docs: align documentation with current CLI and MCP surface

Author: tae2089

AGENTS.md

@@ -4,17 +4,14 @@ A local code analysis tool that parses codebases with Tree-sitter and builds a k
 
 ## MCP Server
 
-The ccg MCP server registered in `.mcp.json` provides 33 tools:
+The ccg MCP server registered in `.mcp.json` provides 17 tools:
 
 - `parse_project`, `build_or_update_graph`, `run_postprocess`
-- `get_postprocess_policy`, `reset_postprocess_policy`
 - `get_node`, `search`, `query_graph`, `list_graph_stats`, `list_namespaces`, `get_minimal_context`
 - `get_impact_radius`, `trace_flow`
-- `find_large_functions`, `find_dead_code`
 - `detect_changes`, `get_affected_flows`, `list_flows`
-- `list_communities`, `get_community`, `get_architecture_overview`
 - `get_annotation`
-- `build_rag_index`, `get_rag_tree`, `get_doc_content`, `search_docs`, `retrieve_docs`
+- `get_doc_content`, `search_docs`
 
 `ccg serve` is the local stdio MCP entry point. Self-hosted HTTP mode is provided by
 the separate `ccg-server` binary, which serves `/mcp`, `/health`, `/ready`, `/status`,
@@ -30,10 +27,10 @@ Graceful shutdown: SIGINT/SIGTERM propagates context cancellation to in-progress
 | Skill            | Description                                                         |
 | ---------------- | ------------------------------------------------------------------- |
 | `/ccg`           | Core build and search: parsing, graph build, query, search          |
-| `/ccg-analyze`   | Code analysis: impact radius, flow tracing, dead code, architecture |
+| `/ccg-analyze`   | Code analysis: impact radius, flow tracing, and change risk         |
 | `/ccg-annotate`  | Annotation system: AI annotation workflow and tag reference         |
-| `/ccg-docs`      | Documentation: doc generation, RAG indexing, lint                   |
-| `/ccg-namespace` | Namespace file management: upload, list, delete                     |
+| `/ccg-docs`      | Documentation: generation, DB-backed discovery, and lint            |
+| `/ccg-namespace` | Namespace isolation for multi-project graph data                    |
 
 Skill files are located under `skills/` and are written so coding agents such as Codex and Claude Code
 can use them as slash-command style workflows.
@@ -43,8 +40,7 @@ Main commands:
 - `ccg build [dir]` - build the code graph (supports `--exclude`, `--no-recursive`)
 - `ccg serve` - start the local MCP server over stdio
 - `ccg-server` - start the self-hosted HTTP MCP/webhook server
-- `ccg docs [--out dir]` - generate Markdown documentation and the default RAG index
-- `ccg rag-index [--out dir]` - build a RAG index from precomputed communities and generated docs
+- `ccg docs [--out dir]` - generate Markdown documentation and the Wiki compatibility index
 - `ccg search <query>` - full-text search (includes annotations)
 - `ccg lint [--strict]` - check documentation quality
 - `/ccg-annotate annotate [file|dir]` - AI annotation generation workflow
@@ -57,18 +53,18 @@ Use `.ccg.yaml` to manage project defaults such as exclude patterns and DB setti
 When looking for code locations, related implementations, call relationships, impact radius, or architecture context,
 use ccg MCP tools and Agent Skills first.
 
-- For natural-language code understanding, module exploration, and architecture context, prefer the `/ccg-docs` skill: use `search_docs` to find relevant docs, then `get_doc_content` to read one (with `get_rag_tree` for module context).
+- For natural-language code understanding and module exploration, prefer the `/ccg-docs` skill: use `search_docs` to find relevant docs, then `get_doc_content` to read one.
 - For exact symbol locations, call relationships, and graph metadata, use ccg MCP `query_graph`, `get_node`, `get_minimal_context`, or the `/ccg` skill.
 - For annotation/keyword-based candidate search, use ccg MCP `search` or `ccg search` as a supplement.
-- For impact radius, flows, dead code, and structural analysis, prefer the `/ccg-analyze` skill and related MCP tools (`get_impact_radius`, `trace_flow`, `find_dead_code`, `get_architecture_overview`).
+- For impact radius, flows, and change-risk analysis, prefer the `/ccg-analyze` skill and related MCP tools (`get_impact_radius`, `trace_flow`, `detect_changes`, `get_affected_flows`).
 - For simple string checks, file existence checks, or cases where the ccg index is missing or stale, use `rg` as a supplement. If needed, refresh the graph with `ccg build .` or `ccg update .`.
 
 ## Documentation
 
 See the `guide/` directory for detailed documentation:
 
 - [CLI Reference](guide/cli-reference.md) - all commands, flags, and config files
-- [MCP Tools](guide/mcp-tools.md) - 33 MCP tools, Agent Skills, AI-Driven Annotation
+- [MCP Tools](guide/mcp-tools.md) - 17 MCP tools, Agent Skills, AI-Driven Annotation
 - [Annotations](guide/annotations.md) - annotation tags, examples, and search
 - [Webhook](guide/webhook.md) - webhook sync, branch filtering, HMAC, graceful shutdown
 - [Docker](guide/docker.md) - Docker builds, MCP server, PostgreSQL deployment

README.md

@@ -1,6 +1,6 @@
 # code-context-graph
 
-Local code analysis tool that parses codebases via Tree-sitter into a knowledge graph. Supports 12 languages, 33 MCP tools, and custom annotation search.
+Local code analysis tool that parses codebases via Tree-sitter into a knowledge graph. Supports 12 languages, 17 MCP tools, and custom annotation search.
 
 CCG is built primarily for GPT, Claude, Codex, and other LLM-based coding agents. It acts as local or self-hosted context infrastructure: agents can search code by intent, inspect call graphs, trace impact, retrieve docs, and keep responses bounded instead of reading entire repositories into context.
 
@@ -11,12 +11,11 @@ Inspired by [code-review-graph](https://github.com/tirth8205/code-review-graph)
 ## Features
 
 - **12 languages**: Go, Python, TypeScript, Java, Ruby, JavaScript, C, C++, Rust, Kotlin, PHP, Lua/Luau
-- **33 MCP tools**: parse, search, impact analysis, flow tracing, dead code detection, postprocess operations, namespace file management, and more
+- **17 MCP tools**: parse, search, graph queries, impact analysis, flow tracing, change detection, documentation discovery, and more
 - **Evidence-driven code exploration**: DB-backed retrieval returns small file-level candidates with matched fields, evidence nodes, and optional docs before agents drill into exact graph nodes
 - **Browser Wiki UI**: `ccg-server` can serve generated docs, tree search, DB-backed retrieval, Context Tray copying, and an Obsidian-style graph viewer
 - **Custom annotations**: `@intent`, `@domainRule`, `@sideEffect`, `@mutates`, `@index` — search code by business context ([details](guide/annotations.md))
 - **Webhook sync**: GitHub / Gitea push events → auto clone + build with per-repo branch filtering and `.ccg.yaml` `include_paths` auto-loading ([details](guide/webhook.md))
-- **Eval**: Golden corpus-based parser accuracy (P/R/F1) and search quality (P@K, MRR, nDCG) evaluation ([details](guide/eval.md))
 - **Multi-DB**: SQLite (local), PostgreSQL
 - **Full-text search**: FTS5 (SQLite), tsvector+GIN (PostgreSQL)
 
@@ -66,7 +65,7 @@ ccg search "authentication"
 # Search by business context
 ccg search "payment"    # finds functions with @intent/@domainRule about payments
 
-# Build docs and the default vectorless RAG index for agent-oriented exploration
+# Build generated docs and the browser Wiki compatibility index
 ccg docs --out docs
 
 # Serve the browser Wiki UI from built assets; builds the graph for DB-backed APIs
@@ -82,22 +81,13 @@ ccg version
 ccg build ./backend --namespace backend
 ccg search --namespace backend "auth"
 
-# Evaluate parser accuracy (12 languages)
-ccg eval --suite parser
-
-# Update golden corpus
-ccg eval --suite parser --update
 ```
 
 `ccg docs` writes generated Markdown plus `.ccg/wiki-index.json` as a browser
 Wiki compatibility snapshot. The Wiki prefers the graph database for tree
 navigation and search, then uses `wiki-index.json` only when DB-backed
-navigation is unavailable. By default `ccg docs` also refreshes community
-structure and writes `.ccg/doc-index.json` as a compatibility snapshot for
-manual RAG-index workflows; runtime `search_docs` uses DB-backed graph and
-annotation evidence. Use `--rag=false` when you only want Markdown and the Wiki
-snapshot, or `--rag-refresh=false` when you want to rebuild the RAG index from
-existing community rows without recalculating communities.
+navigation is unavailable. Runtime `search_docs` uses DB-backed graph and
+annotation evidence; it does not depend on a separately generated retrieval index.
 
 For LLM agents, use DB-backed `search_docs` as the first stop for broad
 natural-language questions such as "how does webhook sync work?" or "where are
@@ -140,9 +130,8 @@ Local development shortcut:
 make wiki-run
 ```
 
-Use `make wiki-run-indexed` when you also want generated Markdown,
-`wiki-index.json` snapshot, and the compatibility `doc-index.json` before
-starting the server.
+Use `make wiki-run-indexed` when you also want generated Markdown and the
+`wiki-index.json` compatibility snapshot before starting the server.
 
 For self-hosted deployments, run `ccg-server --wiki-dir <dist-dir>` and protect
 `/wiki/api/*` with the same bearer token policy used for `/mcp`. See
@@ -262,7 +251,7 @@ server can also expose `/wiki` when `--wiki-dir` is configured:
 ```
 
 MCP-capable clients such as Codex or Claude Code can connect and get access to
-33 MCP tools. See [MCP Tools Reference](guide/mcp-tools.md) for the full list.
+17 MCP tools. See [MCP Tools Reference](guide/mcp-tools.md) for the full list.
 
 ## Architecture
 
@@ -288,14 +277,12 @@ See [Architecture Details](guide/architecture.md) for component breakdown and DB
 |-------|-------------|
 | [Korean Guide](guide/ko/README.md) | 한국어 문서 인덱스 (Korean Documentation Index) |
 | [CLI Reference](guide/cli-reference.md) | All commands, flags, and config file (`.ccg.yaml`) |
-| [Eval](guide/eval.md) | Parser/search quality evaluation, golden corpus, and metrics |
 | [Lint](guide/lint.md) | Detailed `ccg lint` category reference, interpretation guide, and CI usage |
-| [MCP Tools](guide/mcp-tools.md) | 33 MCP tools, agent skills, AI-Driven Annotation |
+| [MCP Tools](guide/mcp-tools.md) | 17 MCP tools, agent skills, AI-Driven Annotation |
 | [Annotations](guide/annotations.md) | Annotation system — tags, examples, search |
 | [Webhook](guide/webhook.md) | Webhook sync, branch filtering, HMAC, graceful shutdown |
 | [Docker](guide/docker.md) | Docker build, MCP server, Wiki UI, PostgreSQL deployment |
 | [Operations](guide/operations.md) | Deployment profiles, database choice, readiness, webhook operations |
-| [Postprocess Failure Policy](guide/postprocess-failure-policy.md) | Status rules, failure causes, and automatic degraded/fail_closed policy for build and postprocess tools |
 | [Runtime Layout](guide/runtime-layout.md) | `ccg`, `ccg-server`, Wiki serving, and shared `ccg-core` ownership boundaries |
 | [Development](guide/development.md) | Dev guide, integration test, project structure |
 | [Namespace Migration](guide/namespace-migration.md) | Default namespace change and migration guide |

guide/README.md

@@ -3,26 +3,25 @@
 Documentation index for code-context-graph.
 
 For LLM-agent workflows, start natural-language code exploration from the
-docs/RAG path: use `search_docs` to find relevant docs, then `get_doc_content`
+generated-docs path: use `search_docs` to find relevant docs, then `get_doc_content`
 to read one. Treat these as an evidence-driven narrowing layer, not a Top1
 search engine: use the small file-level candidates to choose the shortest route
 into docs or graph tools.
 
 The browser Wiki is served by `ccg-server` when `--wiki-dir` points at built
 React assets. It prefers the graph database for presentation, uses
 `wiki-index.json` as a compatibility tree snapshot, and uses `/wiki/api/graph`
-for the visual graph tab. Runtime retrieve mode uses DB-backed graph and
-annotation evidence. Use it when a human developer needs to browse docs,
+for the visual graph tab. Runtime documentation search uses DB-backed graph and
+annotation evidence. Use the Wiki when a human developer needs to browse docs,
 inspect annotation-rich symbol cards, collect Context Tray Markdown, or visually
 explore graph edges.
 
 | Document | Description |
 |----------|-------------|
 | [CLI Reference](cli-reference.md) | Full CLI commands, options, and configuration file (`.ccg.yaml`) |
-| [Eval](eval.md) | Parser/search quality evaluation, golden corpus, and metrics |
 | [Lint](lint.md) | Detailed `ccg lint` category reference, interpretation guide, and CI usage |
-| [MCP Tools](mcp-tools.md) | 33 MCP tools, agent skills, evidence-first routing, AI-driven annotation |
-| [Annotations](annotations.md) | Custom annotation system — tags, examples, search/RAG quality |
+| [MCP Tools](mcp-tools.md) | 17 MCP tools, agent skills, evidence-first routing, AI-driven annotation |
+| [Annotations](annotations.md) | Custom annotation system — tags, examples, and search quality |
 | [Webhook](webhook.md) | GitHub / Gitea webhook sync, branch filtering, graceful shutdown |
 | [Docker](docker.md) | Docker image build, MCP server setup, Wiki UI deployment, PostgreSQL integration |
 | [Operations](operations.md) | Deployment profiles, database choice, readiness, webhook operations, troubleshooting |

guide/annotations.md

@@ -1,13 +1,12 @@
 # Custom Annotations
 
-Add structured metadata to your code so that AI, generated docs, RAG, and
-focused search can leverage business context. Annotations are indexed for
-`ccg search` and are also rendered into generated Markdown that feeds the RAG
-index.
+Add structured metadata to your code so that AI, generated docs, and focused
+search can leverage business context. Annotations are indexed for `ccg search`
+and are also rendered into generated Markdown.
 
-For LLM-agent natural-language exploration, prefer the docs/RAG path first:
+For LLM-agent natural-language exploration, prefer the generated-docs path first:
 `ccg docs`, then use MCP `search_docs` to find relevant docs and `get_doc_content`
-to read one (with `get_rag_tree` for module context). Use `ccg search` when you
+to read one. Use `ccg search` when you
 need a focused list of annotation/keyword-matched symbol candidates.
 
 Annotation quality is validated by `ccg lint`. For category meanings such as `unannotated`, `incomplete`, `dead-ref`, `contradiction`, and `drifted`, see [Lint Guide](lint.md).

guide/architecture.md

@@ -49,8 +49,7 @@ pure incremental-update workflow only refreshes changed nodes, leaving
 untouched nodes without sub-tokens until they change.
 
 Full builds and explicit postprocess runs rebuild namespace search state.
-Incremental updates refresh only affected search documents and FTS rows, while
-community postprocessing can still be namespace-wide. Persisted stored-flow
+Incremental updates refresh only affected search documents and FTS rows. Persisted stored-flow
 rebuild is implemented for full postprocess runs and explicit
 `run_postprocess(flows=true)` calls; use `trace_flow` for per-entry-point flow
 queries.
@@ -65,18 +64,9 @@ queries.
 | `query` | Graph queries (callers, callees, imports) |
 | `incremental` | Incremental update |
 
-### Eval (`internal/eval/`)
-
-Golden corpus-based parser accuracy and search quality evaluation framework.
-
-- **Parser eval**: Parses 12-language source files and compares against golden JSON to compute Node/Edge P/R/F1
-- **Search eval**: Computes P@K, MRR, nDCG metrics for query corpus
-- **Golden update**: `--update` mode saves current parser output as golden files
-- **Corpus**: `testdata/eval/` directory with per-language sources + golden JSON + queries.json
-
 ### MCP Server (`internal/mcp/`)
 
-Exposes 33 tools via MCP protocol. The local `ccg serve` command exposes these
+Exposes 17 tools via MCP protocol. The local `ccg serve` command exposes these
 tools over stdio. The self-hosted `ccg-server` binary exposes the same tool
 surface over Streamable HTTP and adds health/status/webhook endpoints.
 

guide/claude-md-guide.md

@@ -25,8 +25,9 @@ get_minimal_context          ← always start here (graph state + recommended to
         │                   → get_impact_radius(qualified_name: "...", depth: 3)
         │                   → get_affected_flows(repo_root: ".")
         │
-        ├─ understand structure → get_architecture_overview()
-        │                          → list_communities()
+        ├─ understand structure → search_docs()
+        │                          → get_doc_content()
+        │                          → query_graph(file_summary)
         │
         └─ after code change → build_or_update_graph(path: ".", full_rebuild: false)
 ```