docs: Core Phase 5 plan — Go callees + Rust scanner#31
Merged
Conversation
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…pport 3 parts: Go callees + pattern rules, Rust scanner end-to-end, pipeline wiring + local verification against cli/cli and ripgrep. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Clarify Rust uses call_expression for all calls (no separate method_call) - Add Step 0 grammar validation before building scanner - Fix PatternQuery → PatternMatchRule type name throughout - Note .go extension missing from EXTENSION_TO_LANGUAGE as bug fix - Specify Go callee name format (full selector: "fmt.Println") - Add explicit negative test: macros NOT in callees - Add malformed Rust file resilience test - Add block doc comment (/** */) as known limitation - Update decisions table, risk register, and test strategy Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix PatternMatchRule type to { id, category, query } with @match capture
- Clarify impl_item.type field-based access (remove misleading prose)
- Add generic impl fixture + type param stripping (Container<T> → Container)
- Add pub(crate) visibility to fixture and test
- Add closure callee test (transform inside .map)
- Add field access vs method call test (s.host vs s.host.clone())
- Switch async detection from regex to AST keyword child
- Add Known Limitations (v1) section to overview
- Update risk register and test strategy with new entries
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Workflow-ready MCP tools that compose low-level tools internally. One call replaces 5-10 tool calls, saving 3,000-5,000 context tokens. 4 parts: review adapter, research adapter, CLI commands, docs/agents. No LLM dependency — deterministic structured output. AI assistant adds judgment on top. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Address all review findings: - Reframe: MCP is primary, AI assistant IS the LLM, CLI is secondary - Replace adapter DI with shared analysis services in core - Drop "swarm" terminology — it's parallel query composition - Scope controls emphasis not exclusion (fixes usage/callgraph issue) - Add partial failure behavior (partial report + warnings) - Sharpen tool descriptions for AI disambiguation - Reframe value: thoroughness (we always trace cross-package), not tokens Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…l repo indexing Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
code-reviewer: now plans before delegating. Uses MCP tools to understand the change (impact, hot paths, conventions), then writes specific focused tasks for each specialist instead of blind fan-out. Synthesizes with contradiction resolution. research-planner: now delegates external research to parallel sub-agents. Maps internal territory first (MCP tools), decomposes unknowns into specific research tasks, spawns sub-agents for GitHub/docs/web search, synthesizes with citations from both internal and external sources. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Normalize service file names to *-analysis.ts across all parts - Align overview commit strategy (6 commits) with part-level commits Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…tmatter
S1: code-reviewer passes Phase 1 findings to specialists in task brief
so they skip re-querying dev_refs/dev_map
S2: research-planner clarifies general-purpose is a Claude Code built-in
subagent type (default when no subagent_type specified)
S3: Part 2.4 specifies exact tools: frontmatter changes for each agent
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add prerequisites (Claude Code, dev-agent, Antfly), development workflow using MCP tools, agent system overview, CLI tools reference, and plan-before-build process. Remove generic boilerplate. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Files
All docs, no code changes:
.claude/da-plans/core/phase-5-go-rust-support/(overview + 3 parts).claude/da-plans/README.md🤖 Generated with Claude Code