@oh-my-pi/pi-ai 15.8.3 → 15.9.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -2,6 +2,14 @@
2
2
 
3
3
  ## [Unreleased]
4
4
 
5
+ ## [15.9.0] - 2026-06-04
6
+
7
+ ### Fixed
8
+
9
+ - Fixed MiniMax-compatible OpenAI-completions hosts (e.g. `minimax-code-cn/MiniMax-M3`) losing tool-call arguments when the stream delivers `function.arguments` as a complete object instead of the OpenAI JSON-string contract. The streaming buffer previously concatenated the object into a string, coercing it to `[object Object]` and leaving `bash`/`edit` calls with empty or malformed inputs; the tool-call block now holds the object payload directly. ([#1776](https://github.com/can1357/oh-my-pi/issues/1776))
10
+ - Fixed Cloud Code Assist (Gemini / Antigravity) rejecting tool schemas with `Invalid JSON payload received. Unknown name "propertyNames"` (HTTP 400) when a tool exposed a property literally named `properties` (e.g. the Resend MCP `create_contact` tool). The schema normalizer's `insideProperties` flag was re-asserted when descending into such a property's value schema, so Google-unsupported keywords (`propertyNames`, `additionalProperties`, …) nested inside it were never stripped. The flag is now only set when entering a real `properties` map from a schema node, not from within another `properties` map.
11
+ - Fixed local/self-hosted providers leaking machine-specific endpoints into the bundled `models.json`. A `generate-models` run on a machine with a LiteLLM proxy baked 1202 `litellm` models pinned to `http://localhost:4000/v1` into the committed catalog. `litellm` (and `lm-studio`) now join `ollama`/`vllm` in the generator's discovery-only exclusion set, so local providers are never fetched during generation nor written to `models.json` — they are discovered dynamically at runtime instead. LiteLLM model discovery now enriches metadata against models.dev (the same reference source the other gateway providers use) rather than a bundled reference map. Added a regression test pinning the invariant (no local provider blocks, no loopback/private-network `baseUrl`s in the bundled catalog).
12
+
5
13
  ## [15.8.2] - 2026-06-03
6
14
 
7
15
  ### Fixed
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "type": "module",
3
3
  "name": "@oh-my-pi/pi-ai",
4
- "version": "15.8.3",
4
+ "version": "15.9.0",
5
5
  "description": "Unified LLM API with automatic model discovery and provider configuration",
6
6
  "homepage": "https://omp.sh",
7
7
  "author": "Can Boluk",
@@ -39,7 +39,7 @@
39
39
  },
40
40
  "dependencies": {
41
41
  "@bufbuild/protobuf": "^2.12.0",
42
- "@oh-my-pi/pi-utils": "15.8.3",
42
+ "@oh-my-pi/pi-utils": "15.9.0",
43
43
  "openai": "^6.39.0",
44
44
  "partial-json": "^0.1.7",
45
45
  "zod": "4.4.3"