From 0fffd690717232a2f6349a4b7cca91df8952f7d4 Mon Sep 17 00:00:00 2001
From: th-kim0823 <th.kim0823@navercorp.com>
Date: Sun, 10 May 2026 00:01:56 +0900
Subject: [PATCH] feat(cli): kebab fetch chunk / doc / span (fb-35)

JSON output is fetch_result.v1; plain output is human-friendly
labeled sections (chunk: before / target / after; doc/span: full
text + stderr truncated hint).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---
 crates/kebab-cli/src/main.rs | 123 +++++++++++++++++++++++++++++++++++
 crates/kebab-cli/src/wire.rs |   6 ++
 2 files changed, 129 insertions(+)

diff --git a/crates/kebab-cli/src/main.rs b/crates/kebab-cli/src/main.rs
index 16857e5..c92ba27 100644
--- a/crates/kebab-cli/src/main.rs
+++ b/crates/kebab-cli/src/main.rs
@@ -86,6 +86,12 @@ enum Cmd {
         what: InspectWhat,
     },
 
+    /// p9-fb-35: verbatim chunk / doc / span fetch.
+    Fetch {
+        #[command(subcommand)]
+        what: FetchWhat,
+    },
+
     /// Lexical / vector / hybrid search over chunks.
     Search {
         query: String,
@@ -261,6 +267,33 @@ enum InspectWhat {
     Chunk { id: String },
 }
 
+#[derive(Subcommand, Debug)]
+enum FetchWhat {
+    /// Fetch a single chunk verbatim, optionally with surrounding context.
+    Chunk {
+        id: String,
+        /// p9-fb-35: include ±N chunks before and after the target.
+        #[arg(long)]
+        context: Option<u32>,
+    },
+    /// Fetch the entire normalized markdown text of a document.
+    Doc {
+        id: String,
+        /// p9-fb-35: chars/4 budget cap.
+        #[arg(long)]
+        max_tokens: Option<usize>,
+    },
+    /// Fetch a 1-based line range of a document. PDF / audio rejected.
+    Span {
+        doc_id: String,
+        line_start: u32,
+        line_end: u32,
+        /// p9-fb-35: chars/4 budget cap.
+        #[arg(long)]
+        max_tokens: Option<usize>,
+    },
+}
+
 #[derive(Subcommand, Debug)]
 enum EvalWhat {
     /// Run the golden suite end-to-end and persist `eval_runs` +
@@ -526,6 +559,49 @@ fn run(cli: &Cli) -> anyhow::Result<()> {
             }
         },
 
+        Cmd::Fetch { what } => {
+            let cfg = kebab_config::Config::load(cli.config.as_deref())?;
+            let (query, opts) = match what {
+                FetchWhat::Chunk { id, context } => (
+                    kebab_core::FetchQuery::Chunk(kebab_core::ChunkId(id.clone())),
+                    kebab_core::FetchOpts {
+                        context: *context,
+                        max_tokens: None,
+                    },
+                ),
+                FetchWhat::Doc { id, max_tokens } => (
+                    kebab_core::FetchQuery::Doc(kebab_core::DocumentId(id.clone())),
+                    kebab_core::FetchOpts {
+                        context: None,
+                        max_tokens: *max_tokens,
+                    },
+                ),
+                FetchWhat::Span {
+                    doc_id,
+                    line_start,
+                    line_end,
+                    max_tokens,
+                } => (
+                    kebab_core::FetchQuery::Span {
+                        doc_id: kebab_core::DocumentId(doc_id.clone()),
+                        line_start: *line_start,
+                        line_end: *line_end,
+                    },
+                    kebab_core::FetchOpts {
+                        context: None,
+                        max_tokens: *max_tokens,
+                    },
+                ),
+            };
+            let result = kebab_app::fetch_with_config(cfg, query, opts)?;
+            if cli.json {
+                println!("{}", serde_json::to_string(&wire::wire_fetch_result(&result))?);
+            } else {
+                render_fetch_plain(&result);
+            }
+            Ok(())
+        }
+
         Cmd::Search {
             query,
             k,
@@ -1112,6 +1188,53 @@ fn confirm_destructive(
     Ok(matches!(s.as_str(), "y" | "yes"))
 }
 
+/// p9-fb-35: human-friendly plain output for `kebab fetch`.
+fn render_fetch_plain(r: &kebab_core::FetchResult) {
+    println!("# {} ({})", r.doc_path.0, format_kind(r.kind));
+    if r.stale {
+        println!("[stale; indexed_at = {}]", r.indexed_at);
+    }
+    match r.kind {
+        kebab_core::FetchKind::Chunk => {
+            if !r.context_before.is_empty() {
+                println!("\n=== before ===");
+                for c in &r.context_before {
+                    let heading = c.heading_path.last().map(|s| s.as_str()).unwrap_or("");
+                    println!("[{} § {}]\n{}\n", c.chunk_id.0, heading, c.text);
+                }
+            }
+            if let Some(c) = &r.chunk {
+                println!("\n=== target ===");
+                let heading = c.heading_path.last().map(|s| s.as_str()).unwrap_or("");
+                println!("[{} § {}]\n{}\n", c.chunk_id.0, heading, c.text);
+            }
+            if !r.context_after.is_empty() {
+                println!("\n=== after ===");
+                for c in &r.context_after {
+                    let heading = c.heading_path.last().map(|s| s.as_str()).unwrap_or("");
+                    println!("[{} § {}]\n{}\n", c.chunk_id.0, heading, c.text);
+                }
+            }
+        }
+        kebab_core::FetchKind::Doc | kebab_core::FetchKind::Span => {
+            if let Some(text) = &r.text {
+                println!("\n{text}");
+            }
+            if r.truncated {
+                eprintln!("[truncated; widen --max-tokens for fuller text]");
+            }
+        }
+    }
+}
+
+fn format_kind(k: kebab_core::FetchKind) -> &'static str {
+    match k {
+        kebab_core::FetchKind::Chunk => "chunk",
+        kebab_core::FetchKind::Doc => "doc",
+        kebab_core::FetchKind::Span => "span",
+    }
+}
+
 #[cfg(test)]
 mod tests {
     //! p9-fb-32: unit tests for `render_ask_plain_citations`. The
diff --git a/crates/kebab-cli/src/wire.rs b/crates/kebab-cli/src/wire.rs
index 649d3f0..178fa22 100644
--- a/crates/kebab-cli/src/wire.rs
+++ b/crates/kebab-cli/src/wire.rs
@@ -189,6 +189,12 @@ pub fn wire_error_v1(e: &kebab_app::ErrorV1) -> Value {
     tag_object(v, "error.v1")
 }
 
+/// p9-fb-35: tag a [`kebab_core::FetchResult`] as `fetch_result.v1`.
+pub fn wire_fetch_result(r: &kebab_core::FetchResult) -> Value {
+    let v = serde_json::to_value(r).expect("FetchResult serializes");
+    tag_object(v, "fetch_result.v1")
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;