Extracts focused source code snippets and git diffs from a raw error log or stack trace, stripping framework noise (node_modules, site-packages) and redacting credentials.

• Side Effects: None. Strictly read-only; does not modify workspace files, git state, or environment variables. • Auth & Permissions: None required. Reads local filesystem within the current workspace boundary. • Rate Limits: None. Runs entirely locally on native machine code. • Return Shape: Returns a JSON object with 'sanitized_trace' (string without secrets/noise), 'source_frames' (array of objects with file, line, code_snippet), and 'git_diff' (string or null). • Failure Modes: If source files referenced in the trace do not exist locally, omits code snippets for those frames while still returning the sanitized trace. Returns an error JSON on unreadable input. • When to use: Call immediately when receiving a runtime exception, test failure, or compiler error to isolate the root cause before planning code fixes. • When NOT to use: Do NOT use to search web solutions (use search_stack_overflow), do NOT use to modify files (use apply_code_patch), and do NOT use to statically lint clean code without an error log (use analyze_code). • Prerequisites: Workspace directory must be accessible locally; git repository recommended for diff extraction.

Queries the public Stack Overflow / Stack Exchange API for verified programming solutions and discussions matching an error signature.

• Side Effects: None. Strictly read-only network search; does not mutate local files or repository state. • Auth & Permissions: No API key required for standard rate-limited anonymous queries. • Rate Limits: Subject to public Stack Exchange API rate limits (~300 requests/day per IP). Results are cached locally when possible. • Return Shape: Returns a JSON object containing 'query', 'total_results', and 'results' (array of objects with title, url, score, is_answered, answer_count, and answer excerpt). • Failure Modes: Returns empty results array if no matching questions exist. Returns an error message if network connectivity fails or API quota is exhausted. • When to use: Use when local code context from get_error_context is insufficient and external community patterns, known library bugs, or API migration examples are needed. • When NOT to use: Do NOT use with raw un-sanitized logs containing private tokens or file paths, do NOT use for local codebase inspection (use get_error_context), and do NOT use to edit code (use apply_code_patch). • Prerequisites: Outbound HTTP internet access to api.stackexchange.com.

Applies an atomic, verified code edit to a specific file by substituting original_code with new_code, with automatic syntax validation and instant rollback on failure.

• Side Effects: Modifies the target file on the local filesystem. If syntax checks pass, the file is overwritten with patched contents; if syntax validation fails, the file is immediately restored to its exact original state (zero dirty diff). • Auth & Permissions: Requires write permissions for the target file on the host filesystem within the workspace boundary. Path traversal outside workspace root is blocked. • Rate Limits: None. Local disk I/O. • Return Shape: Returns a JSON object with 'status' ('success' or 'error'), 'file_path', 'lines_changed', 'verification' ('passed' or 'reverted'), and 'message'. • Failure Modes: Fails and aborts without touching the file if file_path is not found, if original_code does not match the file content uniquely, or if the compiler/linter check fails after patch application. • When to use: Use when you have finalized a bug fix or refactoring snippet and need safe, transactional application with zero risk of syntax corruption. • When NOT to use: Do NOT use for speculative edits without prior diagnosis (use get_error_context first), and do NOT use for whole-file generation when only a small block changes. • Prerequisites: Target file must exist and be within the current workspace directory.

Performs static AST code analysis using Tree-sitter to detect resource leaks (such as unclosed file handles), security vulnerabilities, and logic flaws with bounded execution limits and precise LSP UTF-16 coordinates.

• Side Effects: None. Strictly read-only analysis of in-memory code; does not execute code, spawn subprocesses, or write to disk. • Auth & Permissions: None required. Fully offline, in-memory parser. • Rate Limits: None. Bounded to 1MB max source size, 128 max AST depth, and 50,000 max node visits per call. • Return Shape: Returns a JSON object containing 'language', 'findings_count', 'duration_ms' (latency metric), and 'findings' (array of objects with rule_id, message, severity, line [1-indexed], column [1-indexed UTF-16 code units], and remediation). • Failure Modes: Returns findings: [] if the code contains no detected defects. Returns an error message if the language is unsupported or if source code exceeds the 1MB or 128 AST depth limits. • When to use: Use proactively before committing or running code, or when reviewing Python files for unclosed file handles, resource leaks, or AST defects. • When NOT to use: Do NOT use when you have an active runtime crash log (use get_error_context instead), and do NOT use to apply fixes automatically (use apply_code_patch instead). • Prerequisites: Supported languages currently include Python ('python', 'py').

Audits a raw error log, code snippet, or prompt payload for token bloat, framework noise, and credential leaks. Returns actionable M2M telemetry and savings recommendations without mutating workspace state.

• Side Effects: None. Read-only in-memory evaluation. • Auth & Permissions: None. • Rate Limits: None. • Return Shape: Returns JSON with 'raw_characters', 'estimated_raw_tokens', 'clean_characters', 'estimated_clean_tokens', 'tokens_saved', 'noise_reduction_pct', 'secrets_detected', 'health_grade' ('OPTIMAL', 'MODERATE_BLOAT', 'CRITICAL_BLOAT'), and 'recommendation'. • When to use: Call proactively when dealing with large terminal dumps or before sending long logs to the LLM to verify context efficiency. • When NOT to use: Do NOT use to apply file edits (use apply_code_patch) or query stack overflow.