llm-messages 0.4.3 → 0.4.5

package/CHANGELOG.md

@@ -4,6 +4,21 @@ All notable changes to this project are documented here. The format is based on
 [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) and this project adheres
 to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.4.5] - 2026-06-04
+
+### Changed
+
+- Aligned npm keywords with the GitHub repository topics for OpenAI-compatible
+  provider portability, chat completions, multimodal messages and zero
+  dependencies.
+
+## [0.4.4] - 2026-06-04
+
+### Changed
+
+- Published the public maintainer roadmap to npm so the package page also shows
+  OpenAI Responses API, conformance fixture and tool-call edge-case priorities.
+
 ## [0.4.3] - 2026-06-04
 
 ### Changed

package/README.md

@@ -171,6 +171,12 @@ Version 0.x covers text, system prompts, tool calls/results, images, audio and
 documents, which is the core of every agent loop. Unsupported parts are reported
 via `dropped-content` rather than failing.
 
+## Roadmap
+
+See [ROADMAP.md](./ROADMAP.md) for current maintenance priorities, including
+OpenAI Responses API coverage, live conformance fixtures and tool-call edge
+cases.
+
 ## Provider portability suite
 
 `llm-messages` is the conversation boundary in a small provider-portability

package/ROADMAP.md

@@ -0,0 +1,45 @@
+# Roadmap
+
+`llm-messages` is maintained as the conversation-boundary package in the
+provider-portability suite. The near-term roadmap focuses on OpenAI-compatible
+agent workflows where message shape correctness, tool-call preservation and
+fallback behavior matter.
+
+## Current priorities
+
+1. **OpenAI Responses API coverage**
+
+   Track and test how Responses API text, multimodal and tool-call payloads map
+   to the current OpenAI Chat Completions-compatible hub shape.
+
+   Public issue: https://github.com/slegarraga/llm-messages/issues/6
+
+2. **Live conformance fixtures**
+
+   Add provider-backed fixture generation for OpenAI, Anthropic and Gemini
+   payloads, keeping the committed test fixtures deterministic and safe to run
+   without API keys.
+
+3. **Tool-call edge cases**
+
+   Expand tests for parallel tool calls, missing provider ids, invalid JSON
+   arguments, tool-result ordering and lossy conversion warnings.
+
+4. **Docs for agent fallback loops**
+
+   Document the recommended flow for converting one conversation across
+   providers after rate limits or retryable provider failures.
+
+## API credit use
+
+If API credits are available, they will be used for conformance checks against
+OpenAI APIs, especially Responses API and tool-call fixtures. Generated fixtures
+should be minimized, reviewed, and committed only when they improve public test
+coverage or documentation.
+
+## Non-goals
+
+- No runtime dependencies.
+- No hidden network calls in the library.
+- No provider-specific SDK dependency.
+- No silent data loss; lossy mappings should be represented as warnings.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llm-messages",
-  "version": "0.4.3",
+  "version": "0.4.5",
   "description": "Convert chat conversations and responses between OpenAI, Anthropic and Gemini. Tool calls, images, audio, documents and roles handled. Zero dependencies.",
   "keywords": [
     "openai",
@@ -10,17 +10,25 @@
     "deepseek",
     "groq",
     "openrouter",
+    "openai-compatible",
     "llm",
     "messages",
     "chat",
+    "chat-completions",
     "convert",
     "function-calling",
     "tool-use",
     "tool-calls",
     "provider",
     "portability",
+    "provider-portability",
+    "structured-outputs",
+    "multimodal",
     "ai",
-    "agents"
+    "agents",
+    "ai-agents",
+    "typescript",
+    "zero-dependencies"
   ],
   "license": "MIT",
   "author": "Sebastian Legarraga",
@@ -47,6 +55,7 @@
   "files": [
     "dist",
     "README.md",
+    "ROADMAP.md",
     "LICENSE",
     "CHANGELOG.md"
   ],