Refactor: Improve MCP logging, update E2E & tests

Refactors MCP server logging and updates testing infrastructure.

- MCP Server:

  - Replaced manual logger wrappers with centralized `createLogWrapper` utility.

  - Updated direct function calls to use `{ session, mcpLog }` context.

  - Removed deprecated `model` parameter from analyze, expand-all, expand-task tools.

  - Adjusted MCP tool import paths and parameter descriptions.

- Documentation:

  - Modified `docs/configuration.md`.

  - Modified `docs/tutorial.md`.

- Testing:

  - E2E Script (`run_e2e.sh`):

    - Removed `set -e`.

    - Added LLM analysis function (`analyze_log_with_llm`) & integration.

    - Adjusted test run directory creation timing.

    - Added debug echo statements.

  - Deleted Unit Tests: Removed `ai-client-factory.test.js`, `ai-client-utils.test.js`, `ai-services.test.js`.

  - Modified Fixtures: Updated `scripts/task-complexity-report.json`.

- Dev Scripts:

  - Modified `scripts/dev.js`.

.changeset/cuddly-zebras-matter.md

@@ -1,5 +1,5 @@
 ---
-'task-master-ai': patch
+'task-master-ai': minor
 ---
 
 feat(expand): Enhance `expand` and `expand-all` commands

.changeset/easy-toys-wash.md

@@ -1,7 +1,7 @@
 ---
-'task-master-ai': patch
+'task-master-ai': minor
 ---
 
-- Adds support for the OpenRouter AI provider. Users can now configure models available through OpenRouter (requiring an `OPENROUTER_API_KEY`) via the `task-master models` command, granting access to a wide range of additional LLMs.
-- IMPORTANT FYI ABOUT OPENROUTER: Taskmaster relies on AI SDK, which itself relies on tool use. It looks like **free** models sometimes do not include tool use. For example, Gemini 2.5 pro (free) failed via OpenRouter (no tool use) but worked fine on the paid version of the model. Custom model support for Open Router is considered experimental and likely will not be further improved for some time.
+Adds support for the OpenRouter AI provider. Users can now configure models available through OpenRouter (requiring an `OPENROUTER_API_KEY`) via the `task-master models` command, granting access to a wide range of additional LLMs.
+    - IMPORTANT FYI ABOUT OPENROUTER: Taskmaster relies on AI SDK, which itself relies on tool use. It looks like **free** models sometimes do not include tool use. For example, Gemini 2.5 pro (free) failed via OpenRouter (no tool use) but worked fine on the paid version of the model. Custom model support for Open Router is considered experimental and likely will not be further improved for some time.
 

.changeset/fancy-cities-march.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': minor
----
-
-Refactor AI service interaction to use unified layer and Vercel SDK

.changeset/mighty-mirrors-watch.md

@@ -1,5 +1,5 @@
 ---
-'task-master-ai': patch
+'task-master-ai': minor
 ---
 
 Adds model management and new configuration file .taskmasterconfig which houses the models used for main, research and fallback. Adds models command and setter flags. Adds a --setup flag with an interactive setup. We should be calling this during init. Shows a table of active and available models when models is called without flags. Includes SWE scores and token costs, which are manually entered into the supported_models.json, the new place where models are defined for support. Config-manager.js is the core module responsible for managing the new config."

.changeset/nine-rocks-sink.md

@@ -2,7 +2,7 @@
 'task-master-ai': patch
 ---
 
-- Improves next command to be subtask-aware
+Improves next command to be subtask-aware
     - The logic for determining the "next task" (findNextTask function, used by task-master next and the next_task MCP tool) has been significantly improved. Previously, it only considered top-level tasks, making its recommendation less useful when a parent task containing subtasks was already marked 'in-progress'.
     - The updated logic now prioritizes finding the next available subtask within any 'in-progress' parent task, considering subtask dependencies and priority. 
     - If no suitable subtask is found within active parent tasks, it falls back to recommending the next eligible top-level task based on the original criteria (status, dependencies, priority). 

.changeset/ninety-ghosts-relax.md

@@ -1,8 +1,8 @@
 ---
-'task-master-ai': patch
+'task-master-ai': minor
 ---
 
-- feat: Add custom model ID support for Ollama and OpenRouter providers.
+Adds custom model ID support for Ollama and OpenRouter providers.
   - Adds the `--ollama` and `--openrouter` flags to `task-master models --set-<role>` command to set models for those providers outside of the support models list.
   - Updated `task-master models --setup` interactive mode with options to explicitly enter custom Ollama or OpenRouter model IDs.
   - Implemented live validation against OpenRouter API (`/api/v1/models`) when setting a custom OpenRouter model ID (via flag or setup).

.changeset/public-cooks-fetch.md

@@ -2,6 +2,6 @@
 'task-master-ai': minor
 ---
 
-Feat: Integrate OpenAI as a new AI provider.
-Feat: Enhance `models` command/tool to display API key status.
-Feat: Implement model-specific `maxTokens` override based on `supported-models.json` to save you if you use an incorrect max token value.
+Integrate OpenAI as a new AI provider.
+    - Enhance `models` command/tool to display API key status.
+    - Implement model-specific `maxTokens` override based on `supported-models.json` to save you if you use an incorrect max token value.

.changeset/tricky-papayas-hang.md

@@ -1,7 +1,7 @@
 ---
-'task-master-ai': patch
+'task-master-ai': minor
 ---
-- Tweaks Perplexity AI calls for research mode to max out input tokens and get day-fresh information
+Tweaks Perplexity AI calls for research mode to max out input tokens and get day-fresh information
     - Forces temp at 0.1 for highly deterministic output, no variations
     - Adds a system prompt to further improve the output
     - Correctly uses the maximum input tokens (8,719, used 8,700) for perplexity

.changeset/violet-parrots-march.md

@@ -2,8 +2,8 @@
 'task-master-ai': patch
 ---
 
-- Adds a 'models' CLI and MCP command to get the current model configuration, available models, and gives the ability to set main/research/fallback models." 
-- In the CLI, `task-master models` shows the current models config. Using the `--setup` flag launches an interactive set up that allows you to easily select the models you want to use for each of the three roles. Use `q` during the interactive setup to cancel the setup.
-- In the MCP, responses are simplified in RESTful format (instead of the full CLI output). The agent can use the `models` tool with different arguments, including `listAvailableModels` to get available models. Run without arguments, it will return the current configuration. Arguments are available to set the model for each of the three roles. This allows you to manage Taskmaster AI providers and models directly from either the CLI or MCP or both.
-- Updated the CLI help menu when you run `task-master` to include missing commands and .taskmasterconfig information.
-- Adds `--research` flag to `add-task` so you can hit up Perplexity right from the add-task flow, rather than having to add a task and then update it.
+Adds a 'models' CLI and MCP command to get the current model configuration, available models, and gives the ability to set main/research/fallback models." 
+    - In the CLI, `task-master models` shows the current models config. Using the `--setup` flag launches an interactive set up that allows you to easily select the models you want to use for each of the three roles. Use `q` during the interactive setup to cancel the setup.
+    - In the MCP, responses are simplified in RESTful format (instead of the full CLI output). The agent can use the `models` tool with different arguments, including `listAvailableModels` to get available models. Run without arguments, it will return the current configuration. Arguments are available to set the model for each of the three roles. This allows you to manage Taskmaster AI providers and models directly from either the CLI or MCP or both.
+    - Updated the CLI help menu when you run `task-master` to include missing commands and .taskmasterconfig information.
+    - Adds `--research` flag to `add-task` so you can hit up Perplexity right from the add-task flow, rather than having to add a task and then update it.