The getSectionContent tool schema and implementation now use `childrenSectionIds` (array of strings) instead of the previous pagination fields `partIndex` and `totalParts`. Updated Zod schema, output types, data handling, and returned objects accordingly. This change simplifies section handling by focusing on child section relationships rather than pagination.
Added fallback to `process.env.COOLIFY_URL` before `MCP_PUBLIC_URL` when constructing the public URL for the MCP inspector, ensuring the correct base URL is used in environments where COOLIFY_URL is set.
- Define /mcp endpoint before mounting inspector at /
- Ensures specific routes are matched before catch-all
- Prevents inspector from intercepting MCP requests
- Eliminated `content` property from `searchSpecResultSchema` and output mapping.
- Updated `toolMetadata` description to reflect that only section references are returned and content must be fetched via `ask262_get_section_content`.
- Adjusted TypeScript code accordingly.
- Replaced the old “Prerequisites” section with an “Available Tools” table describing the three core commands.
- Added a “Quick Start (Hosted Instance)” section with configuration snippets for Claude Desktop and OpenCode.
- Created a detailed “Local Installation” / “Setup” section including cloning, installing, and global install commands.
- Updated environment configuration instructions and clarified .env usage.
- Consolidated MCP client configuration examples (stdio and http) with explicit server start commands.
- Provided updated spec‑building steps and clarified directory contents.
- Cleaned up duplicated installation instructions and improved overall layout for better readability.
- Insert console.error statements to trace loading, initialization, execution, and mark collection.
- Log creation of agent and realm, trace start/stop, and code execution progress.
- Output captured mark count.
- Simplify fatal error handling with a single error message variable and console.error output.
- Import path and fileURLToPath for path resolution.
- Rename imported STORAGE_DIR to STORAGE_DIR_REL.
- Compute STORAGE_DIR as an absolute path relative to the script’s directory.
---
## Explanation
The diff only modifies `Readme.md`, changing the OpenCode configuration snippet. The update replaces the old local config path with a global one, adds a `$schema` reference, restructures the `command` field, and introduces `type` and `enabled` properties. Therefore, a **docs**‑type conventional commit is appropriate, describing the documentation change.
Removed the outdated Setup documentation and introduced a new Development section that includes cloning instructions, spec setup steps, and guidance on building the knowledge graph for custom ECMAScript specifications. This reorganization clarifies the workflow for developers and users building the project from source.
Update README to specify pulling the `qwen3-embedding:0.6b` model and document the optional `OLLAMA_HOST` environment variable. Adjust server code to import `EMBEDDING_MODEL`, use it for Ollama embeddings, and pass `process.env.OLLAMA_HOST` as the base URL.
Deleted the `config.json` entry from the package file list and removed the corresponding `CONFIG_FILE` constant, cleaning up unused configuration references.
Changed the `idempotentHint` annotation from `false` to `true` in the MCP server configuration. This enables idempotent behavior hints for relevant operations.
- Replace union output schema with a single combined schema containing optional fields for success and error cases, addressing MCP SDK limitation with union types.
- Add `importantSections`, `otherSections`, and `consoleOutput` as optional fields in the new schema.
- Update exported `outputSchema` and `EvaluateToolOutput` type to use the combined schema.
- Refactor execution logic to handle engine262's `ThrowCompletion_` instead of relying on thrown exceptions, extracting a readable error message.
- Adjust MCP server error detection to check `result.error !== undefined` rather than using the `in` operator.
- Update related comments and documentation to reflect the new schema design and error handling approach.
- Updated tool metadata to describe pure ECMAScript restrictions and new JSON output (importantSections, otherSections, consoleOutput).
- Added `ConsoleEntry` type and logic to capture console method calls during evaluation.
- Exposed a global `console` with `log`, `warn`, `debug`, and `error` methods to the evaluated code.
- Adjusted argument description and example usage accordingly.
- Introduce `recursive` boolean argument (default true) to the getSectionContent tool schema.
- Update descriptions to clarify that recursive fetching occurs only when `recursive=true`.
- Pass the `recursive` parameter from the CLI wrapper to the core tool function.
- Modify the content fetching logic to traverse child sections only when `recursive` is enabled.
Implemented a capture flag in `Ask262Debug` to enable/disable marking.
- Added `_captureEnabled` property and related logic in `mark()`.
- Introduced `startTrace()` and `stopTrace()` methods to toggle capture.
- Updated verification script to start tracing, run tests, stop tracing, and assert that the `Array.prototype.every` section is captured and marked important.
bendtherules