feat: add parallel chunk processing for large documents in transformations

CHANGELOG.md

@@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 
 ### Added
+- **Transformations handle documents larger than the model's context window.** The full source is tried first; on a context-length rejection it is split into token-sized sections, processed in parallel and synthesized hierarchically into one output, so small-context models can transform large sources. Sources that fit are processed exactly as before (same 8192 output budget). Context-limit detection is shared with the error classifier, and provider errors on the chunk and synthesis paths are classified like the single-shot path, so a context-length failure is never retried by the worker. The merge step synthesizes rather than concatenates, which suits summaries but can drop items for extraction-style prompts — documented in the transformations guide (#990, #529)
 - **New "Quiet Green" design foundation** — the first of three PRs applying the visual identity co-designed with the community in Discussion #1202. The design token system lands in `globals.css` (core palette, neutral reading surfaces, ink ramp, hairline borders, content-type hues, evidence/citation classes, context-state colors, a squared 4–6px radius scale and a near-flat shadow scale where popovers own the only real shadow); fonts move from Inter to Bricolage Grotesque (display) + Instrument Sans (UI) + Spline Sans Mono (data) via `next/font`; the shadcn primitives are restyled to the foundation's rules (fern green primary actions, red reserved exclusively for destructive/error, clay for warnings, teal as the AI/system voice, underline tabs, quiet neutral badges, teal focus ring); and hard-coded palette colors across 38 components were swept into the semantic tokens, which re-resolve automatically per theme. A dev-only living styleguide at `/dev/design` (404 in production) renders every token and primitive in both themes and serves as the review reference for the follow-up screen-by-screen PRs. Purely visual — no behavior, navigation or i18n changes
 - **Screen-by-screen reskin in the "Quiet Green" language** (the second redesign PR): the app shell gets the recomposed tri-hue pebble wordmark (fern/gold/teal — no red left), a fern spine on the active nav item and destination-hued nav icons; the notebook workspace gets display-type titles, panel headers with identity ticks (sources sage / notes gold / chat teal), one-line source-card metadata with the overflow menu at top-right, and de-washed chat bubbles (the AI speaks in teal accents, never washed backgrounds); the notebooks home separates compact recently-viewed rows from active-notebook cards; the sources table gets the library treatment (content-type pebbles, quiet embedded pills, hover that raises the surface); dialogs and the source viewer are flattened (no card-in-card boxes, uniform breathing room, no ⋮/close collision); and Models/Settings/Podcasts/Transformations/Ask-Search get the badge diet, quiet audio-player containers, mono for data and teal AI accents. Still purely visual — no behavior, columns, navigation or i18n changes
 

docs/3-USER-GUIDE/transformations.md

@@ -164,6 +164,12 @@ Bad: "Summarize this"
 
 Processing runs in background. You can continue working.
 
+### Large Documents
+
+A transformation always tries the whole source in one call first. If the source is larger than the model's context window, Open Notebook splits it into sections that fit, processes the sections in parallel, and then merges the partial results into one output. No configuration is needed, and sources that fit are processed exactly as before.
+
+The merge step is a synthesis: the model combines the partial results, removes redundancy and condenses. That suits summaries, key concepts and takeaways well. For extraction-style transformations where every item matters (lists of names, dates, quotes), the synthesis can drop or compress items. When completeness matters more than length, use a model with a larger context window so the source is processed in a single pass.
+
 ---
 
 ## Transformation Examples