Files
yvgude--lean-ctx/AGENTS.md
T
wehub-resource-sync 26382a7ac6
CI / Clippy (push) Failing after 15m13s
CI / Test (ubuntu-latest) (push) Failing after 16m1s
CI / Test (macos-latest) (push) Has been cancelled
CI / Test (windows-latest) (push) Has been cancelled
CI / Build (no embeddings / no ORT) (push) Has been cancelled
CI / Format (push) Has been cancelled
CI / Cookbook (Node) (push) Has been cancelled
CI / Pi Extension (Node) (push) Has been cancelled
CI / Rust SDK (lean-ctx-client) (push) Has been cancelled
CI / Embed SDK (lean-ctx-sdk) (push) Has been cancelled
CI / Python SDK (leanctx) (push) Has been cancelled
CI / Hermes Plugin (Python) (push) Has been cancelled
CI / SDK Conformance Matrix (push) Has been cancelled
CI / Coverage (push) Has been cancelled
CI / cargo-deny (push) Has been cancelled
CI / Adversarial Safety (push) Has been cancelled
CI / Benchmarks (push) Has been cancelled
CI / Output-Quality Gate (eval A/B) (push) Has been cancelled
CI / Documentation (push) Has been cancelled
CI / CI Green (push) Has been cancelled
JetBrains Plugin / Actionlint (push) Has been cancelled
CodeQL / Analyze (actions) (push) Has been cancelled
CodeQL / Analyze (javascript-typescript) (push) Has been cancelled
CodeQL / Analyze (rust) (push) Has been cancelled
JetBrains Plugin / Validation (push) Has been cancelled
JetBrains Plugin / Build (push) Has been cancelled
JetBrains Plugin / Test (push) Has been cancelled
Security Check / Security Scan (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:35:30 +08:00

5.0 KiB

Context Engineering Layer

lean-ctx optimizes LLM context by compressing file reads, shell output, and search results.

Integration Mode: Replace

Native Read/Grep/Glob/Shell are denied by policy. lean-ctx MCP tools are the only path for reading files and running commands:

  • Reads/Searchctx_read, ctx_search, ctx_compose (cached, 10 modes)
  • Shell commandsctx_shell (95+ compression patterns)
  • File editing → native Edit/StrReplace (lean-ctx only handles READ operations)
  • File findingctx_glob, ctx_tree

Native tools will return a deny error with instructions to use ctx_* equivalents. Override: set hook_mode = "hybrid" in ~/.config/lean-ctx/config.toml.

Subagent Compatibility (Cursor / Claude Code)

Cursor blocks MCP tools in readonly: true subagents (Task tool). lean-ctx tools are MCP tools → they WILL FAIL in readonly subagents.

Rules for spawning subagents:

  • Always set readonly: false when the subagent needs ctx_* tools
  • Use subagent_type: "generalPurpose" — NOT "explore" (always readonly)
  • lean-ctx tools declare readOnlyHint: true in MCP annotations

Fallback (MCP unavailable): deny hook detects MCP-down and allows native tools.

CLI commands (optimized shell, lower overhead)

git status                   # compressed by configured agent shell/wrapper
cargo test                   # compressed by configured agent shell/wrapper
lean-ctx -c "git status"     # only if explicitly requested / documented unwrapped
lean-ctx ls src/              # directory map

Development Workflow

When working on lean-ctx itself:

  1. Before building: lean-ctx stop (LaunchAgent respawns otherwise)
  2. Build: cd rust && cargo build --release
  3. Test: cargo test --lib + cargo clippy -- -W clippy::all
  4. Install: lean-ctx dev-install (atomic stop→build→install→restart)

Session Continuity

lean-ctx automatically persists session context across restarts:

  • Findings: Recent tool results (reads, searches, test outcomes)
  • Decisions: Architecture choices made during the session
  • Files: Touched files with summaries and modification status
  • Progress: Task completion state and next steps

This data is delivered through the first tool call's --- AUTO CONTEXT --- briefing (default minimal_overhead = true: initialize instructions stay byte-stable for provider prompt caching, #498). With minimal_overhead = false it is additionally injected at session start via the ACTIVE SESSION LITM block.

Active Documentation (Agent Responsibility)

After completing a significant task (implementation, bugfix, refactoring):

  1. Record the decision: ctx_knowledge(action="remember", category="decision", content="...")
  2. Record progress: ctx_session(action="task", value="<current task> [N%]")
  3. Record blockers: ctx_knowledge(action="remember", category="blocker", content="...")

After 30+ tool calls without documentation:

  • lean-ctx will prompt with [CHECKPOINT: please document current progress]
  • Respond by calling ctx_session(action="task") with current status

Provider Pipeline (Context Engine)

External data sources (GitHub, GitLab, Jira, Postgres, MCP bridges, custom REST) are first-class citizens. All provider data flows through the same consolidation pipeline:

  1. ContextProvider::execute() → raw ProviderResult
  2. consolidation::consolidate()ConsolidationArtifacts (BM25 chunks, graph edges, knowledge facts, cache entries)
  3. apply_artifacts_to_stores() → persists to BM25 index, Graph index, ProjectKnowledge, Session cache (background thread)

This means ctx_semantic_search finds issues/PRs/tickets, ctx_knowledge recalls provider facts, and ctx_read shows cross-source hints (e.g. "Issue #42 references this file").

Quality Bar

  • Zero clippy warnings, all tests pass
  • Security: PathJail, Shell Allowlist, bounded_lock, no hardcoded secrets
  • No mock data, no placeholders, no stubs

Output Determinism (#498)

Tool outputs MUST be deterministic functions of (file content, mode, CRP mode, task). Provider-side prompt caching (Anthropic 90%, OpenAI 50% discount) rewards byte-stable text; any timestamp, counter or random element in tool output bodies defeats it.

  • No timestamps/counters in output bodies. Artifact paths are content-addressed (see save_tee: {cmd_slug}_{blake3(cmd)[..8]}.log).
  • Dynamic additions (hints, checkpoints) only as state-triggered suffixes with stable headers.
  • Regression guard: determinism tests in ctx_read/tests.rs, ctx_search.rs, shell/redact.rs.

lean-ctx

lean-ctx is active — the MCP tools replace native equivalents. Full rules: LEAN-CTX.md (open on demand — do not auto-load).

OUTPUT STYLE: concise

  • Bullet points over paragraphs
  • Skip filler words and hedging ("I think", "probably", "it seems")
  • 1-sentence explanations max, then code/action
  • No repeating what the user said