consult-llm-mcp 2.8.0 → 2.10.0

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # Changelog
 
+## v2.8.0 (2026-03-13)
+
+- Replaced hardcoded model enum with abstract selectors (`gemini`, `openai`,
+  `deepseek`) that resolve to the best available model at query time. This
+  avoids the need to hardcode a specific model in the caller side.
+- Responses now include a `[model:xxx]` prefix showing which concrete model was
+  used
+- Default Codex reasoning effort to "high" (was previously unset)
+- Monitor: added Task column to active and history tables
+- Monitor: show task mode and reasoning effort in detail view header
+- Monitor: press `s` in detail view to toggle system prompt display
+- Monitor: system prompt is now recorded in sidecar event files for viewing in
+  the TUI
+
 ## v2.7.4 (2026-03-13)
 
 - Fixed Linux prebuilt binaries failing on older distros due to glibc version

package/README.md

@@ -23,18 +23,17 @@ to bring in the heavy artillery. Supports multi-turn conversations.
 ```
 
 [Quick start](#quick-start) · [Configuration](#configuration) ·
-[Skills](#skills) · [Monitor TUI](#monitor) · [Changelog](CHANGELOG.md)
+[Skills](#skills) · [Monitor TUI](#monitor) · [Why MCP?](#why-mcp-and-not-cli) ·
+[Changelog](CHANGELOG.md)
 
 ## Features
 
 - Query powerful AI models (GPT-5.4, Gemini 3.1 Pro, DeepSeek Reasoner) with
   relevant files as context
-- Direct queries with optional file context
-- Include git changes for code review and analysis
-- Comprehensive logging with cost estimation
+- Include git changes for code review
+- Comprehensive logging with cost estimation (if using API)
 - [Monitor TUI](#monitor): Real-time dashboard for watching active consultations
-- [Gemini CLI backend](#gemini-cli): Use the `gemini` CLI to take advantage of
-  [free quota](https://developers.google.com/gemini-code-assist/resources/quotas#quotas-for-agent-mode-gemini-cli)
+- [Gemini CLI backend](#gemini-cli): Use the `gemini` CLI for Gemini models
 - [Codex CLI backend](#codex-cli): Use the `codex` CLI for OpenAI models
 - [Cursor CLI backend](#cursor-cli): Use the `cursor-agent` CLI to route GPT and
   Gemini models through a single tool
@@ -64,7 +63,7 @@ to bring in the heavy artillery. Supports multi-turn conversations.
    [Codex CLI](#codex-cli). No API keys required, just `gemini login` and
    `codex login`.
 
-   **With binary** (no Node.js required, but no auto-update):
+   **With binary** (comes with the monitor TUI, no Node.js required):
 
    ```bash
    curl -fsSL https://raw.githubusercontent.com/raine/consult-llm-mcp/main/scripts/install.sh | bash
@@ -520,6 +519,12 @@ See the "Using web mode..." example above for a concrete transcript.
   (optional)
   - Overrides the default `~/.consult-llm-mcp/SYSTEM_PROMPT.md` location
   - Useful for project-specific prompts
+- `CONSULT_LLM_NO_UPDATE_CHECK` - Disable automatic update checking on server
+  startup (optional)
+  - Set to `1` to disable
+  - By default, the server checks for new versions in the background every 24
+    hours and logs a notice when an update is available
+  - Only applies to binary installs — npm installs are never checked
 - `MCP_DEBUG_STDIN` - Log raw JSON-RPC messages received on stdin (optional)
   - Set to `1` to enable
   - Logs every message as `RAW RECV` entries and poll timing gaps as
@@ -818,6 +823,52 @@ forth before synthesizing and implementing. See
 > /debate-vs --gemini design the multi-tenant isolation strategy
 ```
 
+## Updating
+
+**Binary installs:**
+
+```bash
+consult-llm-mcp update
+```
+
+Downloads the latest release from GitHub with SHA-256 checksum verification. If
+`consult-llm-monitor` is found alongside the binary, it's updated too.
+
+The server also checks for updates in the background on startup (every 24 hours)
+and logs a notice when a newer version is available. Disable with
+`CONSULT_LLM_NO_UPDATE_CHECK=1`.
+
+## Why MCP and not CLI?
+
+The server maps one `model` parameter onto five backends (OpenAI API, Gemini
+API, Gemini CLI, Codex CLI, Cursor CLI) with different commands, streaming
+formats, output schemas, file handling, and resume semantics. Doing this through
+agent Bash calls would push all of that per-provider plumbing into the agent or
+a wrapper script/CLI.
+
+MCP also sidesteps shell escaping. Prompts contain code with backticks, `$`, and
+quotes. Passing one model's code-heavy response into another call breaks bash
+quoting and requires temp files. MCP passes structured JSON instead.
+
+Multi-turn workflows add more friction as a CLI. To continue a conversation, the
+agent needs to find a session ID in the CLI's output and pass it back as a flag
+on the next invocation. With MCP, the agent passes `thread_id` as a parameter
+and the server handles the provider-specific resume mechanics internally.
+
+The MCP tool is also easier to compose into [skills](#skills). `/consult`,
+`/collab`, and `/debate` all just say "call `consult_llm` with these
+parameters." A CLI version would need each skill to either teach the agent the
+CLI's interface or reference a separate skill that does. A skill that
+orchestrates a multi-model debate is ~90 lines with MCP. As shell commands, the
+same skill would either balloon into hundreds of lines of escaping rules and
+stdout parsing, or depend on another skill that teaches the agent how to call
+each CLI.
+
+If you only need a single provider with simple prompts, a Bash call to `gemini`
+or `codex` with some `jq` filtering will work fine. MCP starts to make more
+sense with multiple backends, multi-turn conversations across providers, or
+custom workflows that nicely compose on top.
+
 ## Development
 
 To work on the MCP server locally and use your development version:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "consult-llm-mcp",
-  "version": "2.8.0",
+  "version": "2.10.0",
   "description": "MCP server for consulting powerful AI models",
   "repository": {
     "type": "git",
@@ -31,9 +31,9 @@
     "ai"
   ],
   "optionalDependencies": {
-    "consult-llm-mcp-darwin-arm64": "2.8.0",
-    "consult-llm-mcp-darwin-x64": "2.8.0",
-    "consult-llm-mcp-linux-x64": "2.8.0",
-    "consult-llm-mcp-linux-arm64": "2.8.0"
+    "consult-llm-mcp-darwin-arm64": "2.10.0",
+    "consult-llm-mcp-darwin-x64": "2.10.0",
+    "consult-llm-mcp-linux-x64": "2.10.0",
+    "consult-llm-mcp-linux-arm64": "2.10.0"
   }
 }