@tokenlabai/mcp-server 0.6.26 → 0.6.28

package/README.md

@@ -10,7 +10,7 @@ It exposes public catalog tools for agents that need to choose models, inspect s
 
 ## Generated Tool Profiles
 
-The checked-in `generated/tools.json` manifest is generated from TokenLab's public OpenAPI document plus the small MCP-only overlay in `contract/mcp-overlay.json`. Version 0.6.26 generates 87 endpoint tools; with the two MCP-only composite discovery tools, the full profile returns 89 tools from `tools/list`.
+The checked-in `generated/tools.json` manifest is generated from TokenLab's public OpenAPI document plus the small MCP-only overlay in `contract/mcp-overlay.json`. Version 0.6.28 generates 87 endpoint tools; with the two MCP-only composite discovery tools, the full profile returns 89 tools from `tools/list`.
 
 | Profile | Endpoint tools | Total registered tools | Model-facing schema | Coverage |
 | --- | ---: | ---: | --- | --- |
@@ -18,9 +18,9 @@ The checked-in `generated/tools.json` manifest is generated from TokenLab's publ
 | `core` (default) | 30 | 32 | Portable | Catalog and pricing; Chat Completions, Responses, Anthropic Messages, Gemini generateContent; System One typed decisions; images, video, music, 3D, speech and transcription; async tasks; files; embeddings, rerank, and translation |
 | `full` | 87 | 89 | Portable | Every allowlisted developer API operation in the checked-in OpenAPI snapshot, including core plus response lifecycle, batches, worlds, and native model discovery |
 
-The total registered count is the number returned by `tools/list`. All profiles include `compare_models` and `get_api_overview`, producing totals of 6, 32, and 89 tools. Realtime and streaming-only operations are excluded because stdio MCP tool calls return one final result. API operations that accept `stream` fix it internally to `false` without exposing a boolean `const` to provider adapters, and the Gemini query-string API key is intentionally hidden from tool arguments.
+The total registered count is the number returned by `tools/list`. All profiles include `compare_models` and `get_api_overview`, producing totals of 6, 32, and 89 tools. Realtime and streaming-only operations are excluded because stdio MCP tool calls return one final result. API operations that accept `stream` fix it internally to `false` without exposing a boolean `const` to provider adapters, and the Gemini query-string API key is intentionally hidden from tool arguments. `create_gemini_content` exposes the camelCase Gemini fields (`systemInstruction`, `generationConfig`, `safetySettings`, `toolConfig`, `cachedContent`) and hides their snake_case proto spellings, which the API accepts as aliases.
 
-The portable projection keeps every top-level argument but bounds deeply nested model-facing shapes. The server still validates calls against the complete generated OpenAPI schema before issuing an API request. Compatibility budgets keep `core` at no more than 60 KB and depth 8, and `full` at no more than 100 KB and depth 8 for the complete `tools/list` response. Tests also run the full profile through the Google AI SDK version used by the observed OpenCode/Gemini failure.
+The portable projection keeps every top-level argument but bounds deeply nested model-facing shapes. The server still validates calls against the complete generated OpenAPI schema before issuing an API request. Compatibility budgets keep `core` at no more than 60 KB and depth 8, and `full` at no more than 115 KB and depth 8 for the complete `tools/list` response. Tests also run the full profile through the Google AI SDK version used by the observed OpenCode/Gemini failure and keep its function declarations within 90 KB.
 
 Set `TOKENLAB_MCP_TOOL_PROFILE=catalog` for the smallest public-only tool list or `TOKENLAB_MCP_TOOL_PROFILE=full` for the broad developer API. Set `TOKENLAB_MCP_SCHEMA_MODE=exact` only when a client needs the complete nested JSON Schema and can accept its larger/deeper tool payload. Use `strict` for providers that require every property to be listed in `required` and every object to set `additionalProperties: false`; complex top-level arguments are represented as JSON-encoded strings and decoded before canonical validation. Canonical tool names, descriptions, input JSON Schemas, HTTP bindings, content types, auth requirements, and task behavior can be inspected in [`generated/tools.json`](./generated/tools.json).
 
@@ -134,7 +134,7 @@ This repository includes `server.json` for the official MCP Registry.
 
 Release metadata:
 
-- npm package: `@tokenlabai/mcp-server@0.6.26`
+- npm package: `@tokenlabai/mcp-server@0.6.28`
 - MCP registry name: `io.github.hedging8563/tokenlab`
 - `package.json.mcpName`: `io.github.hedging8563/tokenlab`
 

package/contract/mcp-overlay.json

@@ -63,7 +63,8 @@
         "max_endpoint_tools": 87,
         "max_input_schema_bytes": 78000,
         "max_input_schema_depth": 8,
-        "max_tools_list_bytes": 115000
+        "max_tools_list_bytes": 115000,
+        "max_gemini_declarations_bytes": 90000
       },
       "include_tags": [
         "Chat",
@@ -317,7 +318,12 @@
     "geminiGenerateContent": {
       "tool_name": "create_gemini_content",
       "omit_arguments": [
-        "key"
+        "key",
+        "system_instruction",
+        "generation_config",
+        "safety_settings",
+        "tool_config",
+        "cached_content"
       ]
     },
     "createChatCompletion": {