feat: v0.5.0 — navigation + risk positioning, 15→13 tools#6
Merged
rushikeshmore merged 2 commits intomainfrom Mar 8, 2026
Merged
feat: v0.5.0 — navigation + risk positioning, 15→13 tools#6rushikeshmore merged 2 commits intomainfrom
rushikeshmore merged 2 commits intomainfrom
Conversation
Response size caps: all read tools now use size-adaptive limits based on project classification (micro/small/medium/large/extra-large). Responses stay under 10K chars on large repos. detail="brief"|"full" flag on 7 tools. Search rewrite: 3-tier ranked search (symbols→files→docs) with kind bonus, export bonus, and local variable demotion. Exported functions rank above local const assignments. Agent onboarding: generates .codecortex/AGENT.md with tool guide, appends pointer to CLAUDE.md/.cursorrules/.windsurfrules/copilot-instructions.md. New files: project-size.ts (classification + limits), truncate.ts (response helpers), agent-instructions.ts (onboarding), SECURITY.md, CI workflow. Init improvements: compact overview.md (directory summary, not raw file listing), step 7 agent instructions, MCP connection commands in output. 277 tests pass, tsc clean. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…dated claims Repositions CodeCortex from "persistent codebase memory" to "codebase navigation and risk layer" based on 3 rounds of agent comparison testing on a 6,400-file repo. Key changes: - Tools 15→13: removed analyze_module + save_module_analysis, renamed report_feedback → record_observation - AGENT.md rewritten: "CodeCortex finds WHERE to look. You still read the code." - README rewritten with real test data (~50% fewer tokens, 2.5x fewer tool calls, same quality 23/25 vs 23/25) - CLI modules command capped at 30 edges (was 559KB for large modules) - Dropped unvalidated "85% token reduction" claim - All 276 tests pass, tsc clean, build succeeds Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
|
You are seeing this message because GitHub Code Scanning has recently been set up for this repository, or this pull request contains the workflow file for the Code Scanning tool. What Enabling Code Scanning Means:
For more information about GitHub Code Scanning, check out |
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
analyze_module+save_module_analysis, renamedreport_feedback→record_observationmodules <name>output capped at 30 edges (was dumping 559KB for large modules)Validated Test Data (Round 3 apples-to-apples)
Files Changed (14)
README.md— full rewrite with new positioning + real dataCLAUDE.md— tool list 15→13package.json— description updatedsrc/mcp/tools/write.ts— removed 2 tools, renamed 1, renumberedsrc/core/agent-instructions.ts— AGENT_INSTRUCTIONS rewritesrc/cli/commands/modules.ts— EDGE_CAP=30 for CLI outputsrc/mcp/server.ts— tool count + descriptionsrc/mcp/tools/read.ts— tool description updatessrc/core/module-gen.ts,src/utils/truncate.ts— reference updatesTest plan
tsc --noEmit— cleannpm test— 276/276 passnpm run build— success🤖 Generated with Claude Code