@octocodeai/freellama 0.5.0 → 0.6.1

package/LICENSE-MIT

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) FreeLlama contributors
+Copyright (c) 2026 Guy Bary
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of this software and
 associated documentation files (the "Software"), to deal in the Software without restriction, including

package/README.md

@@ -9,7 +9,7 @@ submit managed tasks. Ollama supplies model loading and inference.
 The JavaScript launcher locates the
 compiled Rust CLI in the matching optional native package and forwards arguments, signals, and exit
 status. In a source checkout, it uses `target/release/freellama` after a build. Routing and execution
-logic remain in [`freellama-core`](../rust-core/README.md).
+logic remain in [`freellama-core`](https://github.com/bgauryy/FreeLlama/blob/main/packages/rust-core/README.md).
 
 ```mermaid
 flowchart LR
@@ -27,7 +27,6 @@ flowchart LR
 npx @octocodeai/freellama doctor
 npx @octocodeai/freellama auth-token --out ~/.local/share/freellama/auth.token
 npx @octocodeai/freellama serve \
-  --recommendation-catalog recommendations.example.toml \
   --auth-token-file ~/.local/share/freellama/auth.token \
   --feedback-file ~/.local/share/freellama/feedback.json
 ```
@@ -44,9 +43,9 @@ npx @octocodeai/freellama route --task coding --objective fastest
 npx @octocodeai/freellama task --task completion --objective fastest "Reply with exactly OK."
 ```
 
-Read the repository [CLI reference](../../docs/CLI.md) for the complete command map, task kinds, routing
+Read the repository [CLI reference](https://github.com/bgauryy/FreeLlama/blob/main/docs/CLI.md) for the complete command map, task kinds, routing
 confidence, policy generation, and admission controls. Use the
-[Scope history and model warming reference](../../docs/SCOPES_AND_WARMING.md) for `scope`, `warm`,
+[Scope history and model warming reference](https://github.com/bgauryy/FreeLlama/blob/main/docs/SCOPES_AND_WARMING.md) for `scope`, `warm`,
 and the scoped task flags.
 
 ## Run separate CPU and GPU backends
@@ -61,12 +60,12 @@ npx @octocodeai/freellama serve \
 ```
 
 Managed tasks for assigned models use the CPU backend; other managed models and raw Ollama
-passthrough use the primary backend. See [CPU and GPU model routing](../../docs/CPU_GPU_ROUTING.md)
+passthrough use the primary backend. See [CPU and GPU model routing](https://github.com/bgauryy/FreeLlama/blob/main/docs/CPU_GPU_ROUTING.md)
 for the process setup, verification steps, and measured concurrency result.
 
 The primary admission pool derives its default weighted budget from observed Ollama parallelism;
 the independent CPU pool defaults to one unit. Inspect the effective values with `config`. Override
-them with `--max-concurrent-tasks` and `--cpu-max-concurrent-tasks`. `route`, `recommend`, and
+them with `--max-concurrent-tasks` and `--cpu-max-concurrent-tasks`. `route` and
 `task` also accept `--execution-preference auto|prefer-cpu|prefer-gpu`; this only chooses among
 models already eligible on the requested backend and reports any fallback in the execution receipt.
 `--min-placement-evidence observed` fails closed unless resident `/api/ps` evidence matches; use
@@ -76,13 +75,13 @@ The health endpoint advertises backend, guarded-preference, runtime-feedback, an
 persistence contracts, plus per-backend admission capacity. Comparable speed samples require matching
 model digest, observed context, controls, process settings, and serial admission identity. A successful
 parallel request can report verified placement without qualifying a speed sample. See
-[feedback and adaptive profiles](../../docs/MONITORING.md#adaptive-concurrency) for sample eligibility.
+[feedback and adaptive profiles](https://github.com/bgauryy/FreeLlama/blob/main/docs/MONITORING.md#adaptive-concurrency) for sample eligibility.
 Treat a missing contract as a stale running binary, then rebuild and restart before testing placement.
 
 Authentication covers both control routes and raw Ollama passthrough. A nonloopback listener also
 requires `--allow-remote`; terminate TLS and add tenant authorization outside FreeLlama. The CLI
 persists bounded aggregate feedback by default. Use `--ephemeral-feedback` only for disposable
-runs. See the [production runbook](../../docs/PRODUCTION.md).
+runs. See the [production runbook](https://github.com/bgauryy/FreeLlama/blob/main/docs/PRODUCTION.md).
 
 ## Build the launcher and binary
 
@@ -118,13 +117,9 @@ errors, and the files included in the package. Core CLI contracts live in
 
 ## Understand CLI and MCP differences
 
-```bash
-npx @octocodeai/freellama tools
-```
-
-The output is contract-tested against the MCP server source. `delegate_research` and the online
-model-library view are MCP-only. Control-plane startup, proxy startup, recommendation,
-benchmarks, policy generation, and frozen-suite comparison are CLI-only.
+`delegate_research` and the online model-library view are MCP-only. Control-plane startup, proxy
+startup, auth-token creation, and benchmarks are CLI-only. Generate a routing policy with
+`freellama policy from-eval` (see [CLI reference](https://github.com/bgauryy/FreeLlama/blob/main/docs/CLI.md#earn-medium-routing-confidence)).
 
 Use the surfaces together: the CLI starts and verifies the local services; MCP lets an agent inspect
 that state and submit bounded work. An installed MCP client can read `freellama://docs/index` and

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@octocodeai/freellama",
-  "version": "0.5.0",
+  "version": "0.6.1",
   "description": "Local Ollama model gateway, router, and benchmarker — CLI. Wraps the compiled Rust binary from packages/rust-core.",
   "repository": {
     "type": "git",
@@ -33,16 +33,17 @@
     "test": "vitest run",
     "test:watch": "vitest"
   },
+  "author": "Guy Bary",
   "license": "Apache-2.0 OR MIT",
   "optionalDependencies": {
-    "@octocodeai/freellama-native-darwin-arm64": "0.5.0",
-    "@octocodeai/freellama-native-darwin-x64": "0.5.0",
-    "@octocodeai/freellama-native-linux-arm64-gnu": "0.5.0",
-    "@octocodeai/freellama-native-linux-arm64-musl": "0.5.0",
-    "@octocodeai/freellama-native-linux-x64-gnu": "0.5.0",
-    "@octocodeai/freellama-native-linux-x64-musl": "0.5.0",
-    "@octocodeai/freellama-native-win32-arm64-msvc": "0.5.0",
-    "@octocodeai/freellama-native-win32-x64-msvc": "0.5.0"
+    "@octocodeai/freellama-native-darwin-arm64": "0.6.1",
+    "@octocodeai/freellama-native-darwin-x64": "0.6.1",
+    "@octocodeai/freellama-native-linux-arm64-gnu": "0.6.1",
+    "@octocodeai/freellama-native-linux-arm64-musl": "0.6.1",
+    "@octocodeai/freellama-native-linux-x64-gnu": "0.6.1",
+    "@octocodeai/freellama-native-linux-x64-musl": "0.6.1",
+    "@octocodeai/freellama-native-win32-arm64-msvc": "0.6.1",
+    "@octocodeai/freellama-native-win32-x64-msvc": "0.6.1"
   },
   "publishConfig": {
     "access": "public",