diffctx 1.10.0__tar.gz → 1.10.1__tar.gz

{diffctx-1.10.0 → diffctx-1.10.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: diffctx
-Version: 1.10.0
+Version: 1.10.1
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers

{diffctx-1.10.0 → diffctx-1.10.1}/diffctx/Cargo.lock

@@ -355,12 +355,6 @@ version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
 
-[[package]]
-name = "hermit-abi"
-version = "0.5.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fc0fef456e4baa96da950455cd02c081ca953b141298e41db3fc7e36b1da849c"
-
 [[package]]
 name = "id-arena"
 version = "2.3.0"
@@ -411,23 +405,23 @@ checksum = "52ff2c0fe9bc6cb6b14a0592c2ff4fa9ceb83eea9db979b0487cd054946a2b8f"
 
 [[package]]
 name = "libmimalloc-sys"
-version = "0.1.47"
+version = "0.1.49"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2d1eacfa31c33ec25e873c136ba5669f00f9866d0688bea7be4d3f7e43067df6"
+checksum = "6a45a52f43e1c16f667ccfe4dd8c85b7f7c204fd5e3bf46c5b0db9a5c3c0b8e9"
 dependencies = [
  "cc",
 ]
 
 [[package]]
 name = "libtest-mimic"
-version = "0.7.3"
+version = "0.8.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cc0bda45ed5b3a2904262c1bb91e526127aa70e7ef3758aba2ef93cf896b9b58"
+checksum = "14e6ba06f0ade6e504aff834d7c34298e5155c6baca353cc6a4aaff2f9fd7f33"
 dependencies = [
+ "anstream",
+ "anstyle",
  "clap",
  "escape8259",
- "termcolor",
- "threadpool",
 ]
 
 [[package]]
@@ -459,9 +453,9 @@ checksum = "f8ca58f447f06ed17d5fc4043ce1b10dd205e060fb3ce5b979b8ed8e59ff3f79"
 
 [[package]]
 name = "mimalloc"
-version = "0.1.50"
+version = "0.1.52"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b3627c4272df786b9260cabaa46aec1d59c93ede723d4c3ef646c503816b0640"
+checksum = "2d4139bb28d14ad1facf21d5eb8825051b326e172d216b39f6d31df53cc97862"
 dependencies = [
  "libmimalloc-sys",
 ]
@@ -475,16 +469,6 @@ dependencies = [
  "windows-sys",
 ]
 
-[[package]]
-name = "num_cpus"
-version = "1.17.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "91df4bbde75afed763b708b7eee1e8e7651e02d97f6d5dd763e89367e957b23b"
-dependencies = [
- "hermit-abi",
- "libc",
-]
-
 [[package]]
 name = "once_cell"
 version = "1.21.4"
@@ -622,9 +606,9 @@ dependencies = [
 
 [[package]]
 name = "regex"
-version = "1.12.3"
+version = "1.12.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e10754a14b9137dd7b1e3e5b0493cc9171fdd105e0ab477f51b72e7f3ac0e276"
+checksum = "f1292b7759ae1cb9ec195452d1390a074f0cd8541ab7a5a8c31cd6db45d4a6ba"
 dependencies = [
  "aho-corasick",
  "memchr",
@@ -645,9 +629,9 @@ dependencies = [
 
 [[package]]
 name = "regex-syntax"
-version = "0.8.10"
+version = "0.8.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dc897dd8d9e8bd1ed8cdad82b5966c3e0ecae09fb1907d58efaa013543185d0a"
+checksum = "d6f6ff9a378485b298a5286656da665ba74413d36db0979633275d2e708145d4"
 
 [[package]]
 name = "rustc-hash"
@@ -721,9 +705,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.149"
+version = "1.0.150"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "83fc039473c5595ace860d8c4fafa220ff474b3fc6bfdb4293327f1a37e94d86"
+checksum = "e8014e44b4736ed0538adeecded0fce2a272f22dc9578a7eb6b2d9993c74cfb9"
 dependencies = [
  "indexmap",
  "itoa",
@@ -772,9 +756,9 @@ dependencies = [
 
 [[package]]
 name = "smallvec"
-version = "1.15.1"
+version = "1.15.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "67b1b7a3b5fe4f1376887184045fcf45c69e92af734b7aaddc05fb777b6fbd03"
+checksum = "8ed6a63f02c8539c91a8685a86f4099661ba3da017932f6ebbea6de3f0fa7c90"
 
 [[package]]
 name = "streaming-iterator"
@@ -818,15 +802,6 @@ dependencies = [
  "windows-sys",
 ]
 
-[[package]]
-name = "termcolor"
-version = "1.4.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "06794f8f6c5c898b3275aebefa6b8a1cb24cd2c6c79397ab15774837a0bc5755"
-dependencies = [
- "winapi-util",
-]
-
 [[package]]
 name = "thiserror"
 version = "2.0.18"
@@ -856,15 +831,6 @@ dependencies = [
  "cfg-if",
 ]
 
-[[package]]
-name = "threadpool"
-version = "1.8.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d050e60b33d41c19108b32cea32164033a9013fe3b46cbd4457559bfbf77afaa"
-dependencies = [
- "num_cpus",
-]
-
 [[package]]
 name = "tiktoken-rs"
 version = "0.12.0"
@@ -1058,9 +1024,9 @@ dependencies = [
 
 [[package]]
 name = "tree-sitter-go"
-version = "0.23.4"
+version = "0.25.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b13d476345220dbe600147dd444165c5791bf85ef53e28acbedd46112ee18431"
+checksum = "c8560a4d2f835cc0d4d2c2e03cbd0dde2f6114b43bc491164238d333e28b16ea"
 dependencies = [
  "cc",
  "tree-sitter-language",
@@ -1244,9 +1210,9 @@ dependencies = [
 
 [[package]]
 name = "tree-sitter-r"
-version = "1.2.0"
+version = "1.3.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "429133cbda9f8a46e03ef3aae6abb6c3d22875f8585cad472138101bfd517255"
+checksum = "ffc9954ec870dcad6cffdd302b405306c68cf031ed79a78cd9746f6740d9fe20"
 dependencies = [
  "cc",
  "tree-sitter-language",
@@ -1264,9 +1230,9 @@ dependencies = [
 
 [[package]]
 name = "tree-sitter-rust"
-version = "0.23.3"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ca8ccb3e3a3495c8a943f6c3fd24c3804c471fd7f4f16087623c7fa4c0068e8a"
+checksum = "439e577dbe07423ec2582ac62c7531120dbfccfa6e5f92406f93dd271a120e45"
 dependencies = [
  "cc",
  "tree-sitter-language",

{diffctx-1.10.0 → diffctx-1.10.1}/diffctx/Cargo.toml

@@ -70,8 +70,8 @@ tree-sitter = "0.25"
 tree-sitter-python = { version = "0.23", optional = true }
 tree-sitter-javascript = { version = "0.23", optional = true }
 tree-sitter-typescript = { version = "0.23", optional = true }
-tree-sitter-go = { version = "0.23", optional = true }
-tree-sitter-rust = { version = "0.23", optional = true }
+tree-sitter-go = { version = "0.25", optional = true }
+tree-sitter-rust = { version = "0.24", optional = true }
 tree-sitter-java = { version = "0.23", optional = true }
 tree-sitter-c = { version = "0.24", optional = true }
 tree-sitter-cpp = { version = "0.23", optional = true }
@@ -126,7 +126,7 @@ pyo3 = { version = "0.29", features = ["extension-module", "abi3-py310"], option
 [dev-dependencies]
 tempfile = "3"
 serde_yaml = "0.9"
-libtest-mimic = "0.7"
+libtest-mimic = "0.8"
 
 [[test]]
 name = "yaml_cases"

{diffctx-1.10.0 → diffctx-1.10.1}/diffctx/src/main.rs

@@ -3,6 +3,9 @@ use mimalloc::MiMalloc;
 static GLOBAL: MiMalloc = MiMalloc;
 
 use std::path::PathBuf;
+use std::sync::mpsc;
+use std::thread;
+use std::time::Duration;
 
 use anyhow::Result;
 use clap::Parser;
@@ -60,17 +63,50 @@ fn main() -> Result<()> {
         eprintln!("error: {e}");
         std::process::exit(2);
     });
-    let output = build_diff_context(
-        &cli.path,
-        cli.diff_ref.as_deref(),
-        Some(cli.budget),
-        cli.alpha,
-        cli.tau,
-        cli.no_content,
-        cli.full,
-        scoring_mode,
-        cli.timeout,
-    )?;
+
+    // The per-phase git timeout does not bound in-process phases (parse, graph
+    // build, scoring), so a pathological repo can hang far past `--timeout`
+    // until OOM/SIGKILL (#70). Run the pipeline on a worker thread and enforce
+    // `--timeout` as a true total wall-clock ceiling: on expiry, fail fast with
+    // the actionable-error contract instead of hanging unbounded.
+    let timeout = cli.timeout;
+    let path = cli.path.clone();
+    let diff_ref = cli.diff_ref.clone();
+    let budget = cli.budget;
+    let alpha = cli.alpha;
+    let tau = cli.tau;
+    let no_content = cli.no_content;
+    let full = cli.full;
+    let (tx, rx) = mpsc::channel();
+    thread::spawn(move || {
+        let result = build_diff_context(
+            &path,
+            diff_ref.as_deref(),
+            Some(budget),
+            alpha,
+            tau,
+            no_content,
+            full,
+            scoring_mode,
+            timeout,
+        );
+        let _ = tx.send(result);
+    });
+
+    let output = match rx.recv_timeout(Duration::from_secs(timeout)) {
+        Ok(result) => result?,
+        Err(mpsc::RecvTimeoutError::Timeout) => {
+            eprintln!(
+                "diffctx: pipeline exceeded {timeout}s wall-clock deadline; aborting before \
+                 OOM/SIGKILL. Narrow the review with an explicit '--diff <from>..<to>' range or \
+                 run on a smaller subtree, or raise '--timeout'."
+            );
+            std::process::exit(124);
+        }
+        Err(mpsc::RecvTimeoutError::Disconnected) => {
+            anyhow::bail!("diffctx: pipeline worker terminated unexpectedly");
+        }
+    };
 
     match cli.format.as_str() {
         "json" => {

{diffctx-1.10.0 → diffctx-1.10.1}/diffctx/src/memory_pipeline.rs

@@ -162,6 +162,7 @@ pub fn build_diff_context_in_memory(
         Path::new("."),
         &[],
         None,
+        &core_ids,
     );
 
     let dummy_root = Path::new(".");

{diffctx-1.10.0 → diffctx-1.10.1}/diffctx/src/pipeline.rs

@@ -412,6 +412,7 @@ pub fn select_with_params(
         &state.root_dir,
         &state.preferred_revs,
         batch_reader.as_mut(),
+        &state.core_ids,
     );
     if let Some(mut r) = batch_reader {
         r.close();

{diffctx-1.10.0 → diffctx-1.10.1}/diffctx/src/postpass.rs

@@ -58,9 +58,16 @@ fn pick_smallest_fitting(
     candidates: &[Fragment],
     selected_ids: &FxHashSet<FragmentId>,
     budget_left: u32,
+    core_ids: &FxHashSet<FragmentId>,
 ) -> Option<Fragment> {
     let mut sorted: Vec<&Fragment> = candidates.iter().collect();
-    sorted.sort_by_key(|f| f.token_count);
+    // Prefer a fragment that actually covers the diff hunk (core_ids, i.e.
+    // what render.rs marks `role: "changed"`) over an unrelated same-file
+    // fragment (e.g. a one-line function_signature stub). Sorting by
+    // token_count alone picks whichever candidate is smallest regardless of
+    // relevance, which can silently hide the real change behind a tiny
+    // signature-only stub for the same file (#83).
+    sorted.sort_by_key(|f| (!core_ids.contains(&f.id), f.token_count));
     for cand in sorted {
         if cand.token_count == 0 || selected_ids.contains(&cand.id) {
             continue;
@@ -208,6 +215,7 @@ pub fn ensure_changed_files_represented(
     root_dir: &Path,
     preferred_revs: &[String],
     mut batch_reader: Option<&mut CatFileBatch>,
+    core_ids: &FxHashSet<FragmentId>,
 ) {
     let selected_paths: FxHashSet<String> = selected
         .iter()
@@ -258,7 +266,9 @@ pub fn ensure_changed_files_represented(
             candidates
         };
 
-        if let Some(picked) = pick_smallest_fitting(&candidates, &selected_ids, budget_left) {
+        if let Some(picked) =
+            pick_smallest_fitting(&candidates, &selected_ids, budget_left, core_ids)
+        {
             if !interval_idx.overlaps(&picked) {
                 budget_left = budget_left.saturating_sub(picked.token_count);
                 selected_ids.insert(picked.id.clone());
@@ -268,3 +278,96 @@ pub fn ensure_changed_files_represented(
         }
     }
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn frag(
+        path: &str,
+        start: u32,
+        end: u32,
+        kind: crate::types::FragmentKind,
+        tokens: u32,
+    ) -> Fragment {
+        Fragment {
+            id: FragmentId::new(Arc::from(path), start, end),
+            kind,
+            content: Arc::from(format!("fragment {path}:{start}-{end}")),
+            identifiers: FxHashSet::default(),
+            token_count: tokens,
+            symbol_name: None,
+        }
+    }
+
+    /// Regression for #83: when a changed file has no selected fragment and
+    /// the postpass fallback must pick one, a same-file signature stub that
+    /// is merely *smaller* must not be preferred over a same-file fragment
+    /// that actually covers the diff hunk (core_ids), as long as the core
+    /// fragment also fits the remaining budget.
+    #[test]
+    fn ensure_changed_files_represented_prefers_core_fragment_when_it_fits() {
+        let core = frag("a.ts", 10, 20, crate::types::FragmentKind::Function, 60);
+        let stub = frag(
+            "a.ts",
+            10,
+            10,
+            crate::types::FragmentKind::FunctionSignature,
+            10,
+        );
+        let all_fragments = vec![core.clone(), stub.clone()];
+        let core_ids: FxHashSet<FragmentId> = std::iter::once(core.id.clone()).collect();
+        let changed_files = vec![PathBuf::from("a.ts")];
+        let mut selected: Vec<Fragment> = Vec::new();
+
+        ensure_changed_files_represented(
+            &mut selected,
+            &all_fragments,
+            &changed_files,
+            100,
+            Path::new("."),
+            &[],
+            None,
+            &core_ids,
+        );
+
+        assert_eq!(selected.len(), 1, "expected exactly one fallback fragment");
+        assert_eq!(
+            selected[0].id, core.id,
+            "fallback picked the signature stub instead of the fragment covering the actual diff hunk"
+        );
+    }
+
+    /// When the core fragment does NOT fit the remaining budget, falling
+    /// back to the smaller non-core stub is still the correct behavior
+    /// (some representation beats none).
+    #[test]
+    fn ensure_changed_files_represented_falls_back_to_stub_when_core_does_not_fit() {
+        let core = frag("a.ts", 10, 20, crate::types::FragmentKind::Function, 60);
+        let stub = frag(
+            "a.ts",
+            10,
+            10,
+            crate::types::FragmentKind::FunctionSignature,
+            10,
+        );
+        let all_fragments = vec![core.clone(), stub.clone()];
+        let core_ids: FxHashSet<FragmentId> = std::iter::once(core.id.clone()).collect();
+        let changed_files = vec![PathBuf::from("a.ts")];
+        let mut selected: Vec<Fragment> = Vec::new();
+
+        ensure_changed_files_represented(
+            &mut selected,
+            &all_fragments,
+            &changed_files,
+            15,
+            Path::new("."),
+            &[],
+            None,
+            &core_ids,
+        );
+
+        assert_eq!(selected.len(), 1);
+        assert_eq!(selected[0].id, stub.id);
+    }
+}

{diffctx-1.10.0 → diffctx-1.10.1}/pyproject.toml

@@ -5,7 +5,7 @@ requires = [ "maturin>=1.10,<1.15" ]
 
 [project]
 name = "diffctx"
-version = "1.10.0"
+version = "1.10.1"
 description = "Export codebase structure and contents for AI/LLM context"
 readme = "README.md"
 keywords = [

{diffctx-1.10.0 → diffctx-1.10.1}/src/diffctx/main.py

@@ -40,9 +40,9 @@ def _ensure_git_repo(root_dir: Path) -> None:
             stderr=subprocess.DEVNULL,
             check=False,
         )
-    except (OSError, FileNotFoundError) as exc:
+    except OSError as exc:
         print(
-            f"diffctx: --diff requires git to be installed and on PATH ({exc}); " "install git or run without --diff.",
+            f"diffctx: --diff requires git to be installed and on PATH ({exc}); install git or run without --diff.",
             file=sys.stderr,
         )
         sys.exit(_EXIT_ENVIRONMENT)

{diffctx-1.10.0 → diffctx-1.10.1}/src/diffctx/mcp/__main__.py

@@ -8,7 +8,7 @@ def main(prog: str = "diffctx-mcp", extra: str = "diffctx[mcp]") -> None:
         from diffctx.mcp.server import run_server
     except ImportError:
         print(
-            f"{prog}: missing optional dependencies for MCP server mode.\n" f"Install with: pip install '{extra}'",
+            f"{prog}: missing optional dependencies for MCP server mode.\nInstall with: pip install '{extra}'",
             file=sys.stderr,
         )
         sys.exit(2)

diffctx-1.10.1/src/diffctx/version.py

@@ -0,0 +1 @@
+__version__ = "1.10.1"

{diffctx-1.10.0 → diffctx-1.10.1}/src/diffctx/writer.py

@@ -190,6 +190,29 @@ def _write_text_fragment(file: TextIO, frag: dict[str, Any], indent: str = "") -
             file.write(f"{content_indent}{line}\n")
 
 
+def _write_tree_text_diff_context(file: TextIO, tree: dict[str, Any]) -> None:
+    if tree.get("commit_message"):
+        file.write(f"  change: {tree['commit_message']}\n")
+    if tree.get("changed_files"):
+        file.write(f"  changed files: {', '.join(str(p) for p in tree['changed_files'])}\n")
+    for frag in tree["fragments"]:
+        _write_text_fragment(file, frag, "  ")
+
+
+def _write_tree_text_children(file: TextIO, children: list[dict[str, Any]]) -> None:
+    for i, child in enumerate(children):
+        connector = _TREE_LAST if i == len(children) - 1 else _TREE_BRANCH
+        _write_tree_text_node(file, child, "", connector)
+
+
+def _write_tree_text_content(file: TextIO, content: str) -> None:
+    if not content:
+        file.write("(empty file)\n")
+    else:
+        for line in content.rstrip("\n").split("\n"):
+            file.write(f"{line}\n")
+
+
 def write_tree_text(file: TextIO, tree: dict[str, Any]) -> None:
     name = tree.get("name", "")
     tree_type = tree.get("type", "")
@@ -202,24 +225,11 @@ def write_tree_text(file: TextIO, tree: dict[str, Any]) -> None:
         file.write(f"{name}/\n")
 
     if tree_type == "diff_context" and tree.get("fragments"):
-        if tree.get("commit_message"):
-            file.write(f"  change: {tree['commit_message']}\n")
-        if tree.get("changed_files"):
-            file.write(f"  changed files: {', '.join(str(p) for p in tree['changed_files'])}\n")
-        for frag in tree["fragments"]:
-            _write_text_fragment(file, frag, "  ")
+        _write_tree_text_diff_context(file, tree)
     elif tree.get("children"):
-        children = tree["children"]
-        for i, child in enumerate(children):
-            connector = _TREE_LAST if i == len(children) - 1 else _TREE_BRANCH
-            _write_tree_text_node(file, child, "", connector)
+        _write_tree_text_children(file, tree["children"])
     elif "content" in tree:
-        content = tree["content"]
-        if not content:
-            file.write("(empty file)\n")
-        else:
-            for line in content.rstrip("\n").split("\n"):
-                file.write(f"{line}\n")
+        _write_tree_text_content(file, tree["content"])
 
 
 def _is_placeholder(content: str) -> bool:
@@ -324,6 +334,18 @@ def _write_markdown_fragment(file: TextIO, frag: dict[str, Any]) -> None:
         _write_md_code_block(file, frag["content"], lang, "")
 
 
+def _write_markdown_diff_context(file: TextIO, tree: dict[str, Any]) -> None:
+    if tree.get("commit_message"):
+        file.write(f"> {tree['commit_message']}\n\n")
+    if tree.get("changed_files"):
+        file.write("**Changed files:**\n\n")
+        for path in tree["changed_files"]:
+            file.write(f"- {_escape_md_inline_code(str(path))}\n")
+        file.write("\n")
+    for frag in tree["fragments"]:
+        _write_markdown_fragment(file, frag)
+
+
 def write_tree_markdown(file: TextIO, tree: dict[str, Any]) -> None:
     name = tree.get("name", "")
     tree_type = tree.get("type", "")
@@ -335,15 +357,7 @@ def write_tree_markdown(file: TextIO, tree: dict[str, Any]) -> None:
         file.write(f"# {name}/\n\n")
 
     if tree_type == "diff_context" and tree.get("fragments"):
-        if tree.get("commit_message"):
-            file.write(f"> {tree['commit_message']}\n\n")
-        if tree.get("changed_files"):
-            file.write("**Changed files:**\n\n")
-            for path in tree["changed_files"]:
-                file.write(f"- {_escape_md_inline_code(str(path))}\n")
-            file.write("\n")
-        for frag in tree["fragments"]:
-            _write_markdown_fragment(file, frag)
+        _write_markdown_diff_context(file, tree)
     elif tree.get("children"):
         for child in tree["children"]:
             _write_markdown_node(file, child, 1)

diffctx-1.10.0/src/diffctx/version.py

@@ -1 +0,0 @@
-__version__ = "1.10.0"