsers and SSE/event-stream metering, the embedded pricing
table, and the builtin middleware set: request parser, router, policy
limit-check/record, cost meter, guardrail, identity inject, response parser.
Includes the path-routed providers — Google Vertex AI (keyfile:: service-account
OAuth minting) and AWS Bedrock (bearer auth, invoke/converse/streaming, optional
/bedrock prefix) — plus the Models allowlist and unmeterable-publisher deny.

proxy/internal/llm/fixtures/anthropic_messages.json

@@ -0,0 +1,17 @@
+{
+  "id": "msg_abc",
+  "type": "message",
+  "role": "assistant",
+  "model": "claude-sonnet-4-5",
+  "content": [
+    {
+      "type": "text",
+      "text": "Hello, world!"
+    }
+  ],
+  "stop_reason": "end_turn",
+  "usage": {
+    "input_tokens": 123,
+    "output_tokens": 45
+  }
+}

proxy/internal/llm/fixtures/anthropic_stream.txt

@@ -0,0 +1,21 @@
+event: message_start
+data: {"type":"message_start","message":{"id":"msg_abc","type":"message","role":"assistant","model":"claude-sonnet-4-5","content":[],"stop_reason":null,"usage":{"input_tokens":123,"output_tokens":1}}}
+
+event: content_block_start
+data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}
+
+event: content_block_delta
+data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello"}}
+
+event: content_block_delta
+data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":", world!"}}
+
+event: content_block_stop
+data: {"type":"content_block_stop","index":0}
+
+event: message_delta
+data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"output_tokens":45}}
+
+event: message_stop
+data: {"type":"message_stop"}
+

proxy/internal/llm/fixtures/openai_chat_completion.json

@@ -0,0 +1,21 @@
+{
+  "id": "chatcmpl-abc",
+  "object": "chat.completion",
+  "created": 1700000000,
+  "model": "gpt-4o-mini",
+  "choices": [
+    {
+      "index": 0,
+      "message": {
+        "role": "assistant",
+        "content": "Hello, world!"
+      },
+      "finish_reason": "stop"
+    }
+  ],
+  "usage": {
+    "prompt_tokens": 123,
+    "completion_tokens": 45,
+    "total_tokens": 168
+  }
+}

proxy/internal/llm/fixtures/openai_responses.json

@@ -0,0 +1,24 @@
+{
+  "id": "resp_abc",
+  "object": "response",
+  "created_at": 1700000000,
+  "model": "gpt-5.4",
+  "output": [
+    {
+      "type": "message",
+      "role": "assistant",
+      "content": [{"type": "output_text", "text": "ok"}]
+    }
+  ],
+  "usage": {
+    "input_tokens": 15,
+    "input_tokens_details": {
+      "cached_tokens": 0
+    },
+    "output_tokens": 414,
+    "output_tokens_details": {
+      "reasoning_tokens": 0
+    },
+    "total_tokens": 429
+  }
+}

proxy/internal/llm/fixtures/openai_responses_stream.txt

@@ -0,0 +1,24 @@
+event: response.created
+data: {"type":"response.created","response":{"id":"resp_abc","object":"response","model":"gpt-5.5","usage":null}}
+
+event: response.in_progress
+data: {"type":"response.in_progress","response":{"id":"resp_abc","usage":null}}
+
+event: response.output_item.added
+data: {"type":"response.output_item.added","output_index":0,"item":{"type":"message","role":"assistant","content":[]}}
+
+event: response.content_part.added
+data: {"type":"response.content_part.added","item_id":"msg_1","output_index":0,"content_index":0,"part":{"type":"output_text","text":""}}
+
+event: response.output_text.delta
+data: {"type":"response.output_text.delta","item_id":"msg_1","output_index":0,"content_index":0,"delta":"Hello"}
+
+event: response.output_text.delta
+data: {"type":"response.output_text.delta","item_id":"msg_1","output_index":0,"content_index":0,"delta":", world!"}
+
+event: response.output_text.done
+data: {"type":"response.output_text.done","item_id":"msg_1","output_index":0,"content_index":0,"text":"Hello, world!"}
+
+event: response.completed
+data: {"type":"response.completed","response":{"id":"resp_abc","object":"response","model":"gpt-5.5","usage":{"input_tokens":123,"input_tokens_details":{"cached_tokens":40},"output_tokens":45,"output_tokens_details":{"reasoning_tokens":12},"total_tokens":168}}}
+

proxy/internal/llm/fixtures/openai_stream.txt

@@ -0,0 +1,8 @@
+data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1700000000,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null}]}
+
+data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1700000000,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{"content":", world!"},"finish_reason":null}]}
+
+data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1700000000,"model":"gpt-4o-mini","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":123,"completion_tokens":45,"total_tokens":168}}
+
+data: [DONE]
+

proxy/internal/llm/fixtures/pricing.yaml

@@ -0,0 +1,59 @@
+# Realistic-pricing starter for llm_observability. Drop this into the
+# directory you point the proxy at via --plugin-data-dir, then reference it
+# from the target's plugin config:
+#
+#   plugins:
+#     - id: llm_observability
+#       enabled: true
+#       params:
+#         pricing_path: pricing.yaml
+#
+# Values are USD per 1_000 tokens. Public list prices drift; treat this as a
+# starting point and keep your production copy current.
+
+openai:
+  # GPT-5 family
+  gpt-5:
+    input_per_1k: 0.00125
+    output_per_1k: 0.01
+  gpt-5-mini:
+    input_per_1k: 0.00025
+    output_per_1k: 0.002
+  gpt-5-nano:
+    input_per_1k: 0.00005
+    output_per_1k: 0.0004
+  gpt-5.4:
+    input_per_1k: 0.00125
+    output_per_1k: 0.01
+  # GPT-4o family
+  gpt-4o:
+    input_per_1k: 0.0025
+    output_per_1k: 0.01
+  gpt-4o-mini:
+    input_per_1k: 0.00015
+    output_per_1k: 0.0006
+  # Embeddings
+  text-embedding-3-large:
+    input_per_1k: 0.00013
+    output_per_1k: 0
+  text-embedding-3-small:
+    input_per_1k: 0.00002
+    output_per_1k: 0
+
+anthropic:
+  # Claude 4.x family
+  claude-opus-4-7:
+    input_per_1k: 0.015
+    output_per_1k: 0.075
+  claude-sonnet-4-7:
+    input_per_1k: 0.003
+    output_per_1k: 0.015
+  claude-sonnet-4-6:
+    input_per_1k: 0.003
+    output_per_1k: 0.015
+  claude-sonnet-4-5:
+    input_per_1k: 0.003
+    output_per_1k: 0.015
+  claude-haiku-4-5:
+    input_per_1k: 0.0008
+    output_per_1k: 0.004