Merge pull request #123 from levineuwirth/json-yaml-grammar

feat(json-yaml): JSON + YAML grammars and language servers

Cargo.lock

@@ -2558,6 +2558,7 @@ dependencies = [
  "tree-sitter-cuda",
  "tree-sitter-go",
  "tree-sitter-javascript",
+ "tree-sitter-json",
  "tree-sitter-lua",
  "tree-sitter-make",
  "tree-sitter-md",
@@ -2565,6 +2566,7 @@ dependencies = [
  "tree-sitter-rust",
  "tree-sitter-toml-ng",
  "tree-sitter-typescript",
+ "tree-sitter-yaml",
  "tree-sitter-zig",
  "unicode-width",
 ]
@@ -3807,6 +3809,16 @@ dependencies = [
  "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"
@@ -3883,6 +3895,16 @@ dependencies = [
  "tree-sitter-language",
 ]
 
+[[package]]
+name = "tree-sitter-yaml"
+version = "0.7.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "53c223db85f05e34794f065454843b0668ebc15d240ada63e2b5939f43ce7c97"
+dependencies = [
+ "cc",
+ "tree-sitter-language",
+]
+
 [[package]]
 name = "tree-sitter-zig"
 version = "1.1.2"

Cargo.toml

@@ -196,6 +196,13 @@ tree-sitter-javascript = "0.25"
 tree-sitter-typescript = "0.23"
 tree-sitter-toml-ng = "0.7"
 tree-sitter-zig = "1.1"
+# JSON + YAML — config formats + the honest gate on the Jupyter path
+# (JSON). Both are ABI-current (`LANGUAGE: LanguageFn` via
+# `tree-sitter-language`), NOT a `tree-sitter ^0.20` fork. Registering
+# yaml also lights up markdown `---` frontmatter through the #122
+# injection engine (the block injection query already sets yaml for it).
+tree-sitter-json = "0.24"
+tree-sitter-yaml = "0.7"
 # T M9.7: markdown grammar so prompt result buffers with
 # `_meta.format = "markdown"` get structured highlighting through the
 # same M4 path as rust/lua — no special-case painter in Lua.

builtin/runtime/lsp.lua

@@ -200,6 +200,62 @@ pmacs.lsp.config.zig = pmacs.lsp.config.zig or {
   args = {},
 }
 
+-- JSON via the VS Code JSON server, binary `vscode-json-language-server`.
+-- It is a PUSH-model server: it reads config from
+-- `workspace/didChangeConfiguration` (the daemon now sends one after
+-- `initialized`) and does NOT issue `workspace/configuration` pulls, so
+-- without that push these settings would be inert. `json.validate.enable`
+-- is set explicitly true — the server treats a MISSING value as false, so
+-- an empty `json = {}` would silently disable validation. Schema
+-- retrieval performs NETWORK ACCESS for remote `$schema` URLs (left
+-- enabled; `handledSchemaProtocols = {"file"}` would disable it but break
+-- remote schemas without a `vscode/content` impl). Note: the server does
+-- NOT auto-associate `package.json`/`tsconfig.json` — it starts with empty
+-- contributions; explicit `$schema` refs or configured `json.schemas` /
+-- a `json/schemaAssociations` push (not implemented) are required.
+-- Provider: pin `@t1ckbase/vscode-langservers-extracted@2.0.2`
+-- (`npm install -g @t1ckbase/vscode-langservers-extracted@2.0.2`).
+-- Its published payload bundles the JSON server from VS Code 1.129.0,
+-- preserves this command name, and was live-smoked through initialize →
+-- config push → invalid-JSON diagnostic → shutdown. The older unscoped
+-- package is stale and the current `@zed-industries` payload has a broken
+-- JSON launcher; neither is the recommended provider.
+pmacs.lsp.config.json = pmacs.lsp.config.json or {
+  command = "vscode-json-language-server",
+  args = { "--stdio" },
+  settings = {
+    json = { validate = { enable = true } },
+    http = {},
+  },
+}
+
+-- YAML via Red Hat `yaml-language-server`. On
+-- `workspace/didChangeConfiguration` (now pushed after `initialized`) it
+-- reads the `yaml`, `http`, `[yaml]`, `editor`, and `files` sections — all
+-- ship present-not-null (empty ⇒ server defaults). SchemaStore / remote
+-- schema retrieval performs NETWORK ACCESS by default. The standalone
+-- server does not upload telemetry itself — it emits `telemetry/event`
+-- notifications to its client, and pmacs has no telemetry uploader, so a
+-- `redhat.telemetry` setting would be inert and is not shipped. Sections
+-- live-observed with Red Hat `yaml-language-server@1.24.0`: its initial
+-- pull requests exactly those five sections, and opening a YAML document
+-- requests a second scoped `[yaml]` section. The standalone smoke reached
+-- a real syntax diagnostic and clean shutdown. The PATH-gated pmacs
+-- acceptance also proves auto-attach, initialization, config pulls, a
+-- syntax diagnostic, and continued server liveness with both catalogs
+-- disabled for network-free determinism.
+pmacs.lsp.config.yaml = pmacs.lsp.config.yaml or {
+  command = "yaml-language-server",
+  args = { "--stdio" },
+  settings = {
+    yaml = {},
+    http = {},
+    ["[yaml]"] = {},
+    editor = {},
+    files = {},
+  },
+}
+
 -- LSP-side extension → language map, deliberately independent of the
 -- tree-sitter detection in `pmacs.parse`. Consulted only when
 -- `pmacs.parse.language_for_path` finds nothing (an extension with a
@@ -267,6 +323,11 @@ pmacs.lsp.filetypes.toml = pmacs.lsp.filetypes.toml or "toml"
 -- Zig (zls). `.zon` is Zig Object Notation, handled by the same server.
 pmacs.lsp.filetypes.zig = pmacs.lsp.filetypes.zig or "zig"
 pmacs.lsp.filetypes.zon = pmacs.lsp.filetypes.zon or "zig"
+-- JSON / YAML. Both ship grammars, so `language_for_path` already resolves
+-- these and the map is the stable-id fallback (same role as `lua`/`cuda`).
+pmacs.lsp.filetypes.json = pmacs.lsp.filetypes.json or "json"
+pmacs.lsp.filetypes.yaml = pmacs.lsp.filetypes.yaml or "yaml"
+pmacs.lsp.filetypes.yml = pmacs.lsp.filetypes.yml or "yaml"
 
 -- Per-buffer attachment record: { language, server, uri, version }.
 -- Keyed by `tostring(BufferIdLua)` because BufferIdLua hands out fresh

docs/agent-handoff.md

@@ -323,11 +323,18 @@ runtime/Lua-registered languages (v1 resolves only against
 `BUILTIN_LANGUAGES`), and the next injection *consumers* gated on new
 grammars — HTML/CSS/GraphQL/SQL (`<script>`/`<style>`, JS/TS template
 literals, doc-comment code); modeline detection as a 5th layer
-(`-*- mode: … -*-` / `# vim: ft=…`); JSON/YAML grammars+LSP;
+(`-*- mode: … -*-` / `# vim: ft=…`);
 byte-accurate multibyte cursor placement in `move_active_cursor_to`
-(still steps one codepoint per LSP byte column). A full Jupyter `.ipynb`
+(still steps one codepoint per LSP byte column). **JSON + YAML PR #123
-setup (reader → editable → kernel execution) is a real arc now gated on
+OPEN** (grammar-gap style, `tree-sitter-json`/`-yaml`; LSP configs
-**JSON** (injections shipped in #122), NOT a one-shot.
+`vscode-json-language-server` with provider pin
+`@t1ckbase/vscode-langservers-extracted@2.0.2`, plus
+`yaml-language-server`). The public and checkpoint branches are both at
+fully gated `5c202c5`, rebased onto `f8096ff`; the JSON and YAML
+PATH-gated pmacs smokes both passed, and the PR awaits user review.
+Once merged, YAML `---` and TOML `+++` markdown frontmatter highlight via
+the #122 engine and the Jupyter reader → editable → kernel arc has both
+grammar prerequisites.
 GPU: auto-reconnect after daemon restart, splits/multi-buffer, gutter
 riders (whitespace guides, folding, git markers).
 Themes (full list in theme-faces framing rev 9 "Deferred (named)"):

docs/json-yaml-framing.md

@@ -0,0 +1,220 @@
+# JSON + YAML grammars — framing (side quest, highlight family)
+
+**Revision 4 — 2026-07-21. Status: PR #123 open and awaiting review;
+the public and checkpoint branches are at fully gated `5c202c5`, rebased
+onto `main` `f8096ff`.**
+The JSON provider and Red Hat YAML 1.24.0 have each passed their
+PATH-gated pmacs acceptance, in addition to the deterministic fake-server
+config-push proof and the YAML standalone protocol smoke.
+
+**Intent.** Add `tree-sitter-json` and `tree-sitter-yaml` grammars (plus
+their language servers) to the bundle. Two config formats that pmacs
+currently renders as plain text, and — the reason this is the natural
+next side quest — the **honest gate on the Jupyter `.ipynb` path** (JSON)
+and an **immediate payoff from the injection engine just shipped (#122)**:
+the markdown block grammar's `injections.scm` already sets
+`injection.language "yaml"` for `---` frontmatter and `"toml"` for `+++`
+frontmatter, so registering YAML lights up YAML frontmatter highlighting
+with zero extra wiring (TOML frontmatter already works — `toml` landed in
+#118 and injections in #122). This is a mostly-additive grammar-gap-style
+change, following the #118 pattern, with the frontmatter/fence synergy as
+the demonstrable headline.
+
+---
+
+## Ground truth (as of `main` @ `56eb67e`, #121)
+
+- **Adding a grammar** is a one-line `LanguageEntry` in
+  `crate::syntax::BUILTIN_LANGUAGES` (`name`, `extensions`, `loader`,
+  `highlights_query`, `injections_query`) + a `tree-sitter-foo` dep. The
+  Lua `buffer.after-load` path picks it up automatically; detection is
+  extension → LSP filetype → filename → shebang
+  (`resolve_active_language`).
+- **Grammar name MUST equal the `pmacs.lsp.config.<name>` key** — grammar
+  detection wins over the filetype map, so the name it resolves is the id
+  the LSP client keys off (the #118 invariant; there's an acceptance test
+  that pins every grammar-gap language to its config key).
+- **LSP configs** are `pmacs.lsp.config.<name> = … or { command, args,
+  [settings|init_options] }` (`builtin/runtime/lsp.lua`); no json/yaml
+  config today. `pmacs.lsp.filetypes` is the LSP-only extension fallback
+  (consulted only when `language_for_path` misses).
+- **Injection synergy (#122).** The bundled `tree_sitter_md::
+  INJECTION_QUERY_BLOCK` contains:
+  - `((minus_metadata) @injection.content (#set! injection.language
+    "yaml"))` — `---`-fenced frontmatter,
+  - `((plus_metadata) @injection.content (#set! injection.language
+    "toml"))` — `+++`-fenced frontmatter,
+  - fenced code blocks via the dynamic info-string.
+  So a registered `yaml` grammar is injected into markdown frontmatter
+  automatically, and ` ```json `/` ```yaml `/` ```yml ` fences resolve
+  (`yml`→yaml is already in `default_injection_aliases`; `json` is the
+  bundled name).
+
+**Confirmed crate facts** (probed against the registry + a build under
+tree-sitter 0.26):
+
+1. `tree-sitter-json` **0.24.8** — `pub const LANGUAGE: LanguageFn` (via
+   `tree-sitter-language`, the modern shared ABI) + `HIGHLIGHTS_QUERY`.
+   Compiles and links under our tree-sitter 0.26. No `INJECTIONS_QUERY`
+   (JSON embeds nothing).
+2. `tree-sitter-yaml` **0.7.2** — same shape (`LANGUAGE: LanguageFn`,
+   `HIGHLIGHTS_QUERY`, `tree-sitter-language` dep). Compiles under 0.26.
+   No `INJECTIONS_QUERY`.
+3. Both are the ABI-current crates — **not** a `tree-sitter ^0.20` fork
+   (the dockerfile trap from #118). A single build confirmed link +
+   compile; runtime `set_language` is pinned by the ABI acceptance test.
+
+---
+
+## Decisions
+
+### Q#JY1 — Two `LanguageEntry`s, self-contained highlights, no injections
+
+Add `json` and `yaml` to `BUILTIN_LANGUAGES`, each
+`highlights_query: &[…::HIGHLIGHTS_QUERY]` (self-contained, no
+`; inherits:` delta), `injections_query: &[]`. Extensions:
+
+- **json:** `.json`. (`.jsonc`/`.json5` — comment/trailing-comma variants
+  the plain JSON grammar rejects — are **deferred**; a `.jsonc` grammar
+  or a lenient mode is a separate call.)
+- **yaml:** `.yaml`, `.yml`.
+
+Root kinds (pinned by the ABI test): json `document`, yaml `stream`.
+
+### Q#JY2 — LSP configs: `vscode-json-language-server` + `yaml-language-server`
+
+- **json:** binary `vscode-json-language-server --stdio` (the VS Code
+  JSON server). It is **push-model**: it reads config from
+  `workspace/didChangeConfiguration` and does **not** issue
+  `workspace/configuration` pulls — so pmacs, which previously only
+  *answered* pulls, must now also **push** a `didChangeConfiguration`
+  after `initialized` (a general LSP-client fix in `src/lsp.rs`; pull
+  servers ignore it). `json.validate.enable` is set **explicitly true**
+  — a missing value reads as false and silently disables validation, so
+  an empty `json = {}` is wrong. The server does **not** auto-associate
+  `package.json`/`tsconfig.json` (it starts with empty contributions);
+  explicit `$schema` refs or configured `json.schemas` / a
+  `json/schemaAssociations` push (not implemented) are required. Schema
+  retrieval performs **network access** for remote `$schema` URLs, left
+  enabled (`handledSchemaProtocols = {"file"}` would disable it but break
+  remote schemas without a `vscode/content` impl). **Provider:** pin
+  `@t1ckbase/vscode-langservers-extracted@2.0.2`
+  (`npm install -g @t1ckbase/vscode-langservers-extracted@2.0.2`). Its
+  published payload bundles the JSON server from VS Code 1.129.0,
+  preserves the `vscode-json-language-server` command, and was
+  live-smoked through initialize → config push → invalid-JSON diagnostic
+  → shutdown. The unscoped package is stale; the current
+  `@zed-industries` payload has a broken JSON launcher, so neither is the
+  recommended provider.
+- **yaml:** `yaml-language-server --stdio` (Red Hat). Its settings handler
+  reads the sections **`yaml`, `http`, `[yaml]`, `editor`, `files`** (via
+  `didChangeConfiguration` / pulls) — all ship present-not-null. It does
+  **not** upload telemetry itself (it emits `telemetry/event` to the
+  client; pmacs has no uploader), so a `redhat.telemetry` setting is inert
+  and is not shipped. SchemaStore / remote schema retrieval performs
+  **network access** by default.
+
+Both servers stay **external** (installed by the user), adding **no
+licensing payload** to pmacs; if either is ever bundled, retain its MIT +
+dependency notices. The exact sections are **pinned in the config + a
+test** (not merely "some non-nil table exists"). The pinned JSON
+provider was installed into an isolated temporary prefix and
+live-smoked through pmacs. Red Hat `yaml-language-server@1.24.0` was
+also installed in an isolated prefix and live-smoked over stdio: its
+initial configuration pull was exactly `yaml`, `http`, `[yaml]`,
+`editor`, `files`; opening the document caused a second scoped
+`[yaml]` pull; invalid YAML produced a parser diagnostic; shutdown was
+clean. Both providers have also passed their PATH-gated pmacs acceptance.
+Config-push delivery is proven deterministically through the fake server's
+config sink. Servers activate only if installed; the grammar is the
+always-on value.
+
+### Q#JY3 — Filetype fallback + alias entries
+
+Add `pmacs.lsp.filetypes` entries (`json`→json, `yaml`/`yml`→yaml) as the
+stable-id fallback (grammar detection wins in practice, same role as the
+`cuda`/`lua` entries). `default_injection_aliases` already has `yml`→yaml;
+`json`/`yaml` are bundled names needing no alias. Special *filenames*
+(`.prettierrc`, `docker-compose.yml` is already `.yml`, extensionless
+CI/config yaml) are **deferred** to the filename map as a follow-up.
+
+### Q#JY4 — Frontmatter/fence highlighting is the headline, and it's free
+
+No new injection wiring: registering `yaml` makes the existing markdown
+`minus_metadata`→yaml injection resolve, and ` ```json `/` ```yaml `
+fences resolve through the #122 engine. Acceptance proves both end to end
+(this is the demonstrable payoff and the tie-back to injections).
+
+---
+
+## Bets
+
+1. The two crates are ABI-current and drop in like the #118 grammar-gap
+   languages — verified by a build; the ABI test is the runtime pin.
+2. The frontmatter/fence synergy needs zero engine changes — it falls out
+   of #122 + the markdown injection query.
+3. The two configuration models are now observed: JSON consumes the
+   pushed full settings object; YAML 1.24.0 pulls the five documented
+   sections plus a document-scoped `[yaml]` request. The remaining bet
+   was that pmacs answers the real YAML server correctly end to end;
+   the PATH-gated acceptance now proves that against version 1.24.0.
+
+## Deferred (named)
+
+- `.jsonc` / `.json5` (comments / trailing commas) — needs a lenient
+  grammar or variant entry.
+- Special-filename detection for extensionless config files (`.prettierrc`,
+  CI yaml) via the filename map.
+- JSON **schema** wiring (custom `json.schemas` / `yaml.schemas` settings)
+  beyond the servers' built-in schema stores.
+- The Jupyter `.ipynb` arc itself (JSON is its prerequisite, not its
+  delivery).
+
+## Acceptance
+
+1. `builtin_languages_include_json_and_yaml` — entries present, claim
+   their extensions, ship non-empty highlights.
+2. `json_grammar_loads_and_parses` — ABI: `set_language` + parse a JSON
+   object; root `document`, no error (the runtime ABI pin).
+3. `yaml_grammar_loads_and_parses` — ABI: parse a YAML mapping; root
+   `stream`, no error.
+4. `json_yaml_highlights_compile` — both highlights queries compile and
+   resolve several capture classes.
+5. `language_for_path_resolves_json_yaml` — `.json`→json, `.yaml`/`.yml`→
+   yaml.
+6. `json_yaml_align_with_lsp_configs` — grammar name == the
+   `pmacs.lsp.config.<name>` key (the #118 invariant).
+7. **`yaml_frontmatter_injects_in_markdown`** — a markdown doc with a
+   `---\nkey: val\n---` frontmatter yields a `yaml` child layer that
+   highlights; **the headline synergy with #122**.
+8. `json_fence_injects_in_markdown` — a ` ```json ` fence yields a `json`
+   child layer.
+9. `m4_json_yaml_lsp_configs_pin_command_and_sections` — the configs
+   pin the binary + `json.validate.enable = true` + the exact section
+   sets (json: `json`,`http`; yaml: `yaml`,`http`,`[yaml]`,`editor`,
+   `files`; no inert `redhat.telemetry`) — pinned, not merely non-nil.
+10. `m4_5_initial_config_pushed_via_did_change_configuration` — the
+    daemon PUSHES `workspace/didChangeConfiguration` after `initialized`
+    (the push-model delivery path), verified through the fake server's
+    config sink. Without it, push-only servers' settings are inert.
+11. `m4_real_json_provider_receives_config_and_reports_diagnostics` —
+    PATH-gated live smoke for the pinned provider: initialize through
+    pmacs, receive the pushed default config, open invalid JSON, and
+    publish a syntax diagnostic. Skips when the binary is absent.
+12. `m4_real_yaml_provider_pulls_config_and_reports_diagnostics` —
+    PATH-gated live smoke for Red Hat `yaml-language-server@1.24.0`:
+    auto-attach through pmacs, disable SchemaStore and Kubernetes CRD
+    catalog network access for determinism, reach initialized, open
+    invalid YAML, publish a diagnostic, and remain alive.
+
+## Risks / interactions
+
+- **LSP configuration** (Q#JY2) — JSON push, YAML standalone pulls, and
+  the real YAML-through-pmacs path are observed. Both live provider
+  tests remain PATH-gated, so release verification must put the pinned
+  binaries on PATH rather than accepting their skip paths.
+- **Themes / injections** — untouched. This is pure grammar+detection
+  addition; it consumes the #122 engine, doesn't change it. No protocol
+  bump.
+- **`.yml` vs `.yaml`** — both map to `yaml`; no collision with any
+  existing entry.

src/bin/pmacs_fake_lsp.rs

@@ -414,6 +414,26 @@ fn main() {
                 });
                 write_frame(&mut stdout, &resp);
             }
+            ("workspace/didChangeConfiguration", _) => {
+                // Record the pushed `settings` so a test can assert the
+                // daemon delivered configuration after `initialized` (the
+                // push-model config-delivery path push-only servers like the
+                // VS Code JSON server rely on). One JSON line per push.
+                if let Ok(sink) = std::env::var("PMACS_FAKE_LSP_CONFIG_SINK") {
+                    use std::io::Write as _;
+                    if let Ok(mut f) = std::fs::OpenOptions::new()
+                        .create(true)
+                        .append(true)
+                        .open(&sink)
+                    {
+                        let settings = params
+                            .get("settings")
+                            .cloned()
+                            .unwrap_or(serde_json::Value::Null);
+                        let _ = writeln!(f, "{settings}");
+                    }
+                }
+            }
             ("textDocument/didOpen" | "textDocument/didChange", _) => {
                 let uri = params
                     .get("textDocument")

src/lsp.rs

@@ -2497,6 +2497,25 @@ impl LspManager {
         }
     }
 
+    /// Push the client's configured `settings` via
+    /// `workspace/didChangeConfiguration` immediately after `initialized`.
+    /// Push-model servers — notably the VS Code JSON server, which listens
+    /// for this notification and does NOT issue `workspace/configuration`
+    /// pulls — only learn their config this way; pull-model servers
+    /// (pyright, clangd, gopls) ignore it and pull instead, so it is safe
+    /// to send unconditionally. No-op when no `settings` are configured.
+    fn push_initial_configuration(&self, sid: LspServerId) {
+        if let Some(client) = self.clients.get(&sid)
+            && let Some(settings) = client.spec.settings.clone()
+        {
+            let cfg = make_notification(
+                "workspace/didChangeConfiguration",
+                json!({ "settings": settings }),
+            );
+            let _ = send_frame_to(&self.supervisor, client, &cfg);
+        }
+    }
+
     fn handle_response(
         &mut self,
         sid: LspServerId,
@@ -2552,6 +2571,9 @@ impl LspManager {
             if let Some(client) = self.clients.get(&sid) {
                 let _ = send_frame_to(&self.supervisor, client, &body);
             }
+            // Push the configured settings right after `initialized`
+            // (before any deferred `didOpen`).
+            self.push_initial_configuration(sid);
             // T M4.5 Option B: honour the server's negotiated
             // `general.positionEncoding`. Absent ⇒ LSP spec default
             // (UTF-16). We advertised `["utf-8","utf-16"]`, so a

src/syntax.rs

@@ -1027,6 +1027,27 @@ pub const BUILTIN_LANGUAGES: &[LanguageEntry] = &[
         highlights_query: &[tree_sitter_zig::HIGHLIGHTS_QUERY],
         injections_query: &[],
     },
+    // JSON + YAML — config formats, both self-contained highlights and no
+    // injections of their own. Registering `yaml` also lights up markdown
+    // `---` frontmatter via the #122 injection engine (the markdown block
+    // injection query sets `injection.language "yaml"` for `minus_metadata`;
+    // `+++` TOML frontmatter already works). Root kinds: json `document`,
+    // yaml `stream`. `.jsonc`/`.json5` (comments / trailing commas) are a
+    // deferred variant — the plain JSON grammar rejects them.
+    LanguageEntry {
+        name: "json",
+        extensions: &["json"],
+        loader: || tree_sitter_json::LANGUAGE.into(),
+        highlights_query: &[tree_sitter_json::HIGHLIGHTS_QUERY],
+        injections_query: &[],
+    },
+    LanguageEntry {
+        name: "yaml",
+        extensions: &["yaml", "yml"],
+        loader: || tree_sitter_yaml::LANGUAGE.into(),
+        highlights_query: &[tree_sitter_yaml::HIGHLIGHTS_QUERY],
+        injections_query: &[],
+    },
 ];
 
 /// Registry that the Lua surface ([`crate::lua_bindings::install_parse`])
@@ -2062,6 +2083,167 @@ mod tests {
         }
     }
 
+    #[test]
+    fn builtin_languages_include_json_and_yaml() {
+        // Framing acceptance #1: both entries present, claim their
+        // extensions, ship non-empty highlights.
+        let json = BUILTIN_LANGUAGES
+            .iter()
+            .find(|l| l.name == "json")
+            .expect("`json` entry present");
+        assert!(json.extensions.contains(&"json"), "`json` claims `.json`");
+        assert!(!json.highlights_query.is_empty(), "`json` ships highlights");
+        let yaml = BUILTIN_LANGUAGES
+            .iter()
+            .find(|l| l.name == "yaml")
+            .expect("`yaml` entry present");
+        assert!(yaml.extensions.contains(&"yaml"), "`yaml` claims `.yaml`");
+        assert!(yaml.extensions.contains(&"yml"), "`yaml` claims `.yml`");
+        assert!(!yaml.highlights_query.is_empty(), "`yaml` ships highlights");
+    }
+
+    #[test]
+    fn json_grammar_loads_and_parses() {
+        // Framing acceptance #2 / ABI pin: `tree-sitter-json` 0.24 is
+        // accepted by our tree-sitter 0.26 core; a JSON object parses to a
+        // `document` root without error.
+        let reg = SyntaxRegistry::new();
+        let language = reg.language("json").expect("`json` loads");
+        let mut buf = fresh_buffer("data.json");
+        buf.apply_edit(EditOp::Insert {
+            pos: 0,
+            bytes: b"{\n  \"name\": \"pmacs\",\n  \"nums\": [1, 2, 3],\n  \"ok\": true\n}\n",
+        })
+        .unwrap();
+        let view = ParseView::new(&buf, language, "json".to_owned());
+        let handle = view.handle();
+        let _vid = buf.attach_view(Box::new(view));
+        let bundle = parse_synchronously(&handle);
+        assert_eq!(
+            bundle.root_tree().root_node().kind(),
+            "document",
+            "json grammar roots at `document`"
+        );
+        assert!(
+            !bundle.root_tree().root_node().has_error(),
+            "json grammar parses an object without error"
+        );
+    }
+
+    #[test]
+    fn yaml_grammar_loads_and_parses() {
+        // Framing acceptance #3 / ABI pin: `tree-sitter-yaml` 0.7 loads and
+        // a YAML mapping parses to a `stream` root without error.
+        let reg = SyntaxRegistry::new();
+        let language = reg.language("yaml").expect("`yaml` loads");
+        let mut buf = fresh_buffer("config.yaml");
+        buf.apply_edit(EditOp::Insert {
+            pos: 0,
+            bytes: b"name: pmacs\nversion: 1\ntags:\n  - a\n  - b\n",
+        })
+        .unwrap();
+        let view = ParseView::new(&buf, language, "yaml".to_owned());
+        let handle = view.handle();
+        let _vid = buf.attach_view(Box::new(view));
+        let bundle = parse_synchronously(&handle);
+        assert_eq!(
+            bundle.root_tree().root_node().kind(),
+            "stream",
+            "yaml grammar roots at `stream`"
+        );
+        assert!(
+            !bundle.root_tree().root_node().has_error(),
+            "yaml grammar parses a mapping without error"
+        );
+    }
+
+    #[test]
+    fn json_yaml_highlights_compile() {
+        // Framing acceptance #4: both highlights queries compile against
+        // their grammars and resolve capture classes.
+        let reg = SyntaxRegistry::new();
+        let json = reg
+            .highlights_query("json")
+            .expect("json highlights compile");
+        assert!(
+            json.capture_names().len() >= 3,
+            "json highlights resolve capture classes; got {}",
+            json.capture_names().len()
+        );
+        let yaml = reg
+            .highlights_query("yaml")
+            .expect("yaml highlights compile");
+        assert!(
+            yaml.capture_names().len() >= 3,
+            "yaml highlights resolve capture classes; got {}",
+            yaml.capture_names().len()
+        );
+    }
+
+    #[test]
+    fn language_for_path_resolves_json_yaml() {
+        // Framing acceptance #5.
+        let reg = SyntaxRegistry::new();
+        assert_eq!(
+            reg.language_name_for_path("tsconfig.json").as_deref(),
+            Some("json")
+        );
+        assert_eq!(
+            reg.language_name_for_path("config.yaml").as_deref(),
+            Some("yaml")
+        );
+        assert_eq!(
+            reg.language_name_for_path("ci.yml").as_deref(),
+            Some("yaml")
+        );
+    }
+
+    #[test]
+    fn yaml_frontmatter_injects_in_markdown() {
+        // Framing acceptance #7 — THE headline synergy with #122: a markdown
+        // `---` frontmatter block (a `minus_metadata` node) is injected as
+        // yaml by the bundled markdown injection query, so registering the
+        // yaml grammar lights it up with no extra wiring.
+        let reg = SyntaxRegistry::new();
+        let src = b"---\ntitle: Hello\ntags: [a, b]\n---\n\n# Body\n";
+        let bundle = parse_layered(&reg, "markdown", src);
+        let yaml = bundle
+            .layers
+            .iter()
+            .find(|l| l.language_name == "yaml")
+            .expect("`---` frontmatter yields a yaml child layer");
+        assert_eq!(
+            yaml.tree.root_node().kind(),
+            "stream",
+            "yaml layer roots at stream"
+        );
+        let query = yaml
+            .highlight_query
+            .as_ref()
+            .expect("yaml highlights resolved");
+        let spans = compute_highlight_spans_for(query, &yaml.tree, &bundle.source, None);
+        assert!(!spans.is_empty(), "the yaml frontmatter layer highlights");
+    }
+
+    #[test]
+    fn json_fence_injects_in_markdown() {
+        // Framing acceptance #8: a ```json fence yields a json child layer
+        // through the #122 engine.
+        let reg = SyntaxRegistry::new();
+        let src = b"# Doc\n\n```json\n{\"a\": 1, \"b\": [2, 3]}\n```\n";
+        let bundle = parse_layered(&reg, "markdown", src);
+        let json = bundle
+            .layers
+            .iter()
+            .find(|l| l.language_name == "json")
+            .expect("a ```json fence yields a json child layer");
+        assert_eq!(
+            json.tree.root_node().kind(),
+            "document",
+            "json layer roots at document"
+        );
+    }
+
     #[test]
     fn builtin_languages_include_dockerfile_make_cmake() {
         for (name, exts) in [

tests/m4_acceptance.rs

@@ -6265,6 +6265,9 @@ fn m4_gap_grammars_align_with_lsp_configs() {
         ("A.tsx", "typescriptreact"),
         ("Cargo.toml", "toml"),
         ("build.zig", "zig"),
+        ("tsconfig.json", "json"),
+        ("config.yaml", "yaml"),
+        ("ci.yml", "yaml"),
     ] {
         let (grammar, has_cfg): (Option<String>, bool) = s
             .lua_host
@@ -6287,6 +6290,298 @@ fn m4_gap_grammars_align_with_lsp_configs() {
     }
 }
 
+/// JSON/YAML LSP configs pin the server commands and the settings shape
+/// each consumes (framing Q#JY2): JSON receives a pushed full object;
+/// YAML pulls five named sections. The pinned JSON and YAML providers each
+/// have a separate PATH-gated live smoke below. The point is to pin the
+/// contract, not merely assert that some settings table exists.
+#[test]
+fn m4_json_yaml_lsp_configs_pin_command_and_sections() {
+    use pmacs::editor::EditorState;
+    let s = EditorState::new();
+    let lua = s.lua_host.lua();
+
+    // json: the `@t1ckbase/vscode-langservers-extracted@2.0.2` binary
+    // (NOT the stale standalone `vscode-json-languageserver`), `--stdio`,
+    // and the `json` + `http` workspace-config sections present. The
+    // provider preserves this stable command name; its exact pin and live
+    // handshake evidence are documented beside the default config.
+    let json_command: String = lua
+        .load("return pmacs.lsp.config.json.command")
+        .eval()
+        .unwrap();
+    assert_eq!(
+        json_command, "vscode-json-language-server",
+        "json uses the pinned T1ckbase provider's stable command name"
+    );
+    // The JSON server is push-model (reads didChangeConfiguration, no
+    // pulls), so `json.validate.enable` must be EXPLICITLY true — a missing
+    // value reads as false and disables validation. Remote schemas left on.
+    let json_ok: bool = lua
+        .load(
+            "local c = pmacs.lsp.config.json
+             return c.args[1] == '--stdio'
+                 and c.settings.json.validate.enable == true
+                 and c.settings.http ~= nil
+                 and c.settings.handledSchemaProtocols == nil",
+        )
+        .eval()
+        .unwrap();
+    assert!(
+        json_ok,
+        "json config: --stdio, json.validate.enable=true, http present, remote schemas on"
+    );
+
+    // yaml: `yaml-language-server --stdio`. Its settings handler reads the
+    // `yaml`, `http`, `[yaml]`, `editor`, and `files` sections — pin all
+    // five, and confirm the inert `redhat.telemetry` is NOT shipped (the
+    // standalone server emits telemetry events to the client; it does not
+    // upload, and pmacs has no uploader).
+    let yaml_command: String = lua
+        .load("return pmacs.lsp.config.yaml.command")
+        .eval()
+        .unwrap();
+    assert_eq!(
+        yaml_command, "yaml-language-server",
+        "yaml uses the Red Hat yaml-language-server"
+    );
+    let yaml_ok: bool = lua
+        .load(
+            "local c = pmacs.lsp.config.yaml
+             return c.args[1] == '--stdio'
+                 and c.settings.yaml ~= nil
+                 and c.settings.http ~= nil
+                 and c.settings['[yaml]'] ~= nil
+                 and c.settings.editor ~= nil
+                 and c.settings.files ~= nil
+                 and c.settings.redhat == nil",
+        )
+        .eval()
+        .unwrap();
+    assert!(
+        yaml_ok,
+        "yaml config: --stdio, the five pulled sections present, no inert redhat.telemetry"
+    );
+}
+
+/// Round-1 finding (P1): the daemon must PUSH configuration via
+/// `workspace/didChangeConfiguration` after `initialized`. Push-model
+/// servers — notably the VS Code JSON server — never issue
+/// `workspace/configuration` pulls, so without the push their `settings`
+/// (including `json.validate.enable`) are inert. Verified through the fake
+/// server's config sink: the settings the daemon sends are recorded and
+/// inspected, proving delivery end to end.
+#[test]
+fn m4_5_initial_config_pushed_via_did_change_configuration() {
+    use pmacs::editor::EditorState;
+    let mut state = EditorState::new();
+    let fake = fake_lsp_path();
+    let dir = tempfile::tempdir().expect("tempdir");
+    let sink = dir.path().join("config.jsonl");
+    let file = dir.path().join("probe.rs");
+    std::fs::write(&file, "fn main() {}\n").expect("write");
+    let sink_disp = sink.display().to_string();
+    let file_disp = file.display().to_string();
+
+    // Point rust at the fake server WITH a settings table and route the
+    // config sink into the spawned process, then open the file (auto-attach
+    // → initialize → initialized → the config push).
+    state
+        .lua_host
+        .lua()
+        .load(format!(
+            "pmacs.lsp.config.rust = {{
+               command = '{fake}',
+               env = {{ PMACS_FAKE_LSP_CONFIG_SINK = '{sink_disp}' }},
+               settings = {{ rust = {{ probe = true }} }},
+             }}
+             pmacs.buffer.find_or_open('{file_disp}')"
+        ))
+        .exec()
+        .expect("configure + open");
+
+    assert!(
+        pump_lua_flag(
+            &mut state,
+            "(function() for _,r in ipairs(pmacs.lsp.list()) do \
+               if r.state and r.state.kind=='initialized' then return true end \
+             end return false end)()",
+            5,
+        ),
+        "fake never initialized"
+    );
+    // A few more ticks for the push + the server's sink write to land.
+    let sink_probe = sink.clone();
+    pump_async(&mut state, move |_| {
+        std::fs::read_to_string(&sink_probe).is_ok_and(|s| s.contains("probe"))
+    });
+
+    let recorded = std::fs::read_to_string(&sink).unwrap_or_else(|e| {
+        panic!("config sink not written ({e}); the didChangeConfiguration push did not arrive")
+    });
+    assert!(
+        recorded.contains("\"probe\":true"),
+        "the daemon pushed the configured settings after initialized: {recorded}"
+    );
+}
+
+/// PATH-gated provider smoke: drive a real `vscode-json-language-server`
+/// through pmacs's default JSON config, including the post-initialize
+/// `didChangeConfiguration` push, and require a syntax diagnostic for an
+/// invalid document. The reviewed provider is
+/// `@t1ckbase/vscode-langservers-extracted@2.0.2`; CI skips cleanly when
+/// no compatible binary is installed.
+#[test]
+fn m4_real_json_provider_receives_config_and_reports_diagnostics() {
+    use pmacs::editor::EditorState;
+
+    let Ok(command) = which_binary("vscode-json-language-server") else {
+        eprintln!("vscode-json-language-server not on PATH; skipping");
+        return;
+    };
+    let command = command.display().to_string();
+    let dir = tempfile::tempdir().expect("tempdir");
+    let file = std::fs::canonicalize(dir.path())
+        .expect("canonicalize")
+        .join("invalid.json");
+    std::fs::write(&file, b"{\"broken\": }\n").expect("write invalid json");
+    let file_disp = file.display().to_string();
+    let uri = format!("file://{file_disp}");
+
+    let mut state = EditorState::new();
+    state
+        .lua_host
+        .lua()
+        .load(format!(
+            "pmacs.lsp.config.json.command = '{command}'
+             pmacs.buffer.find_or_open('{file_disp}')"
+        ))
+        .exec()
+        .expect("configure real JSON server + open file");
+
+    assert!(
+        pump_lua_flag(
+            &mut state,
+            "(function() for _,r in ipairs(pmacs.lsp.list()) do \
+               if r.state and r.state.kind=='initialized' then return true end \
+             end return false end)()",
+            30,
+        ),
+        "real JSON server never reached initialized"
+    );
+
+    let deadline = Instant::now() + Duration::from_secs(10);
+    let mut got_diagnostic = false;
+    while Instant::now() < deadline {
+        state.tick_processes();
+        state.tick_lsp();
+        state.tick_async();
+        got_diagnostic = state
+            .lua_host
+            .lua()
+            .load(format!("return pmacs.diag.count('{uri}') > 0"))
+            .eval()
+            .unwrap_or(false);
+        if got_diagnostic {
+            break;
+        }
+        std::thread::sleep(Duration::from_millis(10));
+    }
+    assert!(
+        got_diagnostic,
+        "real JSON server produced no diagnostic; config delivery or validation is broken"
+    );
+    assert_no_lsp_crash(&mut state, "real JSON server");
+}
+
+/// PATH-gated provider smoke: drive Red Hat
+/// `yaml-language-server@1.24.0` through pmacs's default YAML config and
+/// require a syntax diagnostic for an invalid document. `SchemaStore` and
+/// the Kubernetes CRD catalog are disabled in this test so the result is
+/// deterministic and does not depend on network access. CI skips cleanly
+/// when no compatible binary is installed.
+#[test]
+fn m4_real_yaml_provider_pulls_config_and_reports_diagnostics() {
+    use pmacs::editor::EditorState;
+
+    let Ok(command) = which_binary("yaml-language-server") else {
+        eprintln!("yaml-language-server not on PATH; skipping");
+        return;
+    };
+    let command = command.display().to_string();
+    let dir = tempfile::tempdir().expect("tempdir");
+    let file = std::fs::canonicalize(dir.path())
+        .expect("canonicalize")
+        .join("invalid.yaml");
+    std::fs::write(&file, b"root:\n  broken: [one,\n").expect("write invalid yaml");
+    let file_disp = file.display().to_string();
+    let uri = format!("file://{file_disp}");
+
+    let mut state = EditorState::new();
+    state
+        .lua_host
+        .lua()
+        .load(format!(
+            "local c = pmacs.lsp.config.yaml
+             c.command = '{command}'
+             c.settings.yaml.schemaStore = {{ enable = false }}
+             c.settings.yaml.kubernetesCRDStore = {{ enable = false }}
+             pmacs.buffer.find_or_open('{file_disp}')"
+        ))
+        .exec()
+        .expect("configure real YAML server + open file");
+
+    assert!(
+        pump_lua_flag(
+            &mut state,
+            "(function() for _,r in ipairs(pmacs.lsp.list()) do \
+               if r.language_id=='yaml' and r.state \
+                  and r.state.kind=='initialized' then return true end \
+             end return false end)()",
+            30,
+        ),
+        "auto-attached real YAML server never reached initialized"
+    );
+
+    let deadline = Instant::now() + Duration::from_secs(10);
+    let mut got_diagnostic = false;
+    while Instant::now() < deadline {
+        state.tick_processes();
+        state.tick_lsp();
+        state.tick_async();
+        got_diagnostic = state
+            .lua_host
+            .lua()
+            .load(format!("return pmacs.diag.count('{uri}') > 0"))
+            .eval()
+            .unwrap_or(false);
+        if got_diagnostic {
+            break;
+        }
+        std::thread::sleep(Duration::from_millis(10));
+    }
+    assert!(
+        got_diagnostic,
+        "real YAML server produced no diagnostic; config pulls or validation are broken"
+    );
+    assert_no_lsp_crash(&mut state, "real YAML server");
+    let still_initialized: bool = state
+        .lua_host
+        .lua()
+        .load(
+            "for _,r in ipairs(pmacs.lsp.list()) do \
+               if r.language_id=='yaml' and r.state \
+                  and r.state.kind=='initialized' then return true end \
+             end return false",
+        )
+        .eval()
+        .expect("inspect YAML server state");
+    assert!(
+        still_initialized,
+        "real YAML server did not remain alive after publishing diagnostics"
+    );
+}
+
 /// Typing-perf: the default bundle coalesces full-document
 /// `didChange` notifications instead of sending one per keystroke
 /// (each send copies the whole buffer several times and writes