diff --git a/.opencode/plans/archive/1775113983739-sunny-knight.md b/.opencode/plans/archive/1775113983739-sunny-knight.md
new file mode 100644
index 0000000..2ff4b52
--- /dev/null
+++ b/.opencode/plans/archive/1775113983739-sunny-knight.md
@@ -0,0 +1,556 @@
+---
+model: openai/gpt-5.4
+---
+
+# HTMLTextSplitter Implementation Plan
+
+## Overview
+
+Build a new `HTMLTextSplitter` that extends LangChain's `TextSplitter` and splits HTML by traversing the parsed DOM tree instead of slicing raw HTML strings.
+
+This version is intentionally narrow:
+- size metric uses cheerio text extraction only
+- separators are CSS selectors
+- `neverBreakWithin` is respected unless `maxChunkSize` forces a deeper split
+- no `chunkOverlap` support
+- output is text chunks, not reconstructed partial HTML
+
+## Confirmed Decisions
+
+1. Use a traversal-based algorithm, not source offsets.
+2. Only split when needed for size control.
+3. Separator matches are soft structural hints, not unconditional split points.
+4. If a separator subtree is too large, recurse into that subtree.
+5. `neverBreakWithin` wins unless a node exceeds `maxChunkSize`; then recurse as a last resort.
+6. Ignore separator matches inside protected subtrees during normal traversal.
+7. V1 emits text chunks, not valid partial HTML.
+8. Traverse both element nodes and text nodes.
+9. Normalize output after boundary-aware joining so block-ish tags create readable spacing without adding synthetic spaces between inline tags.
+10. When a direct child matches a separator during decomposition, it stays with the following content.
+11. `partIndex` and `totalParts` are tracked per input document.
+12. `chunkOverlap` is not supported.
+13. Scope is the splitter itself, with ingest integration called out as a follow-up.
+
+## Goals
+
+1. Extend `TextSplitter` from `@langchain/textsplitters`.
+2. Accept HTML input and parse with `cheerio`.
+3. Use CSS selectors for `separators` and `neverBreakWithin`.
+4. Use `chunkSize` as a soft target and `maxChunkSize` as a hard limit.
+5. Produce chunks whose content is text derived from the traversed HTML.
+6. Recurse only when needed; avoid unnecessary fragmentation.
+
+## Non-Goals
+
+1. Preserving exact HTML markup in chunk output.
+2. Supporting `chunkOverlap`.
+3. Building a full `setup/ingest.ts` migration in this plan.
+4. Reproducing browser-accurate `innerText` behavior.
+
+## Public Interface
+
+```typescript
+import { type Document } from "@langchain/core/documents";
+import { TextSplitter, type TextSplitterParams } from "@langchain/textsplitters";
+
+export interface HTMLTextSplitterParams extends TextSplitterParams {
+  /**
+   * CSS selectors that act as preferred structural split points.
+   * They are only used when a subtree needs to be broken down.
+   */
+  separators?: string[];
+
+  /**
+   * CSS selectors for nodes that should stay atomic unless maxChunkSize forces recursion.
+   */
+  neverBreakWithin?: string[];
+
+  /**
+   * Absolute hard limit for chunk text length.
+   * Defaults to Infinity if omitted.
+   */
+  maxChunkSize?: number;
+}
+
+export class HTMLTextSplitter extends TextSplitter {
+  constructor(fields?: Partial<HTMLTextSplitterParams>);
+
+  /**
+   * Splits HTML input into normalized text chunks.
+   *
+   * Important: this splitter does not preserve HTML markup in output.
+   * It uses parsed HTML structure for traversal and sizing, but emits text only.
+   */
+  splitText(text: string): Promise<string[]>;
+
+  /**
+   * Splits HTML documents into text-only child documents.
+   *
+   * Important: child document `pageContent` contains normalized text, not HTML.
+   * Parent metadata is preserved and per-document part metadata is added.
+   */
+  splitDocuments(documents: Document[]): Promise<Document[]>;
+}
+```
+
+## Output Semantics
+
+1. `splitText()` accepts HTML and returns `string[]` text chunks.
+2. Each chunk is text content extracted from a DOM subtree or subtree fragment.
+3. `splitDocuments()` preserves parent metadata and adds per-document `partIndex` and `totalParts`.
+4. Final chunk text is normalized after DOM-aware joining; block-ish tag boundaries may add spacing, while inline tag boundaries do not add synthetic spaces.
+
+## Size Semantics
+
+1. `chunkSize` is the target size.
+2. `maxChunkSize` is the hard cap when provided.
+3. The size function is based on the same normalized text content used for output segments.
+4. Segment text is derived from cheerio text extraction, joined with DOM-aware boundaries, then whitespace-normalized before measurement.
+5. No separate text-length implementation should be maintained outside that semantic.
+6. If `maxChunkSize` is omitted, treat it as `Infinity`.
+
+## Core Algorithm
+
+### Mental Model
+
+Treat each DOM node as a unit that can either:
+- fit as-is
+- stay atomic because it is protected and still within `maxChunkSize`
+- be recursively decomposed into children because it is too large
+
+Separators only matter when a node must be broken down. They influence recursion order; they do not force a split on their own.
+
+### Traversal Strategy
+
+1. Parse the HTML with cheerio.
+2. Select a traversal root:
+   - use `body` children if a body exists
+   - otherwise use root children
+3. Walk top-level nodes in document order.
+4. Convert each node into one or more text segments using recursive decomposition.
+5. Merge resulting segments into final chunks while respecting `chunkSize` and `maxChunkSize`.
+
+### Recursive Decomposition Rules
+
+For a node `N`:
+
+1. Compute `nodeText` using the shared `getNodeText()` helper so both element nodes and text nodes follow the same trimming semantics.
+2. If `nodeText` is empty, skip it.
+3. If `nodeText.length <= chunkSize`, emit it as one segment.
+4. If `N` matches `neverBreakWithin` and `nodeText.length <= maxChunkSize`, emit it as one segment.
+5. Otherwise, recurse into children.
+6. If `N` has no element/text children that can further subdivide the content, force-split the node text with `RecursiveCharacterTextSplitter`.
+
+### Separator-Aware Recursion
+
+When recursing into a node with child elements:
+
+1. Partition children into traversal groups.
+2. Prefer group boundaries at direct child elements matching `separators`.
+3. A separator child starts a new group and stays with the following sibling content rather than the preceding content.
+4. If no separator child exists, recurse in plain DOM order.
+5. Ignore separator matches inside any subtree currently treated as protected.
+
+## Internal Types
+
+```typescript
+interface Segment {
+  text: string;
+  isProtected: boolean;
+  sourceKind: "node" | "forced-split";
+}
+```
+
+V1 should keep internal types local to the implementation file unless reuse appears during build.
+
+## Detailed Behavior
+
+### 1. Protected Nodes
+
+If a node matches `neverBreakWithin`, keep it atomic while its text length is `<= maxChunkSize`. Recurse into it only if it exceeds `maxChunkSize`.
+
+If `maxChunkSize` is `Infinity`, protected nodes are never forced open by hard-cap rules.
+
+### 2. Forced Splitting
+
+When recursion reaches a node whose text still exceeds `maxChunkSize`, and there is no useful child structure left, use `RecursiveCharacterTextSplitter` on the extracted text.
+
+Use it with:
+- `chunkSize: this.maxChunkSize`
+- `chunkOverlap: 0`
+
+This is the final fallback that guarantees the hard limit.
+
+If `maxChunkSize` is `Infinity`, this fallback is not used for hard-cap enforcement.
+
+### 3. Merging
+
+After recursion produces a flat list of text segments:
+
+1. Start a new chunk.
+2. Append the next segment if the combined length stays within `chunkSize`.
+3. If appending would exceed `chunkSize`, flush the current chunk and start a new one.
+4. If any individual segment is already larger than `chunkSize` but not larger than `maxChunkSize`, allow that segment to become its own chunk.
+5. Join merged segment text using DOM-aware boundaries and whitespace normalization.
+6. No overlap is applied.
+
+When `maxChunkSize` is `Infinity`, a single segment may grow beyond `chunkSize` if it cannot be decomposed further without violating other rules.
+
+## Pseudocode
+
+```typescript
+async splitText(html: string): Promise<string[]> {
+  const $ = cheerio.load(html);
+  const roots = $("body").length > 0 ? $("body").contents().toArray() : $.root().contents().toArray();
+
+  const segments: Segment[] = [];
+  for (const node of roots) {
+    segments.push(...(await this.collectSegments($, node, false)));
+  }
+
+  return this.mergeSegments(segments);
+}
+
+private async collectSegments(
+  $: cheerio.CheerioAPI,
+  node: cheerio.AnyNode,
+  inProtectedAncestor: boolean,
+): Promise<Segment[]> {
+  const text = this.getNodeText($, node);
+  if (!text) return [];
+
+  const isProtected = !inProtectedAncestor && this.matchesAny($, node, this.neverBreakWithin);
+
+  if (text.length <= this.chunkSize) {
+    return [{ text, isProtected, sourceKind: "node" }];
+  }
+
+  if (isProtected && text.length <= this.maxChunkSize) {
+    return [{ text, isProtected, sourceKind: "node" }];
+  }
+
+  const childNodes = this.getChildNodesForRecursion(node);
+  if (childNodes.length === 0) {
+    return this.forceSplitText(text);
+  }
+
+  const childGroups = this.groupChildrenForDecomposition($, childNodes, isProtected || inProtectedAncestor);
+  const segments: Segment[] = [];
+  for (const group of childGroups) {
+    for (const child of group) {
+      segments.push(...(await this.collectSegments($, child, isProtected || inProtectedAncestor)));
+    }
+  }
+
+  return segments.length > 0 ? segments : this.forceSplitText(text);
+}
+```
+
+## Utils Pseudocode
+
+```typescript
+/**
+ * Returns true when a tag node matches any configured CSS selector.
+ *
+ * Needed so separator and protected-node checks share the same selector logic
+ * and non-tag nodes are ignored safely.
+ */
+private matchesAny(
+  $: cheerio.CheerioAPI,
+  node: cheerio.AnyNode,
+  selectors: string[],
+): boolean {
+  if (node.type !== "tag") {
+    return false;
+  }
+
+  for (const selector of selectors) {
+    if ($(node).is(selector)) {
+      return true;
+    }
+  }
+
+  return false;
+}
+
+/**
+ * Extracts the canonical text value for a node.
+ *
+ * Needed so sizing and emitted output use the same trimmed text semantics for
+ * both element nodes and raw text nodes.
+ */
+private getNodeText($: cheerio.CheerioAPI, node: cheerio.AnyNode): string {
+  if (node.type === "text") {
+    return (node.data ?? "").trim();
+  }
+
+  return $(node).text().trim();
+}
+
+/**
+ * Returns the child nodes that are meaningful recursion units.
+ *
+ * Needed to recurse through DOM structure without carrying empty whitespace-only
+ * text nodes or unsupported node types through the algorithm.
+ */
+private getChildNodesForRecursion(node: cheerio.AnyNode): cheerio.AnyNode[] {
+  if (!("children" in node) || !Array.isArray(node.children)) {
+    return [];
+  }
+
+  return node.children.filter((child) => {
+    if (child.type === "text") {
+      return (child.data ?? "").trim().length > 0;
+    }
+
+    return child.type === "tag";
+  });
+}
+
+/**
+ * Groups child nodes so separator nodes start a new group.
+ *
+ * Needed because separators represent preferred section boundaries. Grouping
+ * makes "separator plus following content" explicit during recursion.
+ */
+private groupChildrenForDecomposition(
+  $: cheerio.CheerioAPI,
+  childNodes: cheerio.AnyNode[],
+  inProtectedTree: boolean,
+): cheerio.AnyNode[][] {
+  if (inProtectedTree || this.separators.length === 0) {
+    return [childNodes];
+  }
+
+  const groups: cheerio.AnyNode[][] = [];
+  let currentGroup: cheerio.AnyNode[] = [];
+
+  const flush = () => {
+    if (currentGroup.length > 0) {
+      groups.push(currentGroup);
+      currentGroup = [];
+    }
+  };
+
+  for (const child of childNodes) {
+    if (this.matchesAny($, child, this.separators)) {
+      flush();
+    }
+
+    currentGroup.push(child);
+  }
+
+  flush();
+  return groups;
+}
+
+/**
+ * Applies the final plain-text fallback when a node cannot be decomposed further.
+ *
+ * Needed to enforce a finite hard cap with `RecursiveCharacterTextSplitter`
+ * once DOM structure is exhausted.
+ */
+private async forceSplitText(text: string): Promise<Segment[]> {
+  if (!Number.isFinite(this.maxChunkSize)) {
+    return [{ text: text.trim(), isProtected: false, sourceKind: "forced-split" }];
+  }
+
+  const fallback = new RecursiveCharacterTextSplitter({
+    chunkSize: this.maxChunkSize,
+    chunkOverlap: 0,
+  });
+
+  const chunks = await fallback.splitText(text);
+  return chunks
+    .map((chunk) => chunk.trim())
+    .filter(Boolean)
+    .map((chunk) => ({
+      text: chunk,
+      isProtected: false,
+      sourceKind: "forced-split" as const,
+    }));
+}
+
+/**
+ * Merges flat segments into final chunks using `chunkSize` as a soft target.
+ *
+ * Needed to keep chunk assembly separate from DOM traversal and to normalize the
+ * final text output by joining segment text with single spaces.
+ */
+private mergeSegments(segments: Segment[]): string[] {
+  const chunks: string[] = [];
+  let currentParts: string[] = [];
+  let currentLength = 0;
+
+  const flush = () => {
+    if (currentParts.length === 0) {
+      return;
+    }
+
+    chunks.push(currentParts.join(" "));
+    currentParts = [];
+    currentLength = 0;
+  };
+
+  for (const segment of segments) {
+    const nextLength = currentLength === 0
+      ? segment.text.length
+      : currentLength + 1 + segment.text.length;
+
+    if (currentParts.length > 0 && nextLength > this.chunkSize) {
+      flush();
+    }
+
+    currentParts.push(segment.text);
+    currentLength = currentLength === 0
+      ? segment.text.length
+      : currentLength + 1 + segment.text.length;
+  }
+
+  flush();
+  return chunks;
+}
+```
+
+## Implementation Plan
+
+### Phase 1: Class Skeleton
+
+1. Create `textsplitters/html_text_splitter.ts`.
+2. Define `HTMLTextSplitterParams`.
+3. Extend `TextSplitter`.
+4. Reject unsupported overlap in the constructor:
+   - if `chunkOverlap !== 0`, throw a clear error
+5. Default `maxChunkSize` to `Infinity` when omitted.
+
+### Phase 2: Tree Traversal Helpers
+
+1. `matchesAny()` for selector matching.
+2. `getNodeText()` using cheerio text extraction and trimming semantics shared with output.
+3. `getChildNodesForRecursion()` to expose both text and element children in DOM order.
+4. `groupChildrenForDecomposition()` to build explicit child groups, with separator nodes grouped with following content.
+
+### Phase 3: Recursive Collection
+
+1. Implement `collectSegments()`.
+2. Preserve document order.
+3. Skip empty/whitespace-only results.
+
+### Phase 4: Final Fallback
+
+1. Implement `forceSplitText()` with `RecursiveCharacterTextSplitter`.
+2. Use `maxChunkSize` as the chunk size when it is finite.
+3. Use `chunkOverlap: 0`.
+4. Trim and drop empty results.
+
+### Phase 5: Merge And Document Support
+
+1. Merge segments into final chunks using `chunkSize` as the soft target.
+2. Implement `splitDocuments()` by mapping each input document through `splitText()`.
+3. Preserve original metadata and add per-document `partIndex` / `totalParts`.
+
+## Edge Cases
+
+### Empty HTML
+
+Return `[]`.
+
+### Plain Text Input
+
+Cheerio will still parse it; return one or more text chunks based on size.
+
+### Deeply Nested Protected Content
+
+Keep it atomic unless it exceeds `maxChunkSize`; then recurse into its children and only force-split as a last resort.
+
+If `maxChunkSize` is `Infinity`, it remains atomic unless some ancestor decomposition requires visiting its children.
+
+### Separator Inside Protected Content
+
+Ignore the separator during normal traversal.
+
+### Large Text Node With No Useful Child Structure
+
+Use text fallback splitting.
+
+### Consecutive Small Nodes
+
+Merge them up to `chunkSize`.
+
+### A Single Segment Between chunkSize And maxChunkSize
+
+Allow it as a standalone chunk.
+
+## Testing Strategy
+
+Use Bun's built-in test runner and add automated tests under `test/textsplitters/`.
+
+### Minimum Verification
+
+1. `bunx tsc --noEmit`
+2. automated splitter tests under `test/textsplitters/`
+3. `bun run setup/ingest.ts` on a small fixture or targeted spec file if practical
+
+### Behavior Cases To Verify
+
+1. Returns one chunk when content is under `chunkSize`.
+2. Ignores HTML tag length when using cheerio text extraction.
+3. Does not split at separators unless size pressure requires it.
+4. Keeps protected nodes intact up to `maxChunkSize`.
+5. Recurses into protected nodes larger than `maxChunkSize`.
+6. Uses fallback splitting for oversized leaf text.
+7. Preserves metadata in `splitDocuments()`.
+8. Throws when `chunkOverlap !== 0`.
+9. Leaves hard-cap fallback disabled when `maxChunkSize` is omitted.
+
+The implementation should also update `package.json` with a real `bun test` command so these tests can run in CI and locally.
+
+### Example Important Cases
+
+```typescript
+// separator is a soft hint, not an unconditional boundary
+const splitter = new HTMLTextSplitter({
+  chunkSize: 100,
+  maxChunkSize: 100,
+  separators: ["h2"],
+});
+
+await splitter.splitText("<div><h2>A</h2><p>short body</p></div>");
+// expected: one chunk because no size pressure exists
+```
+
+```typescript
+// protected node stays atomic until maxChunkSize is exceeded
+const splitter = new HTMLTextSplitter({
+  chunkSize: 20,
+  maxChunkSize: 80,
+  neverBreakWithin: ["pre"],
+});
+
+await splitter.splitText("<pre>...60 chars...</pre>");
+// expected: one chunk
+```
+
+## Repository Integration Notes
+
+The eventual migration in `setup/ingest.ts` should account for these changes:
+
+1. output will already be text chunks, so downstream `cheerio.load(chunk.pageContent).text()` cleanup may become redundant
+2. `keepSeparator` is removed from the new design
+3. `chunkOverlap` must remain `0`
+4. current warnings around chunk sizes should be rechecked after migration
+
+## Success Criteria
+
+1. No raw HTML offset slicing is used anywhere.
+2. The splitter traverses DOM structure recursively.
+3. Separators act as soft decomposition hints only.
+4. Protected nodes remain atomic unless `maxChunkSize` is exceeded.
+5. No output chunk exceeds `maxChunkSize` when a finite hard cap is configured.
+6. No overlap behavior is implemented or implied.
+7. `splitDocuments()` preserves metadata and returns chunked documents.
+8. The implementation can be verified in this repo without assuming a missing test framework.
+
+## Open Questions
+
+No remaining open questions in the current plan.
diff --git a/Readme.md b/Readme.md
index e55aae1..b7b8d39 100644
--- a/Readme.md
+++ b/Readme.md
@@ -12,7 +12,7 @@ This project implements a RAG-based AI chat agent to explore the ECMAScript spec
 
 1. **Install dependencies**:
    ```bash
-   npm install
+   bun install
    ```
 
 2. **Prepare environment**:
@@ -26,13 +26,18 @@ This project implements a RAG-based AI chat agent to explore the ECMAScript spec
 
 4. **Ingest data**:
    ```bash
-   node ingest.mjs
+   bun run ingest
    ```
-   *Note: This will take significant time as it generates local embeddings via Ollama for both the spec and the implementation.*
+    *Note: This will take significant time as it generates local embeddings via Ollama for both the spec and the implementation.*
 
 5. **Build graph**:
    ```bash
-   node build_graph.mjs
+   bun run build
+   ```
+
+6. **Run tests**:
+   ```bash
+   bun test
    ```
 
 ## Usage
@@ -40,7 +45,7 @@ This project implements a RAG-based AI chat agent to explore the ECMAScript spec
 Ask the agent questions about how code relates to the specification:
 
 ```bash
-node agent.mjs "Explain how the 'if' statement works and show its implementation."
+bun run agent "Explain how the 'if' statement works and show its implementation."
 ```
 
 The agent will use tools to search the specification, explore the implementation code, and navigate the relationships between them using the graph.
diff --git a/bun.lock b/bun.lock
index 318a534..02798b8 100644
--- a/bun.lock
+++ b/bun.lock
@@ -19,6 +19,7 @@
       },
       "devDependencies": {
         "@biomejs/biome": "^2.4.9",
+        "bun-types": "^1.3.11",
         "typescript": "^5.5.2",
       },
     },
@@ -70,7 +71,7 @@
 
     "@types/command-line-usage": ["@types/command-line-usage@5.0.4", "", {}, "sha512-BwR5KP3Es/CSht0xqBcUXS3qCAUVXwpRKsV2+arxeb65atasuXG9LykC9Ab10Cw3s2raH92ZqOeILaQbsB2ACg=="],
 
-    "@types/node": ["@types/node@20.19.37", "", { "dependencies": { "undici-types": "~6.21.0" } }, "sha512-8kzdPJ3FsNsVIurqBs7oodNnCEVbni9yUEkaHbgptDACOPW04jimGagZ51E6+lXUwJjgnBw+hyko/lkFWCldqw=="],
+    "@types/node": ["@types/node@24.12.0", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-GYDxsZi3ChgmckRT9HPU0WEhKLP08ev/Yfcq2AstjrDASOYCSXeyjDsHg4v5t4jOj7cyDX3vmprafKlWIG9MXQ=="],
 
     "@types/node-fetch": ["@types/node-fetch@2.6.13", "", { "dependencies": { "@types/node": "*", "form-data": "^4.0.4" } }, "sha512-QGpRVpzSaUs30JBSGPjOg4Uveu384erbHBoT1zeONvyCfwQxIkUshLAOqN/k9EjGviPRmWTTe6aH2qySWKTVSw=="],
 
@@ -106,6 +107,8 @@
 
     "brace-expansion": ["brace-expansion@5.0.5", "", { "dependencies": { "balanced-match": "^4.0.2" } }, "sha512-VZznLgtwhn+Mact9tfiwx64fA9erHH/MCXEUfB/0bX/6Fz6ny5EGTXYltMocqg4xFAQZtnO3DHWWXi8RiuN7cQ=="],
 
+    "bun-types": ["bun-types@1.3.11", "", { "dependencies": { "@types/node": "*" } }, "sha512-1KGPpoxQWl9f6wcZh57LvrPIInQMn2TQ7jsgxqpRzg+l0QPOFvJVH7HmvHo/AiPgwXy+/Thf6Ov3EdVn1vOabg=="],
+
     "call-bind-apply-helpers": ["call-bind-apply-helpers@1.0.2", "", { "dependencies": { "es-errors": "^1.3.0", "function-bind": "^1.1.2" } }, "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ=="],
 
     "camelcase": ["camelcase@6.3.0", "", {}, "sha512-Gmy6FhYlCY7uOElZUSbxo2UCDH8owEk996gkbrpsgGtrJLM3J7jGxl9Ic7Qwwj4ivOE5AWZWRMecDdF7hqGjFA=="],
@@ -316,7 +319,7 @@
 
     "undici": ["undici@7.24.6", "", {}, "sha512-Xi4agocCbRzt0yYMZGMA6ApD7gvtUFaxm4ZmeacWI4cZxaF6C+8I8QfofC20NAePiB/IcvZmzkJ7XPa471AEtA=="],
 
-    "undici-types": ["undici-types@6.21.0", "", {}, "sha512-iwDZqg0QAGrg9Rav5H4n0M64c3mkR59cJ6wQp+7C4nI0gsmExaedaYLNO44eT4AtBBwjbTiGPMlt2Md0T9H9JQ=="],
+    "undici-types": ["undici-types@7.16.0", "", {}, "sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw=="],
 
     "uuid": ["uuid@9.0.1", "", { "bin": { "uuid": "dist/bin/uuid" } }, "sha512-b+1eJOlsR9K8HJpow9Ok3fiWOWSIcIzXodvv0rQjVoOVNpWMpxf1wZNpt4y9h10odCNrqnYp1OBzRktckBe3sA=="],
 
@@ -348,7 +351,7 @@
 
     "@langchain/ollama/uuid": ["uuid@10.0.0", "", { "bin": { "uuid": "dist/bin/uuid" } }, "sha512-8XkAphELsDnEGrDxUOHB3RGvXz6TeuYSGEZBOjtTtPm2lwhGBjLgOzLHB63IUWfBpNucQjND6d3AOudO+H3RWQ=="],
 
-    "@types/node-fetch/@types/node": ["@types/node@24.12.0", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-GYDxsZi3ChgmckRT9HPU0WEhKLP08ev/Yfcq2AstjrDASOYCSXeyjDsHg4v5t4jOj7cyDX3vmprafKlWIG9MXQ=="],
+    "apache-arrow/@types/node": ["@types/node@20.19.37", "", { "dependencies": { "undici-types": "~6.21.0" } }, "sha512-8kzdPJ3FsNsVIurqBs7oodNnCEVbni9yUEkaHbgptDACOPW04jimGagZ51E6+lXUwJjgnBw+hyko/lkFWCldqw=="],
 
     "chalk-template/chalk": ["chalk@4.1.2", "", { "dependencies": { "ansi-styles": "^4.1.0", "supports-color": "^7.1.0" } }, "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA=="],
 
@@ -368,7 +371,7 @@
 
     "table-layout/array-back": ["array-back@6.2.3", "", {}, "sha512-SGDvmg6QTYiTxCBkYVmThcoa67uLl35pyzRHdpCGBOcqFy6BtwnphoFPk7LhJshD+Yk1Kt35WGWeZPTgwR4Fhw=="],
 
-    "@types/node-fetch/@types/node/undici-types": ["undici-types@7.16.0", "", {}, "sha512-Zz+aZWSj8LE6zoxD+xrjh4VfkIG8Ya6LvYkZqtUQGJPZjYl53ypCaUwWqo7eI0x66KBGeRo+mlBEkMSeSZ38Nw=="],
+    "apache-arrow/@types/node/undici-types": ["undici-types@6.21.0", "", {}, "sha512-iwDZqg0QAGrg9Rav5H4n0M64c3mkR59cJ6wQp+7C4nI0gsmExaedaYLNO44eT4AtBBwjbTiGPMlt2Md0T9H9JQ=="],
 
     "chalk-template/chalk/ansi-styles": ["ansi-styles@4.3.0", "", { "dependencies": { "color-convert": "^2.0.1" } }, "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg=="],
 
diff --git a/bunfig.toml b/bunfig.toml
new file mode 100644
index 0000000..d34602b
--- /dev/null
+++ b/bunfig.toml
@@ -0,0 +1,3 @@
+[test]
+# Only run tests in the test/ directory, ignoring engine262/ and other subdirectories
+root = "./test"
diff --git a/package.json b/package.json
index d0984da..0460e32 100644
--- a/package.json
+++ b/package.json
@@ -11,7 +11,7 @@
     "ingest": "bun run setup/ingest.ts",
     "agent": "bun run agent.ts",
     "build": "bun run setup/build_graph.ts",
-    "test": "echo \"Error: no test specified\" && exit 1"
+    "test": "bun test"
   },
   "keywords": [],
   "author": "",
@@ -32,7 +32,8 @@
     "ora": "^9.3.0"
   },
   "devDependencies": {
-    "typescript": "^5.5.2",
-    "@biomejs/biome": "^2.4.9"
+    "@biomejs/biome": "^2.4.9",
+    "bun-types": "^1.3.11",
+    "typescript": "^5.5.2"
   }
 }
diff --git a/test/textsplitters/html_text_splitter.test.ts b/test/textsplitters/html_text_splitter.test.ts
new file mode 100644
index 0000000..1dab8b8
--- /dev/null
+++ b/test/textsplitters/html_text_splitter.test.ts
@@ -0,0 +1,289 @@
+import { describe, expect, test } from "bun:test";
+import { Document } from "@langchain/core/documents";
+import { HTMLTextSplitter } from "../../textsplitters";
+
+describe("HTMLTextSplitter", () => {
+  test("keeps small HTML in a single chunk", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 64,
+      separators: ["h2"],
+    });
+
+    const chunks = await splitter.splitText(
+      "<section><h2>Title</h2><p>Short body text</p></section>",
+    );
+
+    expect(chunks).toEqual(["Title Short body text"]);
+  });
+
+  test("does not add synthetic spaces between inline tags", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 64,
+    });
+
+    const chunks = await splitter.splitText(
+      "<p><span>Hello</span><span>World</span></p>",
+    );
+
+    expect(chunks).toEqual(["HelloWorld"]);
+  });
+
+  test("preserves authored whitespace between inline tags", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 64,
+    });
+
+    const chunks = await splitter.splitText(
+      "<p><span>Hello </span><span>World</span></p>",
+    );
+
+    expect(chunks).toEqual(["Hello World"]);
+  });
+
+  test("adds spacing between adjacent block-ish tags", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 64,
+    });
+
+    const chunks = await splitter.splitText("<div>Hello</div><div>World</div>");
+
+    expect(chunks).toEqual(["Hello World"]);
+  });
+
+  test("normalizes repeated whitespace in emitted text", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 64,
+    });
+
+    const chunks = await splitter.splitText(
+      "<div>  Hello\n\n   World  </div><div>\tAgain</div>",
+    );
+
+    expect(chunks).toEqual(["Hello World Again"]);
+  });
+
+  test("treats separators as soft hints until size pressure exists", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 18,
+      separators: ["h2"],
+    });
+
+    const chunks = await splitter.splitText(
+      [
+        "<section>",
+        "<p>Intro text</p>",
+        "<h2>Section Title</h2>",
+        "<p>Body text</p>",
+        "</section>",
+      ].join(""),
+    );
+
+    expect(chunks).toEqual(["Intro text", "Section Title Body text"]);
+  });
+
+  test("groups consecutive separators into later section boundaries", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 4,
+      separators: ["h2", "h3"],
+    });
+
+    const chunks = await splitter.splitText(
+      "<section><h2>A</h2><h3>B</h3><p>Body</p></section>",
+    );
+
+    expect(chunks).toEqual(["A", "B Body"]);
+  });
+
+  test("keeps protected content intact up to maxChunkSize", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 10,
+      maxChunkSize: 32,
+      neverBreakWithin: ["pre"],
+    });
+
+    const chunks = await splitter.splitText(
+      "<div><pre>12345678901234567890</pre></div>",
+    );
+
+    expect(chunks).toEqual(["12345678901234567890"]);
+  });
+
+  test("recurses into protected nodes once maxChunkSize is exceeded", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 12,
+      maxChunkSize: 18,
+      neverBreakWithin: [".keep"],
+      separators: ["p"],
+    });
+
+    const chunks = await splitter.splitText(
+      [
+        '<div class="keep">',
+        "<p>Alpha beta</p>",
+        "<p>Gamma delta</p>",
+        "</div>",
+      ].join(""),
+    );
+
+    expect(chunks).toEqual(["Alpha beta", "Gamma delta"]);
+  });
+
+  test("ignores separators inside protected subtrees until forced open", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 10,
+      maxChunkSize: 40,
+      neverBreakWithin: [".keep"],
+      separators: ["h2"],
+    });
+
+    const chunks = await splitter.splitText(
+      '<div class="keep"><h2>Title</h2><p>Body text</p></div>',
+    );
+
+    expect(chunks).toEqual(["Title Body text"]);
+  });
+
+  test("force-splits oversized leaf text when maxChunkSize is finite", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 12,
+      maxChunkSize: 15,
+    });
+
+    const chunks = await splitter.splitText(`<pre>${"a".repeat(35)}</pre>`);
+
+    expect(chunks.length).toBeGreaterThan(1);
+    for (const chunk of chunks) {
+      expect(chunk.length).toBeLessThanOrEqual(15);
+    }
+  });
+
+  test("force-splits protected oversized leaf text when maxChunkSize is finite", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 12,
+      maxChunkSize: 15,
+      neverBreakWithin: ["pre"],
+    });
+
+    const chunks = await splitter.splitText(`<pre>${"x".repeat(35)}</pre>`);
+
+    expect(chunks.length).toBeGreaterThan(1);
+    for (const chunk of chunks) {
+      expect(chunk.length).toBeLessThanOrEqual(15);
+    }
+  });
+
+  test("does not enforce a hard cap when maxChunkSize is omitted", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 12,
+      neverBreakWithin: ["pre"],
+    });
+
+    const chunks = await splitter.splitText(`<pre>${"a".repeat(35)}</pre>`);
+
+    expect(chunks).toEqual(["a".repeat(35)]);
+  });
+
+  test("splits plain text input without HTML structure", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 8,
+      maxChunkSize: 8,
+    });
+
+    const chunks = await splitter.splitText("alpha beta gamma");
+
+    expect(chunks).toEqual(["alpha", "beta", "gamma"]);
+  });
+
+  test("preserves metadata and adds per-document part indexes", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 18,
+      separators: ["h2"],
+    });
+
+    const documents = await splitter.splitDocuments([
+      new Document({
+        pageContent:
+          "<section><p>Intro text</p><h2>Section Title</h2><p>Body text</p></section>",
+        metadata: { source: "sample.html" },
+      }),
+    ]);
+
+    expect(documents).toHaveLength(2);
+    expect(documents[0].pageContent).toBe("Intro text");
+    expect(documents[0].metadata).toMatchObject({
+      source: "sample.html",
+      partIndex: 0,
+      totalParts: 2,
+    });
+    expect(documents[1].pageContent).toBe("Section Title Body text");
+    expect(documents[1].metadata).toMatchObject({
+      source: "sample.html",
+      partIndex: 1,
+      totalParts: 2,
+    });
+  });
+
+  test("resets part metadata per input document", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 18,
+      separators: ["h2"],
+    });
+
+    const documents = await splitter.splitDocuments([
+      new Document({
+        pageContent:
+          "<section><p>Intro text</p><h2>Section Title</h2><p>Body text</p></section>",
+        metadata: { source: "first.html" },
+      }),
+      new Document({
+        pageContent:
+          "<section><p>Lead text</p><h2>Second Title</h2><p>More text</p></section>",
+        metadata: { source: "second.html" },
+      }),
+    ]);
+
+    expect(documents).toHaveLength(4);
+    expect(documents[0].metadata).toMatchObject({
+      source: "first.html",
+      partIndex: 0,
+      totalParts: 2,
+    });
+    expect(documents[1].metadata).toMatchObject({
+      source: "first.html",
+      partIndex: 1,
+      totalParts: 2,
+    });
+    expect(documents[2].metadata).toMatchObject({
+      source: "second.html",
+      partIndex: 0,
+      totalParts: 2,
+    });
+    expect(documents[3].metadata).toMatchObject({
+      source: "second.html",
+      partIndex: 1,
+      totalParts: 2,
+    });
+  });
+
+  test("rejects chunkOverlap", () => {
+    expect(
+      () =>
+        new HTMLTextSplitter({
+          chunkSize: 32,
+          chunkOverlap: 4,
+        }),
+    ).toThrow("does not support chunkOverlap");
+  });
+
+  test("keeps adjacent inline text contiguous when no whitespace exists", async () => {
+    const splitter = new HTMLTextSplitter({
+      chunkSize: 100,
+    });
+
+    const chunks = await splitter.splitText(
+      "<span>alpha</span><span>bet</span><span>gamma</span>",
+    );
+
+    expect(chunks).toEqual(["alphabetgamma"]);
+  });
+});
diff --git a/textsplitters/html_text_splitter.ts b/textsplitters/html_text_splitter.ts
new file mode 100644
index 0000000..3a26469
--- /dev/null
+++ b/textsplitters/html_text_splitter.ts
@@ -0,0 +1,523 @@
+import { Document } from "@langchain/core/documents";
+import {
+  RecursiveCharacterTextSplitter,
+  TextSplitter,
+  type TextSplitterChunkHeaderOptions,
+  type TextSplitterParams,
+} from "@langchain/textsplitters";
+import * as cheerio from "cheerio";
+import type { AnyNode } from "domhandler";
+
+export interface HTMLTextSplitterParams extends TextSplitterParams {
+  /**
+   * CSS selectors that act as preferred structural split points.
+   * They are only used when a subtree needs to be broken down.
+   */
+  separators?: string[];
+
+  /**
+   * CSS selectors for nodes that should stay atomic unless maxChunkSize forces recursion.
+   */
+  neverBreakWithin?: string[];
+
+  /**
+   * Absolute hard limit for chunk text length.
+   * Defaults to Infinity if omitted.
+   */
+  maxChunkSize?: number;
+}
+
+interface Segment {
+  text: string;
+  isProtected: boolean;
+  sourceKind: "node" | "forced-split";
+}
+
+const BLOCKISH_TAGS = new Set([
+  "address",
+  "article",
+  "aside",
+  "blockquote",
+  "br",
+  "dd",
+  "div",
+  "dl",
+  "dt",
+  "emu-clause",
+  "emu-example",
+  "emu-grammar",
+  "emu-note",
+  "emu-table",
+  "fieldset",
+  "figcaption",
+  "figure",
+  "footer",
+  "form",
+  "h1",
+  "h2",
+  "h3",
+  "h4",
+  "h5",
+  "h6",
+  "header",
+  "hr",
+  "li",
+  "main",
+  "nav",
+  "ol",
+  "p",
+  "pre",
+  "section",
+  "table",
+  "tbody",
+  "td",
+  "th",
+  "thead",
+  "tr",
+  "ul",
+]);
+
+/**
+ * Splits HTML input into normalized text chunks.
+ *
+ * Important: this splitter does not preserve HTML markup in output.
+ * It uses parsed HTML structure for traversal and sizing, but emits text only.
+ *
+ * @example
+ * ```ts
+ * const splitter = new HTMLTextSplitter({
+ *   chunkSize: 32,
+ *   separators: ["h2"],
+ *   neverBreakWithin: ["pre"],
+ * });
+ *
+ * const chunks = await splitter.splitText(
+ *   "<section><h2>Title</h2><p>Body</p></section>",
+ * );
+ * // => ["Title Body"]
+ * ```
+ */
+export class HTMLTextSplitter extends TextSplitter {
+  separators: string[];
+  neverBreakWithin: string[];
+  maxChunkSize: number;
+
+  constructor(fields?: Partial<HTMLTextSplitterParams>) {
+    if ((fields?.chunkOverlap ?? 0) !== 0) {
+      throw new Error("HTMLTextSplitter does not support chunkOverlap.");
+    }
+
+    super({
+      ...fields,
+      chunkOverlap: 0,
+      keepSeparator: false,
+      lengthFunction: (text: string) => this.normalizeWhitespace(text).length,
+    });
+
+    this.separators = fields?.separators ?? [];
+    this.neverBreakWithin = fields?.neverBreakWithin ?? [];
+    this.maxChunkSize = fields?.maxChunkSize ?? Number.POSITIVE_INFINITY;
+  }
+
+  /**
+   * Splits HTML input into normalized text chunks.
+   *
+   * Important: this method emits text only. HTML markup is used for traversal
+   * and sizing, but is not preserved in returned chunks.
+   */
+  async splitText(text: string): Promise<string[]> {
+    const $ = cheerio.load(text);
+    const rootNodes =
+      $("body").length > 0
+        ? $("body").contents().toArray()
+        : $.root().contents().toArray();
+    const roots = this.getMeaningfulNodes(rootNodes);
+
+    if (roots.length === 0) {
+      return [];
+    }
+
+    const rootGroups = this.groupChildrenForDecomposition($, roots, false);
+    const segments: Segment[] = [];
+
+    for (const group of rootGroups) {
+      segments.push(...(await this.collectSegmentsFromNodes($, group, false)));
+    }
+
+    return this.mergeSegments(segments);
+  }
+
+  /**
+   * Splits HTML documents into text-only child documents.
+   *
+   * Important: child document `pageContent` contains normalized text, not HTML.
+   * Parent metadata is preserved and per-document part metadata is added.
+   */
+  async splitDocuments(
+    documents: Document[],
+    chunkHeaderOptions?: TextSplitterChunkHeaderOptions,
+  ): Promise<Document[]> {
+    const splitDocs: Document[] = [];
+    const chunkHeader = chunkHeaderOptions?.chunkHeader ?? "";
+
+    for (const document of documents) {
+      const chunks = await this.splitText(document.pageContent);
+
+      for (const [index, chunk] of chunks.entries()) {
+        splitDocs.push(
+          new Document({
+            pageContent: `${chunkHeader}${chunk}`,
+            metadata: {
+              ...document.metadata,
+              partIndex: index,
+              totalParts: chunks.length,
+            },
+          }),
+        );
+      }
+    }
+
+    return splitDocs;
+  }
+
+  /**
+   * Returns true when a tag node matches any configured CSS selector.
+   *
+   * Needed so separator and protected-node checks share the same selector logic
+   * and non-tag nodes are ignored safely.
+   */
+  private matchesAny(
+    $: cheerio.CheerioAPI,
+    node: AnyNode,
+    selectors: string[],
+  ): boolean {
+    if (node.type !== "tag") {
+      return false;
+    }
+
+    for (const selector of selectors) {
+      if ($(node).is(selector)) {
+        return true;
+      }
+    }
+
+    return false;
+  }
+
+  /**
+   * Extracts the canonical text value for a node.
+   *
+   * Needed so sizing and emitted output use the same trimmed text semantics for
+   * both element nodes and raw text nodes.
+   */
+  private getNodeText($: cheerio.CheerioAPI, node: AnyNode): string {
+    if (node.type === "text") {
+      return node.data ?? "";
+    }
+
+    return $(node).text();
+  }
+
+  /**
+   * Returns whether a node should introduce a visible boundary when adjacent
+   * text is concatenated.
+   *
+   * Needed so inline elements such as `span` do not get synthetic spaces while
+   * block-ish elements still remain readable in emitted text.
+   */
+  private isBlockishNode(node: AnyNode): boolean {
+    return node.type === "tag" && BLOCKISH_TAGS.has(node.name);
+  }
+
+  /**
+   * Collapses internal whitespace and trims leading/trailing whitespace.
+   *
+   * Needed so text extraction can preserve raw adjacency first and normalize
+   * only once after boundary-aware joining.
+   */
+  private normalizeWhitespace(text: string): string {
+    return text.replace(/\s+/g, " ").trim();
+  }
+
+  /**
+   * Joins multiple nodes into the normalized text the splitter actually emits.
+   *
+   * Needed so grouped nodes are measured and emitted with the same spacing rules
+   * used later during chunk merging.
+   */
+  private getNodesText($: cheerio.CheerioAPI, nodes: AnyNode[]): string {
+    let result = "";
+    let previousNode: AnyNode | null = null;
+
+    for (const node of nodes) {
+      const text = this.getNodeText($, node);
+      if (!text) {
+        continue;
+      }
+
+      if (
+        result.length > 0 &&
+        previousNode &&
+        (this.isBlockishNode(previousNode) || this.isBlockishNode(node))
+      ) {
+        result += " ";
+      }
+
+      result += text;
+      previousNode = node;
+    }
+
+    return this.normalizeWhitespace(result);
+  }
+
+  /**
+   * Filters child nodes down to the recursion units the splitter can handle.
+   *
+   * Needed to recurse through DOM structure without carrying empty whitespace-only
+   * text nodes or unsupported node types through the algorithm.
+   */
+  private getMeaningfulNodes(nodes: AnyNode[]): AnyNode[] {
+    return nodes.filter((node) => {
+      if (node.type === "text") {
+        return (node.data ?? "").trim().length > 0;
+      }
+
+      return node.type === "tag";
+    });
+  }
+
+  /**
+   * Returns the child nodes that are meaningful recursion units.
+   *
+   * Needed to recurse through DOM structure without carrying empty whitespace-only
+   * text nodes or unsupported node types through the algorithm.
+   */
+  private getChildNodesForRecursion(node: AnyNode): AnyNode[] {
+    if (!("children" in node) || !Array.isArray(node.children)) {
+      return [];
+    }
+
+    return this.getMeaningfulNodes(node.children);
+  }
+
+  /**
+   * Groups child nodes so separator nodes start a new group.
+   *
+   * Needed because separators represent preferred section boundaries. Grouping
+   * makes "separator plus following content" explicit during recursion.
+   */
+  private groupChildrenForDecomposition(
+    $: cheerio.CheerioAPI,
+    childNodes: AnyNode[],
+    inProtectedTree: boolean,
+  ): AnyNode[][] {
+    if (childNodes.length === 0) {
+      return [];
+    }
+
+    if (inProtectedTree || this.separators.length === 0) {
+      return [childNodes];
+    }
+
+    const groups: AnyNode[][] = [];
+    let currentGroup: AnyNode[] = [];
+
+    const flush = () => {
+      if (currentGroup.length > 0) {
+        groups.push(currentGroup);
+        currentGroup = [];
+      }
+    };
+
+    for (const child of childNodes) {
+      if (this.matchesAny($, child, this.separators)) {
+        flush();
+      }
+
+      currentGroup.push(child);
+    }
+
+    flush();
+
+    return groups;
+  }
+
+  /**
+   * Collects text segments for a single node or grouped sibling nodes.
+   *
+   * Needed so separator-led groups can be treated as one structural unit before
+   * the splitter decides whether it must recurse deeper.
+   */
+  private async collectSegmentsFromNodes(
+    $: cheerio.CheerioAPI,
+    nodes: AnyNode[],
+    inProtectedAncestor: boolean,
+  ): Promise<Segment[]> {
+    const text = this.getNodesText($, nodes);
+
+    if (!text) {
+      return [];
+    }
+
+    if (nodes.length > 1) {
+      const startsWithSeparator = this.matchesAny($, nodes[0], this.separators);
+
+      if (
+        text.length <= this.chunkSize ||
+        (startsWithSeparator && text.length <= this.maxChunkSize)
+      ) {
+        return [{ text, isProtected: false, sourceKind: "node" }];
+      }
+
+      const segments: Segment[] = [];
+      for (const node of nodes) {
+        segments.push(
+          ...(await this.collectSegmentsFromNodes(
+            $,
+            [node],
+            inProtectedAncestor,
+          )),
+        );
+      }
+
+      return segments.length > 0
+        ? segments
+        : await this.forceSplitText(text, false);
+    }
+
+    const [node] = nodes;
+    const isProtected =
+      !inProtectedAncestor && this.matchesAny($, node, this.neverBreakWithin);
+    const childNodes = this.getChildNodesForRecursion(node);
+
+    if (childNodes.length > 0) {
+      const childGroups = this.groupChildrenForDecomposition(
+        $,
+        childNodes,
+        isProtected || inProtectedAncestor,
+      );
+      const normalizedChildText = this.getNodesText($, childGroups.flat());
+
+      if (normalizedChildText.length <= this.chunkSize) {
+        return [{ text: normalizedChildText, isProtected, sourceKind: "node" }];
+      }
+
+      if (isProtected && normalizedChildText.length <= this.maxChunkSize) {
+        return [{ text: normalizedChildText, isProtected, sourceKind: "node" }];
+      }
+
+      const segments: Segment[] = [];
+      for (const group of childGroups) {
+        segments.push(
+          ...(await this.collectSegmentsFromNodes(
+            $,
+            group,
+            isProtected || inProtectedAncestor,
+          )),
+        );
+      }
+
+      return segments.length > 0
+        ? segments
+        : await this.forceSplitText(normalizedChildText, isProtected);
+    }
+
+    if (text.length <= this.chunkSize) {
+      return [{ text, isProtected, sourceKind: "node" }];
+    }
+
+    if (isProtected && text.length <= this.maxChunkSize) {
+      return [{ text, isProtected, sourceKind: "node" }];
+    }
+
+    return this.forceSplitText(text, isProtected);
+  }
+
+  /**
+   * Applies the final plain-text fallback when a node cannot be decomposed further.
+   *
+   * Needed to enforce a finite hard cap with `RecursiveCharacterTextSplitter`
+   * once DOM structure is exhausted.
+   */
+  private async forceSplitText(
+    text: string,
+    isProtected: boolean,
+  ): Promise<Segment[]> {
+    const normalizedText = text.trim();
+
+    if (!normalizedText) {
+      return [];
+    }
+
+    if (!Number.isFinite(this.maxChunkSize)) {
+      return [
+        {
+          text: normalizedText,
+          isProtected,
+          sourceKind: "forced-split",
+        },
+      ];
+    }
+
+    const fallback = new RecursiveCharacterTextSplitter({
+      chunkSize: this.maxChunkSize,
+      chunkOverlap: 0,
+      keepSeparator: false,
+      lengthFunction: (value: string) => value.trim().length,
+    });
+
+    const chunks = await fallback.splitText(normalizedText);
+
+    return chunks
+      .map((chunk) => chunk.trim())
+      .filter(Boolean)
+      .map((chunk) => ({
+        text: chunk,
+        isProtected,
+        sourceKind: "forced-split" as const,
+      }));
+  }
+
+  /**
+   * Merges flat segments into final chunks using `chunkSize` as a soft target.
+   *
+   * Needed to keep chunk assembly separate from DOM traversal and to normalize the
+   * final text output by joining segment text with single spaces.
+   */
+  private mergeSegments(segments: Segment[]): string[] {
+    const chunks: string[] = [];
+    let currentParts: string[] = [];
+    let currentLength = 0;
+
+    const flush = () => {
+      if (currentParts.length === 0) {
+        return;
+      }
+
+      chunks.push(currentParts.join(" "));
+      currentParts = [];
+      currentLength = 0;
+    };
+
+    for (const segment of segments) {
+      const nextLength =
+        currentLength === 0
+          ? segment.text.length
+          : currentLength + 1 + segment.text.length;
+
+      if (currentParts.length > 0 && nextLength > this.chunkSize) {
+        flush();
+      }
+
+      currentParts.push(segment.text);
+      currentLength =
+        currentLength === 0
+          ? segment.text.length
+          : currentLength + 1 + segment.text.length;
+    }
+
+    flush();
+
+    return chunks;
+  }
+}
diff --git a/textsplitters/index.ts b/textsplitters/index.ts
new file mode 100644
index 0000000..2e941ef
--- /dev/null
+++ b/textsplitters/index.ts
@@ -0,0 +1 @@
+export * from "./html_text_splitter";
diff --git a/tsconfig.json b/tsconfig.json
index dc91905..1b17cd2 100644
--- a/tsconfig.json
+++ b/tsconfig.json
@@ -3,6 +3,7 @@
     "target": "ES2022",
     "module": "esnext",
     "moduleResolution": "node",
+    "types": ["bun-types"],
     "esModuleInterop": true,
     "allowSyntheticDefaultImports": true,
     "strict": true,