diff --git a/.github/workflows/rust.yml b/.github/workflows/rust.yml
index 1f1926e..6bb87b3 100644
--- a/.github/workflows/rust.yml
+++ b/.github/workflows/rust.yml
@@ -19,6 +19,11 @@ on:
       - rust-toolchain.toml
       - rustfmt.toml
       - .github/workflows/rust.yml
+  # The `ignored-tests` job below is network-gated; run it manually or weekly so
+  # the PR gate stays offline. See ADR-0004.
+  workflow_dispatch:
+  schedule:
+    - cron: '0 6 * * 1' # Mondays 06:00 UTC
 
 permissions:
   contents: read
@@ -47,3 +52,19 @@ jobs:
 
       - name: Test
         run: cargo test --all-features --locked --workspace
+
+  ignored-tests:
+    # Network-gated: these tests download tree-sitter grammars from GitHub
+    # releases (see ADR-0004). Kept off the PR/push gate so it stays offline and
+    # flake-free; runs on manual dispatch or the weekly schedule to catch
+    # grammar-fetch / parser-compat regressions.
+    if: github.event_name == 'workflow_dispatch' || github.event_name == 'schedule'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
+        with:
+          persist-credentials: false
+
+      - name: Test (ignored / network-gated)
+        run: cargo test --all-features --locked --workspace -- --ignored
diff --git a/.please/docs/decisions/0004-rust-grammar-coverage-language-pack.md b/.please/docs/decisions/0004-rust-grammar-coverage-language-pack.md
new file mode 100644
index 0000000..62b7764
--- /dev/null
+++ b/.please/docs/decisions/0004-rust-grammar-coverage-language-pack.md
@@ -0,0 +1,69 @@
+# ADR 0004 — Rust grammar coverage via `tree-sitter-language-pack` (downloaded parsers)
+
+- **Status**: Accepted
+- **Date**: 2026-06-20
+- **Deciders**: csp maintainers
+- **Relates to**: [ADR 0001](0001-native-tree-sitter.md) (native tree-sitter bindings, the TS side), [ADR 0003](0003-rewrite-in-rust.md) (Rust rewrite & single-binary distribution)
+- **Closes**: [#38](https://github.com/pleaseai/code-search/issues/38) — "Rust port: expand tree-sitter grammar coverage to match upstream language pack"
+
+## Context
+
+The Rust port's chunker (`crates/csp/src/chunking/core.rs`) resolved a tree-sitter grammar through `language_for(language)`, which statically linked a **curated set of ~14 grammars** (rust, python, javascript, typescript, tsx, go, java, c, cpp, ruby, json, bash, html, css) via individual `tree-sitter-*` crates.
+
+Upstream semble parses with the Python `tree-sitter-language-pack` (≈all languages). Meanwhile the Rust port's `EXTENSION_TO_LANGUAGE` table (`crates/csp/src/indexing/files.rs`, ~350 entries / 265 distinct language names) recognizes far more languages than the curated grammar set. The effect was a **real behavioral narrowing vs upstream**: a file in a recognized-but-uncurated language (kotlin, swift, php, scala, lua, …) was still walked and indexed, but fell through to line-based chunking instead of AST chunking — coarser, less semantically-aligned chunk boundaries than upstream produces.
+
+The options for closing the gap:
+
+1. **Expanded curated set** — hand-pick and statically link ~30–40 more `tree-sitter-*` crates. Keeps a self-contained offline binary, but only partial parity, grows build time / binary size, and requires a per-language audit (not every grammar is published to crates.io at a compatible version).
+2. **`tree-sitter-language-pack` crate (dynamic loading + download)** — adopt the Rust crate published by the same project semble uses. 306 languages, `get_language(name)` maps 1:1 onto `language_for`, and 264 of csp's 265 `EXTENSION_TO_LANGUAGE` names resolve (only `wolfram` is absent). Parsers are fetched from GitHub releases on first use and cached on disk.
+
+## Decision
+
+**Adopt `tree-sitter-language-pack` = "1.9"** with its default features (`dynamic-loading` + `download`) as the canonical grammar source for the Rust chunker. Replace the 14 individual `tree-sitter-*` grammar crates with it.
+
+- `language_for(language)` → `tree_sitter_language_pack::get_language(language).ok()`. Downloads the parser on first use, caches it, then hits the in-process registry. Unknown language or an offline fetch failure → `None` → line fallback (the exact pre-existing degradation contract).
+- `is_supported_language(language)` → `tree_sitter_language_pack::has_language(language)`. A **metadata-only** lookup (bundled manifest + aliases) that does **not** download, so `chunk_source` gates AST chunking cheaply before paying for a fetch.
+- `tree-sitter` stays a direct dependency (the port drives `Parser`/`Node`/`Language` itself). The crate resolves to the same `tree-sitter 0.26.x`, so the returned `Language` is ABI-compatible.
+
+### Trade-off: single binary vs. runtime grammar cache
+
+ADR-0003 motivation #1 is single-binary distribution. This decision **narrows** that property: the `csp` binary is still a single executable that runs with no Node/Bun present, but it is **no longer fully self-contained / offline** for AST chunking — grammars are fetched from GitHub releases on first use and cached under the OS cache dir (`tree_sitter_language_pack::cache_dir()`; `dirs`-based, e.g. `~/Library/Caches/...` or `~/.cache/...`).
+
+We accept this because:
+
+- **Parity is the point of this work.** A statically-linked subset cannot reach upstream's ≈full coverage without an unbounded crate-audit treadmill; the language pack tracks 306 grammars maintained by the same upstream semble depends on.
+- **Degradation is graceful, not fatal.** Offline or fetch-failed → line chunking, exactly what an unsupported language already did. No language regresses below the previous behavior; the previously-curated 14 also just download once and cache.
+- **Binary size shrinks** (grammars no longer compiled in) at the cost of a one-time per-language network fetch.
+
+The negatives: first-use latency and a network/GitHub-availability dependency for never-before-seen languages; a writable cache dir is required for AST chunking. These are documented and considered acceptable for a developer tool. A future offline/air-gapped mode could pre-seed the cache via `tree_sitter_language_pack::download(&[...])` or `download_all()`, or pin a `download`-disabled build that links a static subset — out of scope here.
+
+## Consequences
+
+### Positive
+
+- Full upstream-parity AST chunking: 264/265 recognized languages now AST-chunk instead of line-falling-back.
+- One dependency replaces 14; coverage tracks upstream without a per-language audit.
+- Smaller binary (no compiled-in grammars).
+
+### Negative
+
+- AST chunking now requires a one-time network fetch per language and a writable cache dir; fully offline runs degrade those languages to line chunking until the cache is seeded.
+- `cargo test` for real-parse tests needs network → those tests are `#[ignore]`d (run with `cargo test -- --ignored`); the default suite stays offline-green via metadata-only (`has_language`) and fallback assertions.
+- One language in csp's extension table (`wolfram`) has no pack grammar and stays on line fallback.
+
+### Neutral
+
+- `chunk_source`'s gate (`is_supported_language` then `chunk`) is unchanged in shape; only the resolver backing it changed.
+- An offline/static build mode remains a future option (feature-gated `download`-off build, or cache pre-seeding).
+
+## Alternatives considered
+
+- **Expanded curated static set.** Rejected: partial parity only, ongoing crate-audit burden, and larger build/binary, for a coverage ceiling still well below upstream.
+- **Hybrid (static subset + optional language-pack feature).** Rejected for now: doubles the chunker's resolver paths and the test matrix for little benefit over the download model, whose offline degradation already matches the old static fallback. Kept as a future option if an air-gapped build becomes a requirement.
+
+## References
+
+- Issue [#38](https://github.com/pleaseai/code-search/issues/38).
+- `tree-sitter-language-pack` — <https://crates.io/crates/tree-sitter-language-pack>, <https://github.com/kreuzberg-dev/tree-sitter-language-pack>.
+- Upstream: `src/semble/chunking/core.py`, `src/semble/index/files.py` in [MinishLab/semble](https://github.com/MinishLab/semble).
+- `.please/docs/references/semble.md` §4.3 (chunking) and §6.2 (open gaps).
diff --git a/.please/docs/decisions/index.md b/.please/docs/decisions/index.md
index 9fefb19..a6f846d 100644
--- a/.please/docs/decisions/index.md
+++ b/.please/docs/decisions/index.md
@@ -7,3 +7,4 @@
 | [0001](0001-native-tree-sitter.md) | Use Native Tree-sitter Bindings via `@kreuzberg/tree-sitter-language-pack` | 2026-05-28 | Accepted |
 | [0002](0002-index-storage-cache-model.md) | Index Storage & Caching Model: Global `~/.csp/index/` Content-Hash Cache | 2026-06-18 | Accepted |
 | [0003](0003-rewrite-in-rust.md) | Rewrite `@pleaseai/csp` from TypeScript/Bun to Rust | 2026-06-18 | Proposed |
+| [0004](0004-rust-grammar-coverage-language-pack.md) | Rust grammar coverage via `tree-sitter-language-pack` (downloaded parsers) | 2026-06-20 | Accepted |
diff --git a/.please/docs/references/semble.md b/.please/docs/references/semble.md
index b0aa53c..4cd66f8 100644
--- a/.please/docs/references/semble.md
+++ b/.please/docs/references/semble.md
@@ -123,17 +123,23 @@ Same contract as semble `tokens.py`:
 **`core.rs`** (boundary algorithm, byte-based; `RECURSION_DEPTH = 500`, `MIN_CHUNK_SIZE = 50`):
 - The merge algorithm is generic over a node trait so tests can drive it with mock nodes; in
   production a **`TsNode` bridge** adapts `tree_sitter::Node` to it.
-- `language_for(language)` returns a statically-linked `tree_sitter::Language` for a **curated
-  grammar set**: rust, python, javascript, typescript, tsx, go, java, c, cpp, ruby, json, bash,
-  html, css. Unsupported languages → `None` → line fallback. ⚠ This is **narrower than upstream**,
-  which uses `tree_sitter_language_pack` (≈all languages); see §6.
+- `language_for(language)` returns a `tree_sitter::Language` from
+  **`tree_sitter_language_pack`** (306 grammars — full upstream parity; semble uses the Python
+  package of the same name). Parsers download from GitHub releases on first use and cache on disk;
+  unknown language or an offline fetch failure → `None` → line fallback. `is_supported_language`
+  uses `has_language` — a **metadata-only** check (no download) — so `chunk_source` gates AST
+  chunking before paying for a fetch. 264/265 `EXTENSION_TO_LANGUAGE` names resolve (`wolfram` is
+  the sole gap). See [ADR-0004](../decisions/0004-rust-grammar-coverage-language-pack.md) for the
+  single-binary ↔ runtime-cache trade-off.
 - `_merge_node_inner` (greedy pack), `_merge_adjacent_chunks`, `chunk_lines` fallback — same
   shape as semble. Byte offsets are converted to char offsets for multibyte safety.
 
 **`source.rs`** (`chunk_source`):
 - `DESIRED_CHUNK_LENGTH_CHARS = 1500` (⚠ upstream is now **750** — see §6).
-- AST chunking when `language_for(lang).is_some()`, else line fallback. Char offsets → 1-indexed
-  line numbers; clamps end to avoid the zero-length off-by-one.
+- AST chunking is gated by `is_supported_language(lang)` (metadata-only, no download); the
+  subsequent `chunk(...)` may still return `None` (e.g. an offline grammar fetch failure),
+  falling back to line chunking. Char offsets → 1-indexed line numbers; clamps end to avoid the
+  zero-length off-by-one.
 
 ### 4.4 `indexing/file_walker.rs` — gitignore-aware walk
 
@@ -146,9 +152,9 @@ Same contract as semble `tokens.py`:
 ### 4.5 `indexing/files.rs` — language detection & file gating
 
 - `EXTENSION_TO_LANGUAGE` — `&[(&str, &str)]` table (~350 entries). `detect_language(name)`
-  lowercases the suffix and looks it up. Note: this recognizes far more extensions than the
-  curated tree-sitter set in §4.3 — recognized-but-unparsed languages still get **walked and
-  line-chunked**.
+  lowercases the suffix and looks it up. Since §4.3 now resolves grammars through
+  `tree_sitter_language_pack` (306 grammars), 264/265 of these language names AST-chunk; only
+  `wolfram` (and any extension the pack can't fetch) falls back to line chunking.
 - Content-type partition: `DOC_LANGUAGES`, `CONFIG_LANGUAGES`, `DATA_LANGUAGES`; code = all minus
   those. `get_extensions(types, extra)` inverts the map; the **`extra`** param (custom extensions)
   is a small Rust-side API addition.
@@ -348,10 +354,12 @@ Clean two-layer split:
   `rerank_top_k_saturation`; the real `ranking::{boosting::apply_query_boost,
   penalties::rerank_top_k}` are ported but unwired (matches the TS source). Search-ranking parity
   is fixture-level only. Saturation constants are duplicated as a result.
-- **Curated tree-sitter set** — only ~14 grammars are statically linked (`language_for`); upstream
-  uses `tree_sitter_language_pack` (≈all languages). Languages outside the curated set are
-  recognized by the extension map but **line-chunked**, not AST-chunked. This is a real behavioral
-  narrowing vs upstream.
+- ~~**Curated tree-sitter set**~~ — **closed** ([ADR-0004](../decisions/0004-rust-grammar-coverage-language-pack.md),
+  [#38](https://github.com/pleaseai/code-search/issues/38)). `language_for` now resolves through
+  `tree_sitter_language_pack` (306 grammars, full upstream parity; 264/265 `EXTENSION_TO_LANGUAGE`
+  names AST-chunk, `wolfram` excepted). Trade-off recorded in ADR-0004: parsers download on first
+  use and cache on disk, so AST chunking is no longer fully offline/self-contained — it degrades
+  gracefully to line chunking when offline, exactly as an unsupported language already did.
 
 ### 6.3 Upstream drift since the review baseline (`eacbe43` → `136b6f7`)
 
diff --git a/Cargo.lock b/Cargo.lock
index 738d49d..0af49f2 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -15,6 +15,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "5a15f179cd60c4584b8a8c596927aadc462e27f2ca70c04e0071964a73ba7a75"
 dependencies = [
  "cfg-if",
+ "const-random",
  "getrandom 0.3.4",
  "once_cell",
  "serde",
@@ -155,6 +156,15 @@ dependencies = [
  "generic-array",
 ]
 
+[[package]]
+name = "block-buffer"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d2f6c7dbe95a6ed67ad9f18e57daf93a2f034c524b99fd2b76d18fdfeb6660aa"
+dependencies = [
+ "hybrid-array",
+]
+
 [[package]]
 name = "bstr"
 version = "1.12.1"
@@ -199,9 +209,17 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dad887fd958be91b5098c0248def011f4523ab786cd411be668777e55063501f"
 dependencies = [
  "find-msvc-tools",
+ "jobserver",
+ "libc",
  "shlex",
 ]
 
+[[package]]
+name = "cesu8"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6d43a04d8753f35258c91f8ec639f792891f748a1edbd759cf1dcea3382ad83c"
+
 [[package]]
 name = "cfg-if"
 version = "1.0.4"
@@ -266,6 +284,16 @@ version = "1.0.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
 
+[[package]]
+name = "combine"
+version = "4.6.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba5a308b75df32fe02788e748662718f03fde005016435c444eea572398219fd"
+dependencies = [
+ "bytes",
+ "memchr",
+]
+
 [[package]]
 name = "compact_str"
 version = "0.9.1"
@@ -294,6 +322,42 @@ dependencies = [
  "windows-sys 0.59.0",
 ]
 
+[[package]]
+name = "const-oid"
+version = "0.10.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a6ef517f0926dd24a1582492c791b6a4818a4d94e789a334894aa15b0d12f55c"
+
+[[package]]
+name = "const-random"
+version = "0.1.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "87e00182fe74b066627d63b85fd550ac2998d4b0bd86bfed477a0ae4c7c71359"
+dependencies = [
+ "const-random-macro",
+]
+
+[[package]]
+name = "const-random-macro"
+version = "0.1.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f9d839f2a20b0aee515dc581a6172f2321f96cab76c1a38a4c584a194955390e"
+dependencies = [
+ "getrandom 0.2.17",
+ "once_cell",
+ "tiny-keccak",
+]
+
+[[package]]
+name = "core-foundation"
+version = "0.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b2a6cd9ae233e7f62ba4e9353e81a88df7fc8a5987b8d445b4d90c879bd156f6"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
 [[package]]
 name = "core-foundation-sys"
 version = "0.8.7"
@@ -309,6 +373,15 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "cpufeatures"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8b2a41393f66f16b0823bb79094d54ac5fbd34ab292ddafb9a0456ac9f87d201"
+dependencies = [
+ "libc",
+]
+
 [[package]]
 name = "crc32fast"
 version = "1.5.0"
@@ -359,6 +432,15 @@ dependencies = [
  "typenum",
 ]
 
+[[package]]
+name = "crypto-common"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ce6e4c961d6cd6c9a86db418387425e8bdeaf05b3c8bc1411e6dca4c252f1453"
+dependencies = [
+ "hybrid-array",
+]
+
 [[package]]
 name = "csp"
 version = "0.0.0"
@@ -370,23 +452,11 @@ dependencies = [
  "regex",
  "serde",
  "serde_json",
- "sha2",
+ "sha2 0.10.9",
  "tempfile",
- "thiserror",
+ "thiserror 2.0.18",
  "tree-sitter",
- "tree-sitter-bash",
- "tree-sitter-c",
- "tree-sitter-cpp",
- "tree-sitter-css",
- "tree-sitter-go",
- "tree-sitter-html",
- "tree-sitter-java",
- "tree-sitter-javascript",
- "tree-sitter-json",
- "tree-sitter-python",
- "tree-sitter-ruby",
- "tree-sitter-rust",
- "tree-sitter-typescript",
+ "tree-sitter-language-pack",
 ]
 
 [[package]]
@@ -519,8 +589,19 @@ version = "0.10.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
 dependencies = [
- "block-buffer",
- "crypto-common",
+ "block-buffer 0.10.4",
+ "crypto-common 0.1.7",
+]
+
+[[package]]
+name = "digest"
+version = "0.11.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f1dd6dbb5841937940781866fa1281a1ff7bd3bf827091440879f9994983d5c2"
+dependencies = [
+ "block-buffer 0.12.1",
+ "const-oid",
+ "crypto-common 0.2.2",
 ]
 
 [[package]]
@@ -615,6 +696,27 @@ version = "2.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9f1f227452a390804cdb637b74a86990f2a7d7ba4b7d5693aac9b4dd6defd8d6"
 
+[[package]]
+name = "fd-lock"
+version = "4.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0ce92ff622d6dadf7349484f42c93271a0d49b7cc4d466a936405bacbe10aa78"
+dependencies = [
+ "cfg-if",
+ "rustix",
+ "windows-sys 0.59.0",
+]
+
+[[package]]
+name = "filetime"
+version = "0.2.29"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c287a33c7f0a620c38e641e7f60827713987b3c0f26e8ddc9462cc69cf75759"
+dependencies = [
+ "cfg-if",
+ "libc",
+]
+
 [[package]]
 name = "find-msvc-tools"
 version = "0.1.9"
@@ -828,8 +930,8 @@ dependencies = [
  "rand",
  "serde",
  "serde_json",
- "thiserror",
- "ureq",
+ "thiserror 2.0.18",
+ "ureq 2.12.1",
  "windows-sys 0.60.2",
 ]
 
@@ -843,6 +945,21 @@ dependencies = [
  "itoa",
 ]
 
+[[package]]
+name = "httparse"
+version = "1.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6dbf3de79e51f3d586ab4cb9d5c3e2c14aa28ed23d180cf89b4df0454a69cc87"
+
+[[package]]
+name = "hybrid-array"
+version = "0.4.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9155a582abd142abc056962c29e3ce5ff2ad5469f4246b537ed42c5deba857da"
+dependencies = [
+ "typenum",
+]
+
 [[package]]
 name = "iana-time-zone"
 version = "0.1.65"
@@ -1036,6 +1153,60 @@ version = "1.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8f42a60cbdf9a97f5d2305f08a87dc4e09308d1276d28c869c684d7777685682"
 
+[[package]]
+name = "jni"
+version = "0.21.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1a87aa2bb7d2af34197c04845522473242e1aa17c12f4935d5856491a7fb8c97"
+dependencies = [
+ "cesu8",
+ "cfg-if",
+ "combine",
+ "jni-sys 0.3.1",
+ "log",
+ "thiserror 1.0.69",
+ "walkdir",
+ "windows-sys 0.45.0",
+]
+
+[[package]]
+name = "jni-sys"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41a652e1f9b6e0275df1f15b32661cf0d4b78d4d87ddec5e0c3c20f097433258"
+dependencies = [
+ "jni-sys 0.4.1",
+]
+
+[[package]]
+name = "jni-sys"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c6377a88cb3910bee9b0fa88d4f42e1d2da8e79915598f65fb0c7ee14c878af2"
+dependencies = [
+ "jni-sys-macros",
+]
+
+[[package]]
+name = "jni-sys-macros"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "38c0b942f458fe50cdac086d2f946512305e5631e720728f2a61aabcd47a6264"
+dependencies = [
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "jobserver"
+version = "0.1.34"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9afb3de4395d6b3e67a780b6de64b51c978ecf11cb9a462c66be7d4ca9039d33"
+dependencies = [
+ "getrandom 0.3.4",
+ "libc",
+]
+
 [[package]]
 name = "js-sys"
 version = "0.3.102"
@@ -1053,6 +1224,16 @@ version = "0.2.186"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "68ab91017fe16c622486840e4c83c9a37afeff978bd239b5293d61ece587de66"
 
+[[package]]
+name = "libloading"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "754ca22de805bb5744484a5b151a9e1a8e837d5dc232c2d7d8c2e3492edc8b60"
+dependencies = [
+ "cfg-if",
+ "windows-link",
+]
+
 [[package]]
 name = "libredox"
 version = "0.1.17"
@@ -1143,7 +1324,7 @@ dependencies = [
  "serde",
  "serde_json",
  "tokenizers",
- "ureq",
+ "ureq 2.12.1",
 ]
 
 [[package]]
@@ -1258,6 +1439,12 @@ dependencies = [
  "pkg-config",
 ]
 
+[[package]]
+name = "openssl-probe"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7c87def4c32ab89d880effc9e097653c8da5d6ef28e6b539d313baaacfbafcbe"
+
 [[package]]
 name = "option-ext"
 version = "0.2.0"
@@ -1422,7 +1609,7 @@ checksum = "a4e608c6638b9c18977b00b475ac1f28d14e84b27d8d42f70e0bf1e3dec127ac"
 dependencies = [
  "getrandom 0.2.17",
  "libredox",
- "thiserror",
+ "thiserror 2.0.18",
 ]
 
 [[package]]
@@ -1504,7 +1691,7 @@ dependencies = [
  "schemars",
  "serde",
  "serde_json",
- "thiserror",
+ "thiserror 2.0.18",
  "tokio",
  "tokio-util",
  "tracing",
@@ -1551,6 +1738,18 @@ dependencies = [
  "zeroize",
 ]
 
+[[package]]
+name = "rustls-native-certs"
+version = "0.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dab5152771c58876a2146916e53e35057e1a4dfa2b9df0f0305b07f611fdea4d"
+dependencies = [
+ "openssl-probe",
+ "rustls-pki-types",
+ "schannel",
+ "security-framework",
+]
+
 [[package]]
 name = "rustls-pki-types"
 version = "1.14.1"
@@ -1560,6 +1759,33 @@ dependencies = [
  "zeroize",
 ]
 
+[[package]]
+name = "rustls-platform-verifier"
+version = "0.6.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1d99feebc72bae7ab76ba994bb5e121b8d83d910ca40b36e0921f53becc41784"
+dependencies = [
+ "core-foundation",
+ "core-foundation-sys",
+ "jni",
+ "log",
+ "once_cell",
+ "rustls",
+ "rustls-native-certs",
+ "rustls-platform-verifier-android",
+ "rustls-webpki",
+ "security-framework",
+ "security-framework-sys",
+ "webpki-root-certs",
+ "windows-sys 0.61.2",
+]
+
+[[package]]
+name = "rustls-platform-verifier-android"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f87165f0995f63a9fbeea62b64d10b4d9d8e78ec6d7d51fb2125fda7bb36788f"
+
 [[package]]
 name = "rustls-webpki"
 version = "0.103.13"
@@ -1602,6 +1828,15 @@ dependencies = [
  "winapi-util",
 ]
 
+[[package]]
+name = "schannel"
+version = "0.1.29"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91c1b7e4904c873ef0710c1f407dde2e6287de2bebc1bbbf7d430bb7cbffd939"
+dependencies = [
+ "windows-sys 0.61.2",
+]
+
 [[package]]
 name = "schemars"
 version = "1.2.1"
@@ -1628,6 +1863,29 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "security-framework"
+version = "3.7.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b7f4bc775c73d9a02cde8bf7b2ec4c9d12743edf609006c7facc23998404cd1d"
+dependencies = [
+ "bitflags",
+ "core-foundation",
+ "core-foundation-sys",
+ "libc",
+ "security-framework-sys",
+]
+
+[[package]]
+name = "security-framework-sys"
+version = "2.17.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ce2691df843ecc5d231c0b14ece2acc3efb62c0a398c7e1d875f3983ce020e3"
+dependencies = [
+ "core-foundation-sys",
+ "libc",
+]
+
 [[package]]
 name = "serde"
 version = "1.0.228"
@@ -1690,8 +1948,19 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
 dependencies = [
  "cfg-if",
- "cpufeatures",
- "digest",
+ "cpufeatures 0.2.17",
+ "digest 0.10.7",
+]
+
+[[package]]
+name = "sha2"
+version = "0.11.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "446ba717509524cb3f22f17ecc096f10f4822d76ab5c0b9822c5f9c284e825f4"
+dependencies = [
+ "cfg-if",
+ "cpufeatures 0.3.0",
+ "digest 0.11.3",
 ]
 
 [[package]]
@@ -1793,6 +2062,17 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "tar"
+version = "0.4.46"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f6221d9a6003c78398e3b239969f352578258df48c8eb051caadae0015bc840"
+dependencies = [
+ "filetime",
+ "libc",
+ "xattr",
+]
+
 [[package]]
 name = "tempfile"
 version = "3.27.0"
@@ -1806,13 +2086,33 @@ dependencies = [
  "windows-sys 0.61.2",
 ]
 
+[[package]]
+name = "thiserror"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6aaf5339b578ea85b50e080feb250a3e8ae8cfcdff9a461c9ec2904bc923f52"
+dependencies = [
+ "thiserror-impl 1.0.69",
+]
+
 [[package]]
 name = "thiserror"
 version = "2.0.18"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "4288b5bcbc7920c07a1149a35cf9590a2aa808e0bc1eafaade0b80947865fbc4"
 dependencies = [
- "thiserror-impl",
+ "thiserror-impl 2.0.18",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.69"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4fee6c4efc90059e10f81e6d42c60a18f76588c3d74cb83a0b242a2b6c7504c1"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
 ]
 
 [[package]]
@@ -1826,6 +2126,15 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "tiny-keccak"
+version = "2.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2c9d3793400a45f954c52e73d068316d76b6f4e36977e3fcebb13a2721e80237"
+dependencies = [
+ "crunchy",
+]
+
 [[package]]
 name = "tinystr"
 version = "0.8.3"
@@ -1864,7 +2173,7 @@ dependencies = [
  "serde",
  "serde_json",
  "spm_precompiled",
- "thiserror",
+ "thiserror 2.0.18",
  "unicode-normalization-alignments",
  "unicode-segmentation",
  "unicode_categories",
@@ -1950,96 +2259,6 @@ dependencies = [
  "tree-sitter-language",
 ]
 
-[[package]]
-name = "tree-sitter-bash"
-version = "0.25.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9e5ec769279cc91b561d3df0d8a5deb26b0ad40d183127f409494d6d8fc53062"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
-[[package]]
-name = "tree-sitter-c"
-version = "0.24.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a9b2eb57a55fed6b00812912e730b7a275cf4fe98bfd6a5d76263d4438371728"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
-[[package]]
-name = "tree-sitter-cpp"
-version = "0.23.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df2196ea9d47b4ab4a31b9297eaa5a5d19a0b121dceb9f118f6790ad0ab94743"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
-[[package]]
-name = "tree-sitter-css"
-version = "0.25.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a5cbc5e18f29a2c6d6435891f42569525cf95435a3e01c2f1947abcde178686f"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
-[[package]]
-name = "tree-sitter-go"
-version = "0.25.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c8560a4d2f835cc0d4d2c2e03cbd0dde2f6114b43bc491164238d333e28b16ea"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
-[[package]]
-name = "tree-sitter-html"
-version = "0.23.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "261b708e5d92061ede329babaaa427b819329a9d427a1d710abb0f67bbef63ee"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
-[[package]]
-name = "tree-sitter-java"
-version = "0.23.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0aa6cbcdc8c679b214e616fd3300da67da0e492e066df01bcf5a5921a71e90d6"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
-[[package]]
-name = "tree-sitter-javascript"
-version = "0.25.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "68204f2abc0627a90bdf06e605f5c470aa26fdcb2081ea553a04bdad756693f5"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
-[[package]]
-name = "tree-sitter-json"
-version = "0.24.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4d727acca406c0020cffc6cf35516764f36c8e3dc4408e5ebe2cb35a947ec471"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
 [[package]]
 name = "tree-sitter-language"
 version = "0.1.7"
@@ -2047,43 +2266,25 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "009994f150cc0cd50ff54917d5bc8bffe8cad10ca10d81c34da2ec421ae61782"
 
 [[package]]
-name = "tree-sitter-python"
-version = "0.25.0"
+name = "tree-sitter-language-pack"
+version = "1.9.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6bf85fd39652e740bf60f46f4cda9492c3a9ad75880575bf14960f775cb74a1c"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
-[[package]]
-name = "tree-sitter-ruby"
-version = "0.23.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "be0484ea4ef6bb9c575b4fdabde7e31340a8d2dbc7d52b321ac83da703249f95"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
-[[package]]
-name = "tree-sitter-rust"
-version = "0.24.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "439e577dbe07423ec2582ac62c7531120dbfccfa6e5f92406f93dd271a120e45"
-dependencies = [
- "cc",
- "tree-sitter-language",
-]
-
-[[package]]
-name = "tree-sitter-typescript"
-version = "0.23.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6c5f76ed8d947a75cc446d5fccd8b602ebf0cde64ccf2ffa434d873d7a575eff"
+checksum = "09a9d3b46347363ce7dc86d1df53ebe6af125cb9b30c24461d190aa942da6b50"
 dependencies = [
+ "ahash",
  "cc",
- "tree-sitter-language",
+ "dirs",
+ "fd-lock",
+ "libloading",
+ "memchr",
+ "serde",
+ "serde_json",
+ "sha2 0.11.0",
+ "tar",
+ "thiserror 2.0.18",
+ "tree-sitter",
+ "ureq 3.3.0",
+ "zstd",
 ]
 
 [[package]]
@@ -2150,6 +2351,37 @@ dependencies = [
  "webpki-roots 0.26.11",
 ]
 
+[[package]]
+name = "ureq"
+version = "3.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dea7109cdcd5864d4eeb1b58a1648dc9bf520360d7af16ec26d0a9354bafcfc0"
+dependencies = [
+ "base64 0.22.1",
+ "flate2",
+ "log",
+ "percent-encoding",
+ "rustls",
+ "rustls-pki-types",
+ "rustls-platform-verifier",
+ "socks",
+ "ureq-proto",
+ "utf8-zero",
+ "webpki-roots 1.0.8",
+]
+
+[[package]]
+name = "ureq-proto"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e994ba84b0bd1b1b0cf92878b7ef898a5c1760108fe7b6010327e274917a808c"
+dependencies = [
+ "base64 0.22.1",
+ "http",
+ "httparse",
+ "log",
+]
+
 [[package]]
 name = "url"
 version = "2.5.8"
@@ -2162,6 +2394,12 @@ dependencies = [
  "serde",
 ]
 
+[[package]]
+name = "utf8-zero"
+version = "0.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b8c0a043c9540bae7c578c88f91dda8bd82e59ae27c21baca69c8b191aaf5a6e"
+
 [[package]]
 name = "utf8_iter"
 version = "1.0.4"
@@ -2260,6 +2498,15 @@ dependencies = [
  "wasm-bindgen",
 ]
 
+[[package]]
+name = "webpki-root-certs"
+version = "1.0.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0d46a5a140e6f7afeccd8eae97eff335163939eac8b929834875168b29b3d267"
+dependencies = [
+ "rustls-pki-types",
+]
+
 [[package]]
 name = "webpki-roots"
 version = "0.26.11"
@@ -2368,6 +2615,15 @@ dependencies = [
  "windows-link",
 ]
 
+[[package]]
+name = "windows-sys"
+version = "0.45.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "75283be5efb2831d37ea142365f009c02ec203cd29a3ebecbc093d52315b66d0"
+dependencies = [
+ "windows-targets 0.42.2",
+]
+
 [[package]]
 name = "windows-sys"
 version = "0.52.0"
@@ -2404,6 +2660,21 @@ dependencies = [
  "windows-link",
 ]
 
+[[package]]
+name = "windows-targets"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e5180c00cd44c9b1c88adb3693291f1cd93605ded80c250a75d472756b4d071"
+dependencies = [
+ "windows_aarch64_gnullvm 0.42.2",
+ "windows_aarch64_msvc 0.42.2",
+ "windows_i686_gnu 0.42.2",
+ "windows_i686_msvc 0.42.2",
+ "windows_x86_64_gnu 0.42.2",
+ "windows_x86_64_gnullvm 0.42.2",
+ "windows_x86_64_msvc 0.42.2",
+]
+
 [[package]]
 name = "windows-targets"
 version = "0.52.6"
@@ -2437,6 +2708,12 @@ dependencies = [
  "windows_x86_64_msvc 0.53.1",
 ]
 
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "597a5118570b68bc08d8d59125332c54f1ba9d9adeedeef5b99b02ba2b0698f8"
+
 [[package]]
 name = "windows_aarch64_gnullvm"
 version = "0.52.6"
@@ -2449,6 +2726,12 @@ version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a9d8416fa8b42f5c947f8482c43e7d89e73a173cead56d044f6a56104a6d1b53"
 
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e08e8864a60f06ef0d0ff4ba04124db8b0fb3be5776a5cd47641e942e58c4d43"
+
 [[package]]
 name = "windows_aarch64_msvc"
 version = "0.52.6"
@@ -2461,6 +2744,12 @@ version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b9d782e804c2f632e395708e99a94275910eb9100b2114651e04744e9b125006"
 
+[[package]]
+name = "windows_i686_gnu"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c61d927d8da41da96a81f029489353e68739737d3beca43145c8afec9a31a84f"
+
 [[package]]
 name = "windows_i686_gnu"
 version = "0.52.6"
@@ -2485,6 +2774,12 @@ version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "fa7359d10048f68ab8b09fa71c3daccfb0e9b559aed648a8f95469c27057180c"
 
+[[package]]
+name = "windows_i686_msvc"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "44d840b6ec649f480a41c8d80f9c65108b92d89345dd94027bfe06ac444d1060"
+
 [[package]]
 name = "windows_i686_msvc"
 version = "0.52.6"
@@ -2497,6 +2792,12 @@ version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1e7ac75179f18232fe9c285163565a57ef8d3c89254a30685b57d83a38d326c2"
 
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8de912b8b8feb55c064867cf047dda097f92d51efad5b491dfb98f6bbb70cb36"
+
 [[package]]
 name = "windows_x86_64_gnu"
 version = "0.52.6"
@@ -2509,6 +2810,12 @@ version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9c3842cdd74a865a8066ab39c8a7a473c0778a3f29370b5fd6b4b9aa7df4a499"
 
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "26d41b46a36d453748aedef1486d5c7a85db22e56aff34643984ea85514e94a3"
+
 [[package]]
 name = "windows_x86_64_gnullvm"
 version = "0.52.6"
@@ -2521,6 +2828,12 @@ version = "0.53.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0ffa179e2d07eee8ad8f57493436566c7cc30ac536a3379fdf008f47f6bb7ae1"
 
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.42.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9aec5da331524158c6d1a4ac0ab1541149c0b9505fde06423b02f5ef0106b9f0"
+
 [[package]]
 name = "windows_x86_64_msvc"
 version = "0.52.6"
@@ -2545,6 +2858,16 @@ version = "0.6.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1ffae5123b2d3fc086436f8834ae3ab053a283cfac8fe0a0b8eaae044768a4c4"
 
+[[package]]
+name = "xattr"
+version = "1.6.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32e45ad4206f6d2479085147f02bc2ef834ac85886624a23575ae137c8aa8156"
+dependencies = [
+ "libc",
+ "rustix",
+]
+
 [[package]]
 name = "yoke"
 version = "0.8.3"
@@ -2653,3 +2976,31 @@ name = "zmij"
 version = "1.0.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b8848ee67ecc8aedbaf3e4122217aff892639231befc6a1b58d29fff4c2cabaa"
+
+[[package]]
+name = "zstd"
+version = "0.13.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e91ee311a569c327171651566e07972200e76fcfe2242a4fa446149a3881c08a"
+dependencies = [
+ "zstd-safe",
+]
+
+[[package]]
+name = "zstd-safe"
+version = "7.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f49c4d5f0abb602a93fb8736af2a4f4dd9512e36f7f570d66e65ff867ed3b9d"
+dependencies = [
+ "zstd-sys",
+]
+
+[[package]]
+name = "zstd-sys"
+version = "2.0.16+zstd.1.5.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91e19ebc2adc8f83e43039e79776e3fda8ca919132d68a1fed6a5faca2683748"
+dependencies = [
+ "cc",
+ "pkg-config",
+]
diff --git a/crates/csp/Cargo.toml b/crates/csp/Cargo.toml
index 93d1493..14bacfa 100644
--- a/crates/csp/Cargo.toml
+++ b/crates/csp/Cargo.toml
@@ -20,19 +20,11 @@ sha2 = { workspace = true }
 tempfile = { workspace = true }
 # Phase 3 — real Model2Vec dense embeddings (official MinishLab Rust port).
 model2vec-rs = { workspace = true }
-# Phase 3 — tree-sitter AST chunking (curated grammar set; statically linked for
-# the single-binary goal — unsupported languages fall back to line chunking).
+# Phase 3 — tree-sitter AST chunking. Full upstream-parity grammar coverage via
+# `tree-sitter-language-pack` (306 languages), replacing the earlier ~14-grammar
+# curated static set (see ADR-0004). Parsers are fetched from GitHub releases on
+# first use and cached on disk (`dynamic-loading` + `download`, the crate
+# defaults); a language with no available grammar (or an offline fetch failure)
+# degrades to line chunking exactly as before.
 tree-sitter = { workspace = true }
-tree-sitter-rust = "0.24"
-tree-sitter-python = "0.25"
-tree-sitter-javascript = "0.25"
-tree-sitter-typescript = "0.23"
-tree-sitter-go = "0.25"
-tree-sitter-java = "0.23"
-tree-sitter-c = "0.24"
-tree-sitter-cpp = "0.23"
-tree-sitter-ruby = "0.23"
-tree-sitter-json = "0.24"
-tree-sitter-bash = "0.25"
-tree-sitter-html = "0.23"
-tree-sitter-css = "0.25"
+tree-sitter-language-pack = "1.9"
diff --git a/crates/csp/src/chunking/core.rs b/crates/csp/src/chunking/core.rs
index 83b6576..7b46133 100644
--- a/crates/csp/src/chunking/core.rs
+++ b/crates/csp/src/chunking/core.rs
@@ -3,41 +3,55 @@
 //!
 //! The merge algorithm is generic over [`AstNode`] so it can be unit-tested with
 //! mock nodes; in production it is driven by [`tree_sitter::Node`] via [`TsNode`].
-//! A curated set of grammars is statically linked (see [`language_for`]); a
-//! language with no bundled grammar makes [`chunk`] return `None` and callers
-//! fall back to [`chunk_lines`] — exactly the upstream behavior when
-//! `tree_sitter_language_pack` has no parser for the language.
+//! Grammars come from [`tree_sitter_language_pack`] (306 languages, full upstream
+//! parity — semble uses the Python `tree_sitter_language_pack`; see ADR-0004).
+//! Parsers are fetched from GitHub releases on first use and cached on disk; a
+//! language with no available grammar — or an offline fetch failure — makes
+//! [`language_for`] return `None`, so [`chunk`] returns `None` and callers fall
+//! back to [`chunk_lines`], exactly the upstream behavior when the language pack
+//! has no parser for the language.
+
+use std::collections::HashSet;
+use std::sync::{LazyLock, Mutex};
 
 use tree_sitter::{Language, Parser};
 
 pub const RECURSION_DEPTH: usize = 500;
 pub const MIN_CHUNK_SIZE: usize = 50;
 
+/// Languages we've already warned about failing to resolve, so a polyglot
+/// offline index degrades quietly after the first notice per language.
+static WARNED_LANGUAGES: LazyLock<Mutex<HashSet<String>>> =
+    LazyLock::new(|| Mutex::new(HashSet::new()));
+
 /// Resolve a semble language name (the values in
-/// [`crate::indexing::files`]'s `EXTENSION_TO_LANGUAGE`) to a statically-linked
-/// tree-sitter grammar, or `None` when no grammar is bundled for it.
+/// [`crate::indexing::files`]'s `EXTENSION_TO_LANGUAGE`) to a tree-sitter grammar
+/// from the language pack, or `None` when the pack has no grammar for it.
 ///
-/// The curated set covers the common code languages; everything else falls back
-/// to line chunking. Add a grammar crate + an arm here to extend coverage.
+/// This calls [`tree_sitter_language_pack::get_language`], which downloads the
+/// parser from GitHub releases on first use and caches it on disk; later calls
+/// hit the in-process registry. A network failure (offline) or an unknown
+/// language degrades to `None` → line chunking, with a one-time stderr warning
+/// per language so the cause is visible without spamming a polyglot index. Use
+/// [`is_supported_language`] (a metadata-only check) when you only need to know
+/// whether a grammar *exists* without triggering a download.
 pub fn language_for(language: &str) -> Option<Language> {
-    let lang: Language = match language {
-        "rust" => tree_sitter_rust::LANGUAGE.into(),
-        "python" => tree_sitter_python::LANGUAGE.into(),
-        "javascript" => tree_sitter_javascript::LANGUAGE.into(),
-        "typescript" => tree_sitter_typescript::LANGUAGE_TYPESCRIPT.into(),
-        "tsx" => tree_sitter_typescript::LANGUAGE_TSX.into(),
-        "go" => tree_sitter_go::LANGUAGE.into(),
-        "java" => tree_sitter_java::LANGUAGE.into(),
-        "c" => tree_sitter_c::LANGUAGE.into(),
-        "cpp" => tree_sitter_cpp::LANGUAGE.into(),
-        "ruby" => tree_sitter_ruby::LANGUAGE.into(),
-        "json" => tree_sitter_json::LANGUAGE.into(),
-        "bash" => tree_sitter_bash::LANGUAGE.into(),
-        "html" => tree_sitter_html::LANGUAGE.into(),
-        "css" => tree_sitter_css::LANGUAGE.into(),
-        _ => return None,
-    };
-    Some(lang)
+    match tree_sitter_language_pack::get_language(language) {
+        Ok(lang) => Some(lang),
+        Err(err) => {
+            // Don't swallow the error silently: warn once per language, then
+            // fall back to line chunking (the caller treats `None` that way).
+            if let Ok(mut warned) = WARNED_LANGUAGES.lock() {
+                if warned.insert(language.to_string()) {
+                    eprintln!(
+                        "csp: could not load tree-sitter grammar for '{language}': {err}. \
+                         Falling back to line-based chunking for this language."
+                    );
+                }
+            }
+            None
+        }
+    }
 }
 
 /// A half-open `[start, end)` boundary in character offsets.
@@ -54,9 +68,15 @@ pub trait AstNode: Sized {
     fn children(&self) -> Vec<Self>;
 }
 
-/// Check if the language has a bundled tree-sitter grammar.
+/// Check whether the language pack knows a grammar for `language`.
+///
+/// This is a metadata-only lookup ([`tree_sitter_language_pack::has_language`],
+/// resolving aliases) — unlike [`language_for`] it does **not** download the
+/// parser, so [`crate::chunking::source::chunk_source`] can gate AST chunking
+/// cheaply before paying for a fetch. A recognized language can still fall back
+/// to line chunking later if the actual download fails (e.g. offline).
 pub fn is_supported_language(language: &str) -> bool {
-    language_for(language).is_some()
+    tree_sitter_language_pack::has_language(language)
 }
 
 /// [`AstNode`] adapter over a real [`tree_sitter::Node`]. `Node` is `Copy` and
@@ -320,7 +340,8 @@ mod tests {
     }
 
     #[test]
-    fn supported_languages_resolve_grammars() {
+    fn recognizes_expanded_language_set() {
+        // The original curated set stays supported...
         for lang in [
             "rust",
             "python",
@@ -338,13 +359,20 @@ mod tests {
             "css",
         ] {
             assert!(is_supported_language(lang), "{lang} should be supported");
+        }
+        // ...plus the languages that used to fall through to line chunking and
+        // now resolve to a language-pack grammar (full upstream parity). This is
+        // a metadata-only check (`has_language`) — it does not download parsers.
+        for lang in [
+            "kotlin", "swift", "php", "scala", "lua", "csharp", "dart", "elixir", "haskell",
+            "ocaml", "zig", "nix", "perl", "r", "julia", "clojure",
+        ] {
             assert!(
-                language_for(lang).is_some(),
-                "{lang} grammar should resolve"
+                is_supported_language(lang),
+                "{lang} should be supported by the language pack"
             );
         }
         assert!(!is_supported_language("not-a-real-language"));
-        assert!(language_for("not-a-real-language").is_none());
     }
 
     // --- merge_adjacent_chunks ---
@@ -470,13 +498,21 @@ mod tests {
 
     #[test]
     fn chunk_returns_none_without_parser() {
+        // An unknown language is rejected by the language pack's bundled manifest
+        // without any network access, so `chunk` returns `None` → line fallback.
         assert_eq!(
             chunk("let x = 1\n", "__definitely_not_a_real_language__", 1500),
             None
         );
     }
 
+    // The remaining `chunk(...)` tests parse real source, which makes the language
+    // pack download the grammar from GitHub releases on first use (then cache it).
+    // They are `#[ignore]`d so the default `cargo test` stays offline; run them
+    // with `cargo test -- --ignored` where network is available.
+
     #[test]
+    #[ignore = "downloads a tree-sitter grammar from GitHub releases"]
     fn chunk_parses_real_rust_into_covering_boundaries() {
         let src = "fn a() {\n    let x = 1;\n}\n\nfn b() {\n    let y = 2;\n}\n";
         let boundaries = chunk(src, "rust", 1500).expect("rust is supported → Some");
@@ -498,6 +534,7 @@ mod tests {
     }
 
     #[test]
+    #[ignore = "downloads a tree-sitter grammar from GitHub releases"]
     fn chunk_byte_to_char_handles_multibyte() {
         // A multibyte comment ensures byte→char conversion doesn't over-count.
         let src = "// café ☕ a comment\nfn z() {}\n";
@@ -507,4 +544,43 @@ mod tests {
             assert!(b.end <= n, "char boundary {b:?} exceeds char count {n}");
         }
     }
+
+    #[test]
+    #[ignore = "downloads tree-sitter grammars from GitHub releases"]
+    fn newly_supported_languages_are_ast_chunked() {
+        // Languages outside the old curated set now AST-chunk instead of falling
+        // back to line chunking. A small `desired_length` forces a split that the
+        // AST honors at declaration boundaries.
+        let cases = [
+            (
+                "kotlin",
+                "fun a() {\n    val x = 1\n}\n\nfun b() {\n    val y = 2\n}\n",
+            ),
+            (
+                "swift",
+                "func a() {\n    let x = 1\n}\n\nfunc b() {\n    let y = 2\n}\n",
+            ),
+            (
+                "php",
+                "<?php\nfunction a() {\n    $x = 1;\n}\nfunction b() {\n    $y = 2;\n}\n",
+            ),
+        ];
+        for (lang, src) in cases {
+            let boundaries = chunk(src, lang, 1500)
+                .unwrap_or_else(|| panic!("{lang} should AST-chunk → Some, not line fallback"));
+            assert!(!boundaries.is_empty(), "{lang}: expected boundaries");
+            let n = src.chars().count();
+            for b in &boundaries {
+                assert!(
+                    b.start <= b.end && b.end <= n,
+                    "{lang}: boundary {b:?} out of range (n={n})"
+                );
+            }
+            let split = chunk(src, lang, 20).expect("Some");
+            assert!(
+                split.len() >= 2,
+                "{lang}: small desired_length should split: {split:?}"
+            );
+        }
+    }
 }