compendium-mcp 0.6.2 → 0.6.3

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.
Files changed (2) hide show
  1. package/README.md +17 -26
  2. package/package.json +8 -8
package/README.md CHANGED
@@ -48,35 +48,23 @@ That alone is enough: filter, compress, summarize, cache, and BM25 actions all w
48
48
 
49
49
  ### 2. (Optional) Smarter summaries with Ollama
50
50
 
51
- Want better `summarize_smart` / `filter_relevant`? Run a small model on your machine and point Compendium at it.
52
-
53
- 1. Install [Ollama](https://ollama.com/) and start it (default: `http://127.0.0.1:11434`).
54
- 2. Pull a chat model, for example:
51
+ Want better `summarize_smart` / `filter_relevant` / hybrid `rerank`? One command after the MCP server is added:
55
52
 
56
53
  ```bash
57
- ollama pull qwen:latest
58
- # or a smaller one: ollama pull qwen2.5:3b
54
+ npx -y compendium-mcp setup-ollama --write-mcp
59
55
  ```
60
56
 
61
- 3. Extend the MCP `env` block (URL must stay on **localhost** — Compendium blocks remote hosts on purpose):
57
+ That detects (or `--install`s) [Ollama](https://ollama.com/), pulls a small chat + embed model (`qwen2.5:3b` + `nomic-embed-text`), probes loopback `http://127.0.0.1:11434/v1`, and merges `COMPENDIUM_LOCAL_LLM_*` into `~/.cursor/mcp.json`. Use `--project` for `.cursor/mcp.json`. Reload MCP, then `action: "llm_status"` should show `reachable: true`. `"backend": "local_llm"` on smart actions means Ollama answered; `"heuristic"` means it fell back.
62
58
 
63
- ```json
64
- {
65
- "mcpServers": {
66
- "compendium": {
67
- "command": "npx",
68
- "args": ["-y", "compendium-mcp"],
69
- "env": {
70
- "COMPENDIUM_LOCAL_LLM_URL": "http://127.0.0.1:11434/v1",
71
- "COMPENDIUM_LOCAL_LLM_MODEL": "qwen:latest"
72
- }
73
- }
74
- }
75
- }
59
+ ```bash
60
+ npx -y compendium-mcp setup-ollama --help
61
+ npx -y compendium-mcp setup-ollama --install --write-mcp --project
62
+ npx -y compendium-mcp setup-ollama --dry-run --json
76
63
  ```
77
64
 
78
- 4. Reload MCP, then ask the agent to call `compendium` with `action: "summarize_smart"`.
79
- In the result, `"backend": "local_llm"` means Ollama answered; `"heuristic"` means it fell back (Ollama down, wrong model name, or URL missing).
65
+ Agent recipe: playbook `setup-ollama` (`cmp://skill/playbook/setup-ollama`).
66
+
67
+ Manual / Lemonade / custom models: set `COMPENDIUM_LOCAL_LLM_URL` yourself (must stay on **localhost** — Compendium blocks remote hosts on purpose). See [Environment](#environment).
80
68
 
81
69
  **Notes**
82
70
 
@@ -107,6 +95,7 @@ Binary packaging details for maintainers: [npm/DISTRIBUTION.md](npm/DISTRIBUTION
107
95
  |------|---------|-------|
108
96
  | **stdio** (default) | `compendium` / `compendium stdio` | Cursor / Claude Desktop — dual-compat (legacy initialize or modern connect) |
109
97
  | **Streamable HTTP** | `compendium http [BIND]` | Requires `--features http`. Endpoint: `http://{bind}/mcp`. Sessionless (`2026-07-28`); JSON preferred, SSE fallback |
98
+ | **Ollama setup** | `compendium setup-ollama` | Not an MCP transport — CLI helper (`--write-mcp`, `--dry-run`, `--json`). Alias: `compendium ollama` |
110
99
 
111
100
  Default HTTP bind: `127.0.0.1:8788` (override with arg or `COMPENDIUM_HTTP_BIND`). App cache (`COMPENDIUM_CACHE_DIR`) is not an MCP session — set it for multi-request HTTP. See playbook `http-transport`.
112
101
 
@@ -181,7 +170,8 @@ docs/ # architecture notes
181
170
  examples/ # sample MCP tool-call JSON payloads
182
171
  testdata/ # eval fixtures (logs, audit, PR JSON, untrusted paste, …)
183
172
  src/
184
- main.rs # CLI: stdio | http
173
+ main.rs # CLI: stdio | http | setup-ollama
174
+ setup_ollama.rs # `compendium setup-ollama` (detect/pull/probe/write MCP env)
185
175
  lib.rs
186
176
  brand.rs # SEP-973 icons for serverInfo + tool
187
177
  config.rs # COMPENDIUM_* env config
@@ -246,7 +236,8 @@ Same `command` / `args` / `env` as Cursor, in Claude’s MCP config file.
246
236
  "COMPENDIUM_DEFAULT_MAX_TOKENS": "2048",
247
237
  "COMPENDIUM_TOKENIZER": "cl100k_base",
248
238
  "COMPENDIUM_LOCAL_LLM_URL": "http://127.0.0.1:11434/v1",
249
- "COMPENDIUM_LOCAL_LLM_MODEL": "qwen:latest"
239
+ "COMPENDIUM_LOCAL_LLM_MODEL": "qwen2.5:3b",
240
+ "COMPENDIUM_LOCAL_EMBED_MODEL": "nomic-embed-text"
250
241
  }
251
242
  ```
252
243
 
@@ -292,7 +283,7 @@ Point an MCP streamable-HTTP client at that URL (e.g. `StreamableHttpClientTrans
292
283
  | `COMPENDIUM_SIMILARITY_THRESHOLD` | `0.85` | Jaccard line-dedupe threshold |
293
284
  | `COMPENDIUM_HTTP_BIND` | `127.0.0.1:8788` | Default HTTP listen address |
294
285
  | `COMPENDIUM_LOCAL_LLM_URL` | _(unset)_ | OpenAI-compatible base URL (e.g. `http://127.0.0.1:11434/v1` or `http://127.0.0.1:13305/api/v1`). Enables smart actions. |
295
- | `COMPENDIUM_LOCAL_LLM_MODEL` | `Qwen3-4B-GGUF` | Model id on that server (Ollama: e.g. `qwen:latest`) |
286
+ | `COMPENDIUM_LOCAL_LLM_MODEL` | `Qwen3-4B-GGUF` | Model id on that server (Ollama setup default: `qwen2.5:3b`) |
296
287
  | `COMPENDIUM_LOCAL_EMBED_MODEL` | _(same as chat)_ | Embeddings model for hybrid `rerank` / `brief` (e.g. `nomic-embed-text`) |
297
288
  | `COMPENDIUM_HYBRID_ALPHA` | `0.55` | BM25 weight in hybrid score (0–1); remainder is embedding cosine |
298
289
  | `COMPENDIUM_RERANK_CROSS_ENCODER` | _(off)_ | When `1`/`true`, `rerank` SLM-rescores top-N after BM25/hybrid |
@@ -389,7 +380,7 @@ Start the new turn with the returned `briefing` (or `cache_get` the `cache_key`)
389
380
 
390
381
  ## Local small language model
391
382
 
392
- Follow [Quick start §2](#2-optional-smarter-summaries-with-ollama) for Ollama.
383
+ Follow [Quick start §2](#2-optional-smarter-summaries-with-ollama) (`npx -y compendium-mcp setup-ollama`).
393
384
 
394
385
  Rules of thumb:
395
386
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "compendium-mcp",
3
- "version": "0.6.2",
3
+ "version": "0.6.3",
4
4
  "description": "MCP server that compresses, summarizes, and filters context to minimize LLM token usage",
5
5
  "license": "MIT",
6
6
  "keywords": [
@@ -42,13 +42,13 @@
42
42
  "prepare": "node npm/scripts/link-bins.js"
43
43
  },
44
44
  "optionalDependencies": {
45
- "compendium-mcp-darwin-arm64": "0.6.2",
46
- "compendium-mcp-darwin-x64": "0.6.2",
47
- "compendium-mcp-linux-x64": "0.6.2",
48
- "compendium-mcp-linux-x64-musl": "0.6.2",
49
- "compendium-mcp-linux-arm64": "0.6.2",
50
- "compendium-mcp-win32-x64": "0.6.2",
51
- "compendium-mcp-win32-arm64": "0.6.2"
45
+ "compendium-mcp-darwin-arm64": "0.6.3",
46
+ "compendium-mcp-darwin-x64": "0.6.3",
47
+ "compendium-mcp-linux-x64": "0.6.3",
48
+ "compendium-mcp-linux-x64-musl": "0.6.3",
49
+ "compendium-mcp-linux-arm64": "0.6.3",
50
+ "compendium-mcp-win32-x64": "0.6.3",
51
+ "compendium-mcp-win32-arm64": "0.6.3"
52
52
  },
53
53
  "preferUnplugged": true
54
54
  }