Add: R (.r/.R) language support via bespoke extract_r

README.md

@@ -259,6 +259,7 @@ Codex users also need `multi_agent = true` under `[features]` in `~/.codex/confi
 | `terraform` | Terraform / HCL `.tf`/`.tfvars`/`.hcl` AST extraction | `uv tool install "graphifyy[terraform]"` |
 | `pascal` | Pascal / Delphi `.pas`/`.dpr`/`.dpk`/`.inc` AST extraction (more accurate `calls`/`inherits` edges; falls back to a regex extractor when absent) | `uv tool install "graphifyy[pascal]"` |
 | `chinese` | Chinese query segmentation (jieba) | `uv tool install "graphifyy[chinese]"` |
+| `r` | R `.r`/`.R` AST extraction (functions, calls, imports, static `source()`); ships via `tree-sitter-language-pack` which may fetch/cache the R grammar on first use (no source uploaded, R not executed) | `uv tool install "graphifyy[r]"` |
 | `all` | Everything above | `uv tool install "graphifyy[all]"` |
 
 </details>
@@ -327,7 +328,7 @@ To remove graphify from all platforms at once: `graphify uninstall` (add `--purg
 
 | Type | Extensions |
 |------|-----------|
-| Code (36 tree-sitter grammars) | `.py .ts .mts .cts .js .jsx .tsx .mjs .go .rs .java .c .cpp .cc .cxx .h .hpp .cu .cuh .metal .rb .cs .kt .kts .scala .php .swift .lua .luau .toc .zig .ps1 .psm1 .psd1 .ex .exs .m .mm .jl .vue .svelte .astro .groovy .gradle .dart .v .sv .svh .sql .f .f90 .f95 .f03 .f08 .pas .pp .dpr .dpk .lpr .inc .dfm .lfm .lpk .sh .bash .json .dm .dme .dmi .dmm .dmf .sln .slnx .csproj .fsproj .vbproj .xaml .razor .cshtml` (`.dm`/`.dme` requires `uv tool install graphifyy[dm]`; `.mts`/`.cts` reuse the TypeScript grammar, `.cc`/`.cxx` and CUDA `.cu`/`.cuh` and Metal `.metal` reuse the C++ grammar) |
+| Code (37 tree-sitter grammars) | `.py .ts .mts .cts .js .jsx .tsx .mjs .go .rs .java .c .cpp .cc .cxx .h .hpp .cu .cuh .metal .rb .cs .kt .kts .scala .php .swift .lua .luau .toc .zig .ps1 .psm1 .psd1 .ex .exs .m .mm .jl .r .R .vue .svelte .astro .groovy .gradle .dart .v .sv .svh .sql .f .f90 .f95 .f03 .f08 .pas .pp .dpr .dpk .lpr .inc .dfm .lfm .lpk .sh .bash .json .dm .dme .dmi .dmm .dmf .sln .slnx .csproj .fsproj .vbproj .xaml .razor .cshtml` (`.dm`/`.dme` requires `uv tool install graphifyy[dm]`; `.r`/`.R` requires `uv tool install "graphifyy[r]"`; `.mts`/`.cts` reuse the TypeScript grammar, `.cc`/`.cxx` and CUDA `.cu`/`.cuh` and Metal `.metal` reuse the C++ grammar) |
 | Salesforce Apex | `.cls .trigger` (regex-based; classes, interfaces, enums, methods, triggers, SOQL/DML edges) |
 | Terraform / HCL | `.tf .tfvars .hcl` (requires `uv tool install graphifyy[terraform]`) |
 | MCP configs | `.mcp.json` `mcp.json` `mcp_servers.json` `claude_desktop_config.json` — extracts server nodes, package refs, env var requirements |
@@ -835,8 +836,8 @@ See [ARCHITECTURE.md](ARCHITECTURE.md) for module responsibilities and how to ad
 ---
 
 <p align="center">
-  <a href="https://star-history.com/#safishamsi/graphify&Date">
-    <img src="https://api.star-history.com/svg?repos=safishamsi/graphify&type=Date" alt="Star History Chart" width="370"/>
+  <a href="https://star-history.com/#Graphify-Labs/graphify&Date">
+    <img src="https://api.star-history.com/svg?repos=Graphify-Labs/graphify&type=Date" alt="Star History Chart" width="370"/>
   </a>
 </p>
 
@@ -846,7 +847,7 @@ See [ARCHITECTURE.md](ARCHITECTURE.md) for module responsibilities and how to ad
 
 <p align="center">
   <a href="https://discord.gg/598Ad9zQZ"><img src="https://img.shields.io/badge/Discord-Join-5865F2?style=flat&logo=discord&logoColor=white" alt="Discord"/></a>
-  <a href="https://x.com/graphifyy"><img src="https://img.shields.io/badge/X-graphifyy-000000?logo=x&logoColor=white" alt="X"/></a>
+  <a href="https://x.com/graphify"><img src="https://img.shields.io/badge/X-graphify-000000?logo=x&logoColor=white" alt="X"/></a>
   <a href="https://github.com/sponsors/safishamsi"><img src="https://img.shields.io/badge/sponsor-safishamsi-ea4aaa?logo=github-sponsors" alt="Sponsor"/></a>
   <a href="https://safishamsi.gumroad.com/l/qetvlo"><img src="https://img.shields.io/badge/Book-The%20Memory%20Layer-2ea44f?style=flat&logo=gitbook&logoColor=white" alt="The Memory Layer"/></a>
 </p>

graphify/__main__.py

@@ -174,7 +174,7 @@ def _check_skill_version(skill_dst: Path) -> None:
     except OSError:
         return
     if not skill_exists:
-        print("  warning: skill dir exists but SKILL.md is missing. Run 'graphify install' to repair.")
+        print("  warning: skill dir exists but SKILL.md is missing. Run 'graphify install' to repair.", file=sys.stderr)
         return
     # A progressive SKILL.md links to its references/ sidecar. If the body points
     # at references/ but the dir is gone (manual delete, partial upgrade), the
@@ -597,6 +597,8 @@ def _run_cli() -> None:
         print("                            proxy, gateways): set ANTHROPIC_BASE_URL and ANTHROPIC_MODEL")
         print("    --model M               override backend default model")
         print("    --mode deep             aggressive INFERRED-edge semantic extraction")
+        print("    --force                 full re-scan and re-dispatch: skip the incremental")
+        print("                            manifest gate and semantic cache reads (env: GRAPHIFY_FORCE=1)")
         print("    --max-workers N         AST extraction subprocess count (default: cpu_count)")
         print("    --token-budget N        per-chunk token cap for semantic extraction (default: 60000)")
         print("    --max-concurrency N     parallel semantic chunks in flight (default: 4; set 1 for local LLMs)")

graphify/analyze.py

@@ -23,7 +23,7 @@
 # Language families — extensions sharing a runtime can legitimately call each other
 _LANG_FAMILY: dict[str, str] = {
     **{e: "python" for e in (".py", ".pyw")},
-    **{e: "js" for e in (".js", ".jsx", ".mjs", ".ejs", ".ts", ".tsx", ".mts", ".cts", ".vue", ".svelte")},
+    **{e: "js" for e in (".js", ".jsx", ".mjs", ".cjs", ".ejs", ".ts", ".tsx", ".mts", ".cts", ".vue", ".svelte")},
     **{e: "go" for e in (".go",)},
     **{e: "rust" for e in (".rs",)},
     **{e: "jvm" for e in (".java", ".kt", ".kts", ".scala")},

graphify/build.py

@@ -287,6 +287,16 @@ def _semantic_id_remap(nodes: list, root: str | None) -> dict:
         if not new_stem:
             continue
         norm_nid = _normalize_id(nid)
+        # Idempotency guard (#1917): an id already carrying its canonical stem is
+        # done — do not re-run the legacy branch on it. When the canonical stem
+        # contains a shorter legacy stem as a prefix (parent dir name == file
+        # stem, e.g. `.claude/CLAUDE.md` -> `claude_claude` over legacy `claude`),
+        # an already-migrated id like `claude_claude_x` still matches the legacy
+        # `claude_` prefix below and would gain another stem segment on every
+        # build, defeating the same_topology/no_change short-circuits. Mirrors the
+        # canonical check in graph_has_legacy_ids.
+        if norm_nid == new_stem or norm_nid.startswith(new_stem + "_"):
+            continue
         new_id: str | None = None
         for old_stem in _old_file_stems(rel):
             if old_stem == new_stem:
@@ -755,10 +765,43 @@ def build_from_json(extraction: dict, *, directed: bool = False, root: str | Pat
         # Relativize hyperedge source_file the same way nodes and edges are
         # (above), so to_json — which has no root and writes G.graph["hyperedges"]
         # verbatim — never leaks an absolute path from a semantic subagent (#1418).
+        kept_hyperedges = []
         for he in hyperedges:
             if isinstance(he, dict) and he.get("source_file"):
                 he["source_file"] = _norm_source_file(he["source_file"], _root)
-        G.graph["hyperedges"] = hyperedges
+            # Validate members against the built node set (#1916): a hyperedge
+            # member absent from the graph used to be copied into
+            # G.graph["hyperedges"] verbatim and reach graph.json dangling,
+            # even from a live (non-cache) extraction. Mirror the pairwise-edge
+            # handling above: remap mismatched ids via normalization first,
+            # then drop members that still don't resolve; drop the hyperedge
+            # itself when no valid member remains (single-member hyperedges
+            # are legal in this codebase, e.g. a per-file flow, so we prune
+            # rather than require two survivors).
+            if isinstance(he, dict) and isinstance(he.get("nodes"), list):
+                valid_members = []
+                for m in he["nodes"]:
+                    try:
+                        hash(m)
+                    except TypeError:
+                        continue
+                    if m not in node_set and isinstance(m, str):
+                        m = norm_to_id.get(_normalize_id(m), m)
+                    if m in node_set:
+                        valid_members.append(m)
+                if not valid_members:
+                    print(
+                        f"[graphify] WARNING: dropping hyperedge "
+                        f"{he.get('id', '?')!r} — none of its members "
+                        f"{he.get('nodes')!r} match built nodes.",
+                        file=sys.stderr,
+                    )
+                    continue
+                if valid_members != he["nodes"]:
+                    he["nodes"] = valid_members
+            kept_hyperedges.append(he)
+        if kept_hyperedges:
+            G.graph["hyperedges"] = kept_hyperedges
     return G