Land release blocker fixes and workspace cleanup

crates/ai-formatting/src/llm_client.rs

@@ -225,13 +225,19 @@ mod tests {
         assert_eq!(LlmPromptPreset::parse("EMAIL"), LlmPromptPreset::Email);
         assert_eq!(LlmPromptPreset::parse("notes"), LlmPromptPreset::Notes);
         assert_eq!(LlmPromptPreset::parse("meeting"), LlmPromptPreset::Notes);
-        assert_eq!(LlmPromptPreset::parse("meeting-notes"), LlmPromptPreset::Notes);
+        assert_eq!(
+            LlmPromptPreset::parse("meeting-notes"),
+            LlmPromptPreset::Notes
+        );
         assert_eq!(LlmPromptPreset::parse("code"), LlmPromptPreset::Code);
         assert_eq!(LlmPromptPreset::parse("software"), LlmPromptPreset::Code);
         // Unknown values and explicit default fall back safely.
         assert_eq!(LlmPromptPreset::parse("default"), LlmPromptPreset::Default);
         assert_eq!(LlmPromptPreset::parse(""), LlmPromptPreset::Default);
-        assert_eq!(LlmPromptPreset::parse("random-unknown"), LlmPromptPreset::Default);
+        assert_eq!(
+            LlmPromptPreset::parse("random-unknown"),
+            LlmPromptPreset::Default
+        );
     }
 
     #[test]
@@ -240,7 +246,10 @@ mod tests {
         // be empty so it composes cleanly with dictionary suffix.
         assert!(LlmPromptPreset::Default.suffix().is_empty());
         assert!(LlmPromptPreset::Email.suffix().contains("email"));
-        assert!(LlmPromptPreset::Notes.suffix().to_lowercase().contains("bullet"));
+        assert!(LlmPromptPreset::Notes
+            .suffix()
+            .to_lowercase()
+            .contains("bullet"));
         assert!(LlmPromptPreset::Code.suffix().contains("technical"));
     }
 }

crates/ai-formatting/src/rule_based.rs

@@ -540,8 +540,12 @@ mod tests {
     fn is_hallucination_allows_dialogue_containing_thanks_mid_sentence() {
         // Exact-match on trail phrases means legitimate dialogue that
         // mentions "thanks" or "subscribe" is never dropped.
-        assert!(!is_hallucination("Thanks for the heads up on the migration"));
-        assert!(!is_hallucination("Please subscribe to the RSS feed and tell me when it updates"));
+        assert!(!is_hallucination(
+            "Thanks for the heads up on the migration"
+        ));
+        assert!(!is_hallucination(
+            "Please subscribe to the RSS feed and tell me when it updates"
+        ));
     }
 
     #[test]

crates/ai-formatting/src/to_plain_text.rs

@@ -168,7 +168,10 @@ mod tests {
         ];
         for (input, expected) in cases {
             let out = to_plain_text(&[seg(input)]);
-            assert_eq!(out, expected, "input {input:?} should strip to {expected:?}");
+            assert_eq!(
+                out, expected,
+                "input {input:?} should strip to {expected:?}"
+            );
         }
     }
 

crates/audio/src/wav.rs

@@ -42,9 +42,8 @@ impl WavWriter {
         };
         let file = std::fs::File::create(path).map_err(KonError::Io)?;
         let buffered = BufWriter::new(file);
-        let inner = hound::WavWriter::new(buffered, spec).map_err(|e| {
-            KonError::Io(std::io::Error::other(format!("WAV create failed: {e}")))
-        })?;
+        let inner = hound::WavWriter::new(buffered, spec)
+            .map_err(|e| KonError::Io(std::io::Error::other(format!("WAV create failed: {e}"))))?;
         Ok(Self {
             inner,
             samples_since_flush: 0,
@@ -77,9 +76,9 @@ impl WavWriter {
     /// `Self::DEFAULT_FLUSH_EVERY_SAMPLES` — but may do so at natural
     /// boundaries (end-of-utterance, UI events) for tighter recovery.
     pub fn flush(&mut self) -> Result<()> {
-        self.inner.flush().map_err(|e| {
-            KonError::Io(std::io::Error::other(format!("WAV flush failed: {e}")))
-        })?;
+        self.inner
+            .flush()
+            .map_err(|e| KonError::Io(std::io::Error::other(format!("WAV flush failed: {e}"))))?;
         self.samples_since_flush = 0;
         Ok(())
     }
@@ -244,8 +243,7 @@ mod tests {
         let _ = std::fs::remove_file(&path);
 
         // Write 100 samples (200 bytes at 16-bit).
-        let original =
-            AudioSamples::mono_16khz((0..100).map(|i| (i as f32) / 100.0).collect());
+        let original = AudioSamples::mono_16khz((0..100).map(|i| (i as f32) / 100.0).collect());
         write_wav(&path, &original).unwrap();
 
         // Drop the last 10 bytes — 5 samples' worth. hound's iterator

crates/cloud-providers/src/keystore.rs

@@ -1,29 +1,77 @@
-/// Store an API key in the OS keychain.
+use std::collections::HashMap;
+use std::sync::{Mutex, OnceLock};
+
+/// Store an API key in Kon's process-local keystore.
 ///
-/// Stub implementation using environment variables until the `keyring` crate is
-/// added. Keys are only held in-process and lost on exit.
+/// Keys are held in memory for the lifetime of the process and are lost on
+/// exit. This avoids the undefined behaviour of mutating process environment
+/// variables from arbitrary threads while keeping the public API safe.
 ///
-/// # Safety note
-/// `std::env::set_var` is deprecated in Rust 2024 edition and is **not**
-/// thread-safe — mutating the environment while other threads read it is
-/// undefined behaviour. This is acceptable during single-threaded app init
-/// but must not be called from async/multi-threaded contexts.
+/// `retrieve_api_key` still falls back to `KON_API_KEY_<PROVIDER>` environment
+/// variables so externally injected secrets continue to work.
 ///
 /// TODO: Replace with the `keyring` crate (or platform-native credential
 /// storage) so keys persist across sessions and are accessed safely.
-#[allow(deprecated)] // set_var deprecated in Rust 2024 edition
 pub fn store_api_key(provider: &str, key: &str) {
-    // SAFETY: Only safe when called from a single-threaded context (e.g. app
-    // initialisation). See doc comment above.
-    std::env::set_var(format!("KON_API_KEY_{}", provider.to_uppercase()), key);
+    api_key_store()
+        .lock()
+        .unwrap()
+        .insert(provider_env_key(provider), key.to_string());
 }
 
-/// Retrieve an API key from the OS keychain.
+/// Retrieve an API key from Kon's process-local keystore.
 ///
-/// Stub implementation using environment variables until the `keyring` crate is
-/// added. Returns `None` if no key has been stored this session.
-///
-/// TODO: Replace with the `keyring` crate alongside `store_api_key`.
+/// Returns a previously stored in-memory key when present, otherwise falls
+/// back to the read-only `KON_API_KEY_<PROVIDER>` environment variable so
+/// operator-supplied secrets still work.
 pub fn retrieve_api_key(provider: &str) -> Option<String> {
-    std::env::var(format!("KON_API_KEY_{}", provider.to_uppercase())).ok()
+    let env_key = provider_env_key(provider);
+    api_key_store()
+        .lock()
+        .unwrap()
+        .get(&env_key)
+        .cloned()
+        .or_else(|| std::env::var(env_key).ok())
+}
+
+fn api_key_store() -> &'static Mutex<HashMap<String, String>> {
+    static STORE: OnceLock<Mutex<HashMap<String, String>>> = OnceLock::new();
+    STORE.get_or_init(|| Mutex::new(HashMap::new()))
+}
+
+fn provider_env_key(provider: &str) -> String {
+    format!("KON_API_KEY_{}", provider.to_uppercase())
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::sync::atomic::{AtomicUsize, Ordering};
+
+    fn unique_provider(prefix: &str) -> String {
+        static NEXT_ID: AtomicUsize = AtomicUsize::new(1);
+        format!("{prefix}_{}", NEXT_ID.fetch_add(1, Ordering::Relaxed))
+    }
+
+    #[test]
+    fn stored_key_is_retrievable_without_env_mutation() {
+        let provider = unique_provider("provider");
+        store_api_key(&provider, "secret-token");
+        assert_eq!(
+            retrieve_api_key(&provider),
+            Some("secret-token".to_string())
+        );
+    }
+
+    #[test]
+    fn providers_do_not_overlap() {
+        let first = unique_provider("first");
+        let second = unique_provider("second");
+
+        store_api_key(&first, "alpha");
+        store_api_key(&second, "beta");
+
+        assert_eq!(retrieve_api_key(&first), Some("alpha".to_string()));
+        assert_eq!(retrieve_api_key(&second), Some("beta".to_string()));
+    }
 }

crates/hotkey/src/linux.rs

@@ -349,10 +349,7 @@ fn is_event_device(path: &Path) -> bool {
 /// Return true when the device's reported key set includes the combo's
 /// configured trigger key. A device that reports no keys at all (for
 /// example a mouse whose `EV_KEY` capability is buttons only) is rejected.
-fn device_supports_combo(
-    supported: Option<&AttributeSetRef<Key>>,
-    combo: &HotkeyCombo,
-) -> bool {
+fn device_supports_combo(supported: Option<&AttributeSetRef<Key>>, combo: &HotkeyCombo) -> bool {
     supported.map_or(false, |keys| keys.contains(Key::new(combo.key_code)))
 }
 

crates/llm/src/lib.rs

@@ -18,6 +18,8 @@ pub mod prompts;
 pub use model_manager::{recommend_tier, LlmModelId, LlmModelInfo};
 
 const DEFAULT_CONTEXT_TOKENS: u32 = 4096;
+const MAX_CONTEXT_TOKENS: u32 = 8192;
+const CONTEXT_RESERVE_TOKENS: u32 = 64;
 const GENERATION_SEED: u32 = 0;
 
 #[derive(Debug, thiserror::Error)]
@@ -26,6 +28,15 @@ pub enum EngineError {
     NotLoaded,
     #[error("LLM load failed: {0}")]
     LoadFailed(String),
+    #[error(
+        "prompt too long: {prompt_tokens} prompt tokens exceed the {available_prompt_tokens}-token prompt budget for an {context_window}-token context with {max_tokens} reserved response tokens"
+    )]
+    PromptTooLong {
+        prompt_tokens: usize,
+        max_tokens: u32,
+        available_prompt_tokens: u32,
+        context_window: u32,
+    },
     #[error("inference failed: {0}")]
     Inference(String),
     #[error("model output not valid JSON: {0}")]
@@ -149,7 +160,7 @@ impl LlmEngine {
             return Ok(String::new());
         }
 
-        let n_ctx = context_window_size(prompt_tokens.len(), config.max_tokens);
+        let n_ctx = preflight_context_window(prompt_tokens.len(), config.max_tokens)?;
         let thread_count = i32::try_from(num_cpus::get().max(1)).unwrap_or(4);
         let ctx_params = LlamaContextParams::default()
             .with_n_ctx(Some(
@@ -317,8 +328,26 @@ impl LlmEngine {
 fn context_window_size(prompt_tokens: usize, max_tokens: u32) -> u32 {
     let required = prompt_tokens
         .saturating_add(max_tokens as usize)
-        .saturating_add(64);
-    DEFAULT_CONTEXT_TOKENS.max(required.min(8192) as u32)
+        .saturating_add(CONTEXT_RESERVE_TOKENS as usize);
+    DEFAULT_CONTEXT_TOKENS.max(required.min(MAX_CONTEXT_TOKENS as usize) as u32)
+}
+
+fn preflight_context_window(prompt_tokens: usize, max_tokens: u32) -> Result<u32, EngineError> {
+    let required = prompt_tokens
+        .saturating_add(max_tokens as usize)
+        .saturating_add(CONTEXT_RESERVE_TOKENS as usize);
+    if required > MAX_CONTEXT_TOKENS as usize {
+        let available_prompt_tokens =
+            MAX_CONTEXT_TOKENS.saturating_sub(max_tokens.saturating_add(CONTEXT_RESERVE_TOKENS));
+        return Err(EngineError::PromptTooLong {
+            prompt_tokens,
+            max_tokens,
+            available_prompt_tokens,
+            context_window: MAX_CONTEXT_TOKENS,
+        });
+    }
+
+    Ok(context_window_size(prompt_tokens, max_tokens))
 }
 
 fn first_stop_index(text: &str, stop_sequences: &[String]) -> Option<usize> {
@@ -417,4 +446,24 @@ mod tests {
         let index = first_stop_index(text, &["<|im_end|>".into(), "zzz".into()]);
         assert_eq!(index, Some(5));
     }
+
+    #[test]
+    fn prompt_preflight_rejects_oversized_prompt_tokens() {
+        let err = preflight_context_window(7_105, 1_024).unwrap_err();
+        assert!(matches!(
+            err,
+            EngineError::PromptTooLong {
+                prompt_tokens: 7_105,
+                max_tokens: 1_024,
+                available_prompt_tokens: 7_104,
+                context_window: MAX_CONTEXT_TOKENS,
+            }
+        ));
+    }
+
+    #[test]
+    fn prompt_preflight_keeps_prompts_within_budget() {
+        let n_ctx = preflight_context_window(7_104, 1_024).unwrap();
+        assert_eq!(n_ctx, MAX_CONTEXT_TOKENS);
+    }
 }

crates/mcp/src/lib.rs

@@ -226,7 +226,9 @@ async fn list_transcripts_tool(pool: &SqlitePool, args: Value) -> Result<Value,
         })
         .collect();
 
-    Ok(text_content(serde_json::to_string_pretty(&summaries).unwrap()))
+    Ok(text_content(
+        serde_json::to_string_pretty(&summaries).unwrap(),
+    ))
 }
 
 async fn get_transcript_tool(pool: &SqlitePool, args: Value) -> Result<Value, JsonRpcError> {
@@ -288,7 +290,9 @@ async fn search_transcripts_tool(pool: &SqlitePool, args: Value) -> Result<Value
         })
         .collect();
 
-    Ok(text_content(serde_json::to_string_pretty(&summaries).unwrap()))
+    Ok(text_content(
+        serde_json::to_string_pretty(&summaries).unwrap(),
+    ))
 }
 
 async fn list_tasks_tool(pool: &SqlitePool) -> Result<Value, JsonRpcError> {
@@ -311,7 +315,9 @@ async fn list_tasks_tool(pool: &SqlitePool) -> Result<Value, JsonRpcError> {
         })
         .collect();
 
-    Ok(text_content(serde_json::to_string_pretty(&summaries).unwrap()))
+    Ok(text_content(
+        serde_json::to_string_pretty(&summaries).unwrap(),
+    ))
 }
 
 fn text_content(text: String) -> Value {
@@ -404,7 +410,10 @@ mod tests {
         let pool = sqlx::SqlitePool::connect("sqlite::memory:").await.unwrap();
         let response = handle_message(&pool, request).await.expect("has response");
 
-        let tools = response.result.expect("ok")["tools"].as_array().unwrap().clone();
+        let tools = response.result.expect("ok")["tools"]
+            .as_array()
+            .unwrap()
+            .clone();
         let names: Vec<String> = tools
             .iter()
             .map(|tool| tool["name"].as_str().unwrap().to_string())
@@ -426,7 +435,9 @@ mod tests {
         assert_eq!(resp.jsonrpc, "2.0");
         assert_eq!(resp.id, Value::Null);
         assert!(resp.result.is_none());
-        let err = resp.error.expect("parse_error_response must carry an error");
+        let err = resp
+            .error
+            .expect("parse_error_response must carry an error");
         assert_eq!(err.code, -32700);
         assert!(err.message.contains("Parse error"));
         assert!(err.message.contains("expected value"));
@@ -449,7 +460,9 @@ mod tests {
         });
 
         let pool = sqlx::SqlitePool::connect("sqlite::memory:").await.unwrap();
-        kon_storage::migrations::run_migrations(&pool).await.unwrap();
+        kon_storage::migrations::run_migrations(&pool)
+            .await
+            .unwrap();
         let response = handle_message(&pool, request).await.expect("has response");
 
         assert!(

crates/mcp/src/main.rs

@@ -7,10 +7,7 @@ use tokio::io::{AsyncBufReadExt, AsyncWriteExt, BufReader};
 #[tokio::main(flavor = "current_thread")]
 async fn main() -> anyhow::Result<()> {
     let db_path = kon_storage::database_path();
-    eprintln!(
-        "[kon-mcp] opening Kon database at {}",
-        db_path.display()
-    );
+    eprintln!("[kon-mcp] opening Kon database at {}", db_path.display());
     let pool = kon_storage::init(&db_path).await?;
     eprintln!("[kon-mcp] ready, waiting for JSON-RPC on stdin");
 

crates/storage/src/database.rs

@@ -62,6 +62,13 @@ pub async fn insert_transcript(
     pool: &SqlitePool,
     params: &InsertTranscriptParams<'_>,
 ) -> Result<()> {
+    if !profile_exists(pool, params.profile_id).await? {
+        return Err(KonError::StorageError(format!(
+            "Insert transcript failed: unknown profile id '{}'",
+            params.profile_id
+        )));
+    }
+
     sqlx::query(
         "INSERT INTO transcripts (id, text, source, profile_id, title, audio_path, duration, engine, model_id, inference_ms, sample_rate, audio_channels, format_mode, remove_fillers, british_english, anti_hallucination)
          VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
@@ -731,6 +738,12 @@ pub async fn delete_profile(pool: &SqlitePool, id: &str) -> Result<()> {
             "Default profile cannot be deleted".into(),
         ));
     }
+    let transcript_count = transcript_count_for_profile(pool, id).await?;
+    if transcript_count > 0 {
+        return Err(KonError::StorageError(format!(
+            "Cannot delete profile while {transcript_count} transcript(s) still reference it; reassign transcripts first"
+        )));
+    }
     sqlx::query("DELETE FROM profiles WHERE id = ?")
         .bind(id)
         .execute(pool)
@@ -789,6 +802,23 @@ pub async fn delete_profile_term(pool: &SqlitePool, id: &str) -> Result<()> {
     Ok(())
 }
 
+async fn profile_exists(pool: &SqlitePool, id: &str) -> Result<bool> {
+    let exists: Option<i64> = sqlx::query_scalar("SELECT 1 FROM profiles WHERE id = ? LIMIT 1")
+        .bind(id)
+        .fetch_optional(pool)
+        .await
+        .map_err(|e| KonError::StorageError(format!("Profile existence check failed: {e}")))?;
+    Ok(exists.is_some())
+}
+
+async fn transcript_count_for_profile(pool: &SqlitePool, id: &str) -> Result<i64> {
+    sqlx::query_scalar("SELECT COUNT(*) FROM transcripts WHERE profile_id = ?")
+        .bind(id)
+        .fetch_one(pool)
+        .await
+        .map_err(|e| KonError::StorageError(format!("Profile transcript count failed: {e}")))
+}
+
 // --- Error Logging ---
 
 /// Log a structured error to the `error_log` table.
@@ -865,9 +895,14 @@ mod tests {
 
     async fn test_pool() -> SqlitePool {
         let pool = SqlitePoolOptions::new()
+            .max_connections(1)
             .connect("sqlite::memory:")
             .await
             .unwrap();
+        sqlx::query("PRAGMA foreign_keys = ON")
+            .execute(&pool)
+            .await
+            .unwrap();
         run_migrations(&pool).await.unwrap();
         pool
     }
@@ -1047,11 +1082,19 @@ mod tests {
         insert_task(&pool, "p1", "Ship release", "inbox", None, None, None)
             .await
             .unwrap();
-        insert_subtask(&pool, "s1", "Final test", "p1").await.unwrap();
-        insert_subtask(&pool, "s2", "Tag release", "p1").await.unwrap();
+        insert_subtask(&pool, "s1", "Final test", "p1")
+            .await
+            .unwrap();
+        insert_subtask(&pool, "s2", "Tag release", "p1")
+            .await
+            .unwrap();
 
-        complete_subtask_and_check_parent(&pool, "s1").await.unwrap();
-        complete_subtask_and_check_parent(&pool, "s2").await.unwrap();
+        complete_subtask_and_check_parent(&pool, "s1")
+            .await
+            .unwrap();
+        complete_subtask_and_check_parent(&pool, "s2")
+            .await
+            .unwrap();
         let parent = get_task_by_id(&pool, "p1").await.unwrap().unwrap();
         assert!(parent.done);
 
@@ -1353,6 +1396,72 @@ mod tests {
         assert_eq!(profiles.len(), 1);
     }
 
+    #[tokio::test]
+    async fn insert_transcript_rejects_unknown_profile_id() {
+        let pool = test_pool().await;
+        let err = insert_transcript(
+            &pool,
+            &InsertTranscriptParams {
+                id: "bad-profile",
+                text: "Hello",
+                source: "microphone",
+                profile_id: "profile-missing",
+                title: None,
+                audio_path: None,
+                duration: 0.0,
+                engine: None,
+                model_id: None,
+                inference_ms: None,
+                sample_rate: None,
+                audio_channels: None,
+                format_mode: None,
+                remove_fillers: false,
+                british_english: false,
+                anti_hallucination: false,
+            },
+        )
+        .await
+        .expect_err("unknown profile id must be rejected");
+
+        let msg = err.to_string();
+        assert!(msg.contains("unknown profile id"), "got: {msg}");
+    }
+
+    #[tokio::test]
+    async fn delete_profile_rejects_when_transcripts_reference_it() {
+        let pool = test_pool().await;
+        let profile = create_profile(&pool, "Referenced", "").await.unwrap();
+        insert_transcript(
+            &pool,
+            &InsertTranscriptParams {
+                id: "referenced-transcript",
+                text: "Hello",
+                source: "microphone",
+                profile_id: &profile.id,
+                title: None,
+                audio_path: None,
+                duration: 0.0,
+                engine: None,
+                model_id: None,
+                inference_ms: None,
+                sample_rate: None,
+                audio_channels: None,
+                format_mode: None,
+                remove_fillers: false,
+                british_english: false,
+                anti_hallucination: false,
+            },
+        )
+        .await
+        .unwrap();
+
+        let err = delete_profile(&pool, &profile.id)
+            .await
+            .expect_err("profile with transcript references must not delete");
+        let msg = err.to_string();
+        assert!(msg.contains("reassign transcripts first"), "got: {msg}");
+    }
+
     #[tokio::test]
     async fn list_profile_terms_happy_path() {
         let pool = test_pool().await;

crates/storage/src/migrations.rs

@@ -215,6 +215,125 @@ const MIGRATIONS: &[(i64, &str, &str)] = &[
             ON transcripts(profile_id);
         "#,
     ),
+    (
+        9,
+        "transcript_profile_fk",
+        r#"
+        INSERT OR IGNORE INTO profiles (id, name, initial_prompt, created_at)
+        VALUES ('00000000-0000-0000-0000-000000000001', 'Default', '', datetime('now'));
+
+        DROP TRIGGER IF EXISTS transcripts_ai;
+        DROP TRIGGER IF EXISTS transcripts_ad;
+        DROP TRIGGER IF EXISTS transcripts_au;
+        DROP TABLE IF EXISTS transcripts_fts;
+        DROP INDEX IF EXISTS idx_segments_transcript;
+        DROP INDEX IF EXISTS idx_transcripts_created;
+        DROP INDEX IF EXISTS idx_transcripts_profile_id;
+
+        ALTER TABLE segments RENAME TO segments_old;
+        ALTER TABLE transcripts RENAME TO transcripts_old;
+
+        CREATE TABLE transcripts (
+            id TEXT PRIMARY KEY,
+            text TEXT NOT NULL DEFAULT '',
+            source TEXT NOT NULL DEFAULT 'microphone',
+            title TEXT,
+            audio_path TEXT,
+            duration REAL NOT NULL DEFAULT 0.0,
+            engine TEXT,
+            model_id TEXT,
+            inference_ms INTEGER,
+            sample_rate INTEGER,
+            audio_channels INTEGER,
+            format_mode TEXT,
+            remove_fillers INTEGER NOT NULL DEFAULT 0,
+            british_english INTEGER NOT NULL DEFAULT 0,
+            anti_hallucination INTEGER NOT NULL DEFAULT 0,
+            created_at TEXT NOT NULL DEFAULT (datetime('now')),
+            starred INTEGER NOT NULL DEFAULT 0,
+            manual_tags TEXT NOT NULL DEFAULT '',
+            template TEXT NOT NULL DEFAULT '',
+            language TEXT NOT NULL DEFAULT '',
+            segments_json TEXT NOT NULL DEFAULT '',
+            profile_id TEXT NOT NULL DEFAULT '00000000-0000-0000-0000-000000000001'
+                REFERENCES profiles(id) ON DELETE RESTRICT
+        );
+
+        CREATE INDEX idx_transcripts_created
+            ON transcripts(created_at);
+        CREATE INDEX idx_transcripts_profile_id
+            ON transcripts(profile_id);
+
+        INSERT INTO transcripts (
+            id, text, source, title, audio_path, duration, engine, model_id,
+            inference_ms, sample_rate, audio_channels, format_mode,
+            remove_fillers, british_english, anti_hallucination, created_at,
+            starred, manual_tags, template, language, segments_json, profile_id
+        )
+        SELECT
+            id, text, source, title, audio_path, duration, engine, model_id,
+            inference_ms, sample_rate, audio_channels, format_mode,
+            remove_fillers, british_english, anti_hallucination, created_at,
+            starred, manual_tags, template, language, segments_json,
+            CASE
+                WHEN profile_id IS NOT NULL
+                 AND EXISTS (
+                    SELECT 1 FROM profiles
+                    WHERE id = transcripts_old.profile_id
+                 )
+                    THEN profile_id
+                ELSE '00000000-0000-0000-0000-000000000001'
+            END
+        FROM transcripts_old;
+
+        CREATE TABLE segments (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            transcript_id TEXT NOT NULL REFERENCES transcripts(id) ON DELETE CASCADE,
+            start_time REAL NOT NULL,
+            end_time REAL NOT NULL,
+            text TEXT NOT NULL DEFAULT ''
+        );
+
+        CREATE INDEX idx_segments_transcript
+            ON segments(transcript_id);
+
+        INSERT INTO segments (id, transcript_id, start_time, end_time, text)
+        SELECT id, transcript_id, start_time, end_time, text
+        FROM segments_old;
+
+        DROP TABLE segments_old;
+        DROP TABLE transcripts_old;
+
+        CREATE VIRTUAL TABLE transcripts_fts USING fts5(
+            text,
+            title,
+            content='transcripts',
+            content_rowid='rowid',
+            tokenize='porter unicode61 remove_diacritics 2'
+        );
+
+        CREATE TRIGGER transcripts_ai AFTER INSERT ON transcripts BEGIN
+            INSERT INTO transcripts_fts(rowid, text, title)
+            VALUES (new.rowid, new.text, COALESCE(new.title, ''));
+        END;
+
+        CREATE TRIGGER transcripts_ad AFTER DELETE ON transcripts BEGIN
+            INSERT INTO transcripts_fts(transcripts_fts, rowid, text, title)
+            VALUES ('delete', old.rowid, old.text, COALESCE(old.title, ''));
+        END;
+
+        CREATE TRIGGER transcripts_au AFTER UPDATE ON transcripts BEGIN
+            INSERT INTO transcripts_fts(transcripts_fts, rowid, text, title)
+            VALUES ('delete', old.rowid, old.text, COALESCE(old.title, ''));
+            INSERT INTO transcripts_fts(rowid, text, title)
+            VALUES (new.rowid, new.text, COALESCE(new.title, ''));
+        END;
+
+        INSERT INTO transcripts_fts(rowid, text, title)
+        SELECT rowid, text, COALESCE(title, '')
+        FROM transcripts;
+        "#,
+    ),
 ];
 
 /// Split SQL into individual statements, respecting BEGIN...END trigger blocks.
@@ -281,10 +400,7 @@ pub async fn run_migrations(pool: &SqlitePool) -> Result<()> {
 /// implicitly commits (`VACUUM`, `REINDEX`, `ATTACH`), it must be split
 /// out into its own non-transactional migration — reviewer's job to
 /// flag.
-async fn run_migrations_slice(
-    pool: &SqlitePool,
-    migrations: &[(i64, &str, &str)],
-) -> Result<()> {
+async fn run_migrations_slice(pool: &SqlitePool, migrations: &[(i64, &str, &str)]) -> Result<()> {
     sqlx::query(
         "CREATE TABLE IF NOT EXISTS schema_version (
             version INTEGER PRIMARY KEY,
@@ -344,12 +460,22 @@ mod tests {
     use sqlx::sqlite::SqlitePoolOptions;
     use sqlx::Row;
 
-    #[tokio::test]
-    async fn test_migrations_run_on_empty_db() {
+    async fn fk_test_pool() -> SqlitePool {
         let pool = SqlitePoolOptions::new()
+            .max_connections(1)
             .connect("sqlite::memory:")
             .await
-            .unwrap();
+            .expect("pool");
+        sqlx::query("PRAGMA foreign_keys = ON")
+            .execute(&pool)
+            .await
+            .expect("enable foreign keys");
+        pool
+    }
+
+    #[tokio::test]
+    async fn test_migrations_run_on_empty_db() {
+        let pool = fk_test_pool().await;
 
         run_migrations(&pool).await.unwrap();
 
@@ -357,7 +483,7 @@ mod tests {
             .fetch_one(&pool)
             .await
             .unwrap();
-        assert_eq!(count, 8);
+        assert_eq!(count, 9);
 
         sqlx::query("INSERT INTO settings (key, value) VALUES ('test', 'value')")
             .execute(&pool)
@@ -367,10 +493,7 @@ mod tests {
 
     #[tokio::test]
     async fn test_migrations_idempotent() {
-        let pool = SqlitePoolOptions::new()
-            .connect("sqlite::memory:")
-            .await
-            .unwrap();
+        let pool = fk_test_pool().await;
 
         run_migrations(&pool).await.unwrap();
         run_migrations(&pool).await.unwrap();
@@ -379,7 +502,7 @@ mod tests {
             .fetch_one(&pool)
             .await
             .unwrap();
-        assert_eq!(count, 8);
+        assert_eq!(count, 9);
     }
 
     #[tokio::test]
@@ -440,11 +563,7 @@ mod tests {
 
     #[tokio::test]
     async fn migration_transcript_profile_provenance_adds_profile_id() {
-        let pool = SqlitePoolOptions::new()
-            .max_connections(1)
-            .connect("sqlite::memory:")
-            .await
-            .expect("pool");
+        let pool = fk_test_pool().await;
         run_migrations(&pool).await.expect("migrate");
 
         let info = sqlx::query("PRAGMA table_info(transcripts)")
@@ -459,11 +578,108 @@ mod tests {
     }
 
     #[tokio::test]
-    async fn test_parent_task_id_cascade_delete() {
-        let pool = SqlitePoolOptions::new()
-            .connect("sqlite::memory:")
+    async fn migration_v9_reconciles_orphaned_transcript_profiles_and_adds_fk() {
+        let pool = fk_test_pool().await;
+        run_migrations_up_to(&pool, 8).await.expect("migrate to v8");
+
+        sqlx::query(
+            "INSERT INTO profiles (id, name, initial_prompt, created_at)
+             VALUES ('profile-valid', 'Valid', '', datetime('now'))",
+        )
+        .execute(&pool)
+        .await
+        .expect("seed valid profile");
+
+        sqlx::query(
+            "INSERT INTO transcripts (
+                id, text, source, title, audio_path, duration, engine, model_id,
+                inference_ms, sample_rate, audio_channels, format_mode,
+                remove_fillers, british_english, anti_hallucination, created_at,
+                starred, manual_tags, template, language, segments_json, profile_id
+            ) VALUES (
+                't-orphan', 'orphan body', 'microphone', 'Orphan', NULL, 0.0, NULL, NULL,
+                NULL, NULL, NULL, NULL, 0, 0, 0, datetime('now'),
+                0, '', '', '', '', 'profile-missing'
+            )",
+        )
+        .execute(&pool)
+        .await
+        .expect("seed orphan transcript");
+        sqlx::query(
+            "INSERT INTO transcripts (
+                id, text, source, title, audio_path, duration, engine, model_id,
+                inference_ms, sample_rate, audio_channels, format_mode,
+                remove_fillers, british_english, anti_hallucination, created_at,
+                starred, manual_tags, template, language, segments_json, profile_id
+            ) VALUES (
+                't-valid', 'valid body', 'microphone', 'Valid', NULL, 0.0, NULL, NULL,
+                NULL, NULL, NULL, NULL, 0, 0, 0, datetime('now'),
+                0, '', '', '', '', 'profile-valid'
+            )",
+        )
+        .execute(&pool)
+        .await
+        .expect("seed valid transcript");
+        sqlx::query(
+            "INSERT INTO segments (transcript_id, start_time, end_time, text)
+             VALUES ('t-orphan', 0.0, 1.0, 'segment')",
+        )
+        .execute(&pool)
+        .await
+        .expect("seed segment");
+
+        run_migrations(&pool).await.expect("migrate to v9");
+
+        let orphan_profile: String =
+            sqlx::query_scalar("SELECT profile_id FROM transcripts WHERE id = 't-orphan'")
+                .fetch_one(&pool)
+                .await
+                .expect("read healed orphan");
+        assert_eq!(orphan_profile, crate::DEFAULT_PROFILE_ID);
+
+        let valid_profile: String =
+            sqlx::query_scalar("SELECT profile_id FROM transcripts WHERE id = 't-valid'")
+                .fetch_one(&pool)
+                .await
+                .expect("read preserved profile");
+        assert_eq!(valid_profile, "profile-valid");
+
+        let segment_count: i64 =
+            sqlx::query_scalar("SELECT COUNT(*) FROM segments WHERE transcript_id = 't-orphan'")
+                .fetch_one(&pool)
+                .await
+                .expect("read migrated segments");
+        assert_eq!(segment_count, 1, "segments must survive transcript rebuild");
+
+        let fk_rows = sqlx::query("PRAGMA foreign_key_list(transcripts)")
+            .fetch_all(&pool)
             .await
-            .unwrap();
+            .expect("read transcript foreign keys");
+        assert!(
+            fk_rows.iter().any(|row| {
+                row.get::<String, _>("table") == "profiles"
+                    && row.get::<String, _>("from") == "profile_id"
+                    && row.get::<String, _>("to") == "id"
+                    && row.get::<String, _>("on_delete") == "RESTRICT"
+            }),
+            "transcripts.profile_id must reference profiles(id) with ON DELETE RESTRICT"
+        );
+
+        let fts_hits: i64 = sqlx::query_scalar(
+            "SELECT COUNT(*) FROM transcripts_fts WHERE transcripts_fts MATCH 'orphan'",
+        )
+        .fetch_one(&pool)
+        .await
+        .expect("query rebuilt fts");
+        assert_eq!(
+            fts_hits, 1,
+            "fts index must be rebuilt for existing transcripts"
+        );
+    }
+
+    #[tokio::test]
+    async fn test_parent_task_id_cascade_delete() {
+        let pool = fk_test_pool().await;
 
         run_migrations(&pool).await.unwrap();
 
@@ -656,7 +872,7 @@ mod tests {
         run_migrations(&pool).await.expect("baseline migrate");
 
         const POISON: &[(i64, &str, &str)] = &[(
-            9,
+            10,
             "rb-02 atomicity poison",
             r#"
             CREATE TABLE poison_marker (id INTEGER PRIMARY KEY);
@@ -680,15 +896,14 @@ mod tests {
             "poison_marker must not exist; got: {marker:?}"
         );
 
-        // `schema_version` must not include v9 — version insert is part
+        // `schema_version` must not include v10 — version insert is part
         // of the same transaction that rolled back.
-        let max: i64 =
-            sqlx::query_scalar("SELECT COALESCE(MAX(version), 0) FROM schema_version")
-                .fetch_one(&pool)
-                .await
-                .expect("read schema_version");
+        let max: i64 = sqlx::query_scalar("SELECT COALESCE(MAX(version), 0) FROM schema_version")
+            .fetch_one(&pool)
+            .await
+            .expect("read schema_version");
         assert_eq!(
-            max, 8,
+            max, 9,
             "schema_version must not advance past the failed migration"
         );
     }

crates/transcription/src/lib.rs

@@ -7,13 +7,13 @@ pub mod transcriber;
 pub mod whisper_rs_backend;
 
 pub use concurrency::run_inference;
-pub use local_engine::{load_parakeet, LocalEngine, SpeechModelAdapter, TimedTranscript};
 #[cfg(feature = "whisper")]
 pub use local_engine::load_whisper;
+pub use local_engine::{load_parakeet, LocalEngine, SpeechModelAdapter, TimedTranscript};
 pub use model_manager::{download, is_downloaded, list_downloaded, model_dir, models_dir};
 pub use streaming::{
     sample_index_for_seconds, trim_buffer_to_commit_point, CommitDecision, CommitPolicy,
     LocalAgreement, RmsVadChunker, Token, VadChunk, VadChunker,
 };
-pub use transcriber::{Transcriber, TranscriberCapabilities};
 pub use transcribe_rs::SpeechModel;
+pub use transcriber::{Transcriber, TranscriberCapabilities};

crates/transcription/src/model_manager.rs

@@ -557,7 +557,10 @@ mod tests {
             .expect_err("mismatched sha must fail");
         let msg = err.to_string();
         assert!(msg.contains("SHA256 mismatch"), "unexpected error: {msg}");
-        assert!(!dest.exists(), ".part → dest rename must not run on mismatch");
+        assert!(
+            !dest.exists(),
+            ".part → dest rename must not run on mismatch"
+        );
         let part = dest.with_extension("bin.part");
         assert!(!part.exists(), "failed hash must clean up the .part file");
     }

crates/transcription/src/streaming/commit_policy.rs

@@ -108,11 +108,7 @@ impl LocalAgreement {
 
         // Can't commit anything until we have n passes in hand.
         if self.history.len() < self.n {
-            let tentative = self
-                .history
-                .back()
-                .cloned()
-                .unwrap_or_default();
+            let tentative = self.history.back().cloned().unwrap_or_default();
             return CommitDecision {
                 newly_committed: Vec::new(),
                 tentative,

crates/transcription/src/streaming/rms_vad.rs

@@ -121,7 +121,7 @@ impl RmsVadChunker {
             pending_onset_frames: 0,
             onset_buffer: Vec::new(),
             next_sample_index: 0,
-        active_chunk_start: 0,
+            active_chunk_start: 0,
         }
     }
 
@@ -552,10 +552,7 @@ mod tests {
         let mut c = RmsVadChunker::new();
         assert!(c.flush().is_empty());
         let _ = c.push(&constant_signal(16_000, 0.0));
-        assert!(
-            c.flush().is_empty(),
-            "flushing pure silence emits nothing"
-        );
+        assert!(c.flush().is_empty(), "flushing pure silence emits nothing");
     }
 
     #[test]

crates/transcription/src/whisper_rs_backend.rs

@@ -62,10 +62,9 @@ impl Transcriber for WhisperRsBackend {
             "WhisperRsBackend::transcribe_sync entering"
         );
 
-        let mut state = self
-            .ctx
-            .create_state()
-            .map_err(|e| KonError::TranscriptionFailed(WhisperBackendError::State(e.to_string()).to_string()))?;
+        let mut state = self.ctx.create_state().map_err(|e| {
+            KonError::TranscriptionFailed(WhisperBackendError::State(e.to_string()).to_string())
+        })?;
 
         let mut params = FullParams::new(SamplingStrategy::Greedy { best_of: 1 });
         if let Some(lang) = options.language.as_deref() {
@@ -83,9 +82,11 @@ impl Transcriber for WhisperRsBackend {
         params.set_print_progress(false);
         params.set_print_realtime(false);
 
-        state
-            .full(params, samples)
-            .map_err(|e| KonError::TranscriptionFailed(WhisperBackendError::Transcribe(e.to_string()).to_string()))?;
+        state.full(params, samples).map_err(|e| {
+            KonError::TranscriptionFailed(
+                WhisperBackendError::Transcribe(e.to_string()).to_string(),
+            )
+        })?;
 
         let n = state.full_n_segments();
 
@@ -96,7 +97,11 @@ impl Transcriber for WhisperRsBackend {
             };
             let text = seg
                 .to_str()
-                .map_err(|e| KonError::TranscriptionFailed(WhisperBackendError::Transcribe(e.to_string()).to_string()))?
+                .map_err(|e| {
+                    KonError::TranscriptionFailed(
+                        WhisperBackendError::Transcribe(e.to_string()).to_string(),
+                    )
+                })?
                 .to_string();
             // whisper-rs timestamps are centiseconds (10ms units). Convert to seconds (f64).
             let start = seg.start_timestamp() as f64 * 0.01;

docs/issues/README.md

@@ -11,43 +11,36 @@ Issues here must land before Kon v0.1 ships. Each is sourced from
 `docs/code-review-2026-04-22.md`. When `gh` CLI is available, these
 should be mirrored as real GitHub issues on `jakejars/kon`.
 
-## CRITICAL (2 open, 1 resolved)
+## CRITICAL (0 open, 3 resolved)
+
+No open CRITICAL blockers.
+
+## MAJOR (1 open, 8 resolved)
 
 | # | File | Area | Fix scope |
 |---|---|---|---|
-| RB-01 | [c1-live-session-race.md](c1-live-session-race.md) | `src-tauri/commands/live.rs` | large |
-| RB-03 | [c4-transcript-profile-fk.md](c4-transcript-profile-fk.md) | `crates/storage/migrations.rs` + `database.rs` | large |
-
-## MAJOR (5 open, 4 resolved)
-
-| # | File | Area | Fix scope |
-|---|---|---|---|
-| RB-04 | [run-live-session-monolith.md](run-live-session-monolith.md) | `src-tauri/commands/live.rs` | large |
-| RB-05 | [poll-inference-channel-fatality.md](poll-inference-channel-fatality.md) | `src-tauri/commands/live.rs` | medium |
 | RB-08 | [power-assertion-macos-objc2.md](power-assertion-macos-objc2.md) | `src-tauri/commands/power.rs` | medium |
-| RB-10 | [llm-prompt-preflight.md](llm-prompt-preflight.md) | `crates/llm/lib.rs` | medium |
-| RB-11 | [keystore-thread-safety.md](keystore-thread-safety.md) | `crates/cloud-providers/keystore.rs` | medium |
 
 ## Resolved
 
 | # | File | Area | Resolution |
 |---|---|---|---|
+| RB-01 | [c1-live-session-race.md](c1-live-session-race.md) | `src-tauri/commands/live.rs` | Added `LiveTranscriptionState.lifecycle: tokio::sync::Mutex<()>` and hold it across the async spans of both `start_live_transcription_session` and `stop_live_transcription_session`. The running-slot check/insert and stop/take/join sequence are now serialized, so concurrent starts can no longer both pass the empty-slot check and a start during stop blocks until the previous worker fully joins. Two async regression tests cover both races. |
 | RB-02 | [c3-migrations-atomicity.md](c3-migrations-atomicity.md) | `crates/storage/migrations.rs` | Each migration now runs inside a `pool.begin()` / `tx.commit()` transaction alongside its `schema_version` insert. Regression test injects a poisoned v9 migration and asserts neither the partial schema change nor the version row persists. DRY'd `run_migrations_up_to` test helper onto the same code path. |
+| RB-03 | [c4-transcript-profile-fk.md](c4-transcript-profile-fk.md) | `crates/storage/migrations.rs` + `database.rs` | Added a transactional v9 rebuild of `transcripts` that enforces `profile_id REFERENCES profiles(id) ON DELETE RESTRICT`, reassigns any orphaned transcript provenance to `DEFAULT_PROFILE_ID`, rebuilds dependent `segments` / FTS state, and preserves valid profile references. `insert_transcript` now rejects unknown profile ids up front, and `delete_profile` returns a clear reassign-first error when transcripts still reference the profile. Regression tests cover migration reconciliation, invalid inserts, and delete rejection. |
+| RB-04 | [run-live-session-monolith.md](run-live-session-monolith.md) | `src-tauri/commands/live.rs` | Replaced the 200+ line `run_live_session` loop with an explicit `LiveSessionRuntime` + `LiveLoopState` structure. Capture startup, runtime mic-error draining, audio chunk processing, overflow handling, stop-tail flush, inference dispatch/drain, and WAV finalisation each live in focused helpers, preserving behaviour while making the lifecycle auditable enough for RB-01 follow-up. Existing live tests and the full `kon` lib suite stay green. |
+| RB-05 | [poll-inference-channel-fatality.md](poll-inference-channel-fatality.md) | `src-tauri/commands/live.rs` | `poll_inference` now treats result-channel loss as a listener-lifecycle problem rather than a transcription failure. On the first `result_channel.send(...)` error it marks the live result listener as lost, emits a single warning that transcription will continue in the background, and keeps processing later chunks without retrying the dead channel. Regression test simulates a dead result listener and asserts chunk processing continues with only one warning. |
 | RB-06 | [native-capture-worker-join.md](native-capture-worker-join.md) | `src-tauri/commands/audio.rs` | `NativeCaptureState.stop_tx` replaced by `worker: AsyncMutex<Option<CaptureWorker>>`. `CaptureWorker` bundles the stop sender and the spawned task's `JoinHandle`; `stop_worker(worker)` sends stop then `await`s termination. Both `start_native_capture` (prior-worker stop) and `stop_native_capture` use the helper. Removed the 50ms sleep — the join barrier is exact. Two regression tests cover the lifecycle guarantee and the already-exited case. |
 | RB-07 | [runtime-capabilities-accelerators.md](runtime-capabilities-accelerators.md) | `src-tauri/commands/models.rs` | Introduced `compose_accelerators(whisper_enabled, loader_available, target)` as a pure helper; `supported_accelerators()` reads `cfg(feature = "whisper")`, `vulkan_loader_available()`, and target OS then delegates. `get_runtime_capabilities` uses it in place of the hard-coded `["cpu", "vulkan"]`. Whisper's `supports_gpu` now follows the feature flag. Five regression tests cover all permutations. |
 | RB-09 | [decoder-partial-audio-on-error.md](decoder-partial-audio-on-error.md) | `crates/audio/decode.rs` | Packet-loop now propagates all non-EOF `SymphoniaError`s as `AudioDecodeFailed`; per-packet decode errors bubble via `?`. Mock-`MediaSource` regression test confirms mid-stream I/O errors surface instead of returning partial audio. |
+| RB-10 | [llm-prompt-preflight.md](llm-prompt-preflight.md) | `crates/llm/lib.rs` | Added an explicit prompt-budget preflight before context creation. If `prompt_tokens + max_tokens + reserve` exceeds the 8192-token cap, `generate` now returns a typed `EngineError::PromptTooLong { ... }` instead of failing late inside inference. Regression tests cover both the over-budget and exact-budget boundaries. |
+| RB-11 | [keystore-thread-safety.md](keystore-thread-safety.md) | `crates/cloud-providers/keystore.rs` | Replaced the `std::env::set_var` stub with a process-global `OnceLock<Mutex<HashMap<...>>>` keystore, keeping the API safe from any thread. Retrieval still falls back to read-only `KON_API_KEY_*` env vars for externally supplied secrets. Two regression tests cover store/retrieve and provider isolation. |
 | RB-12 | [hotkey-linux-device-filter.md](hotkey-linux-device-filter.md) | `crates/hotkey/linux.rs` | Extracted `device_supports_combo` helper; `try_attach_device` now reads the configured `HotkeyCombo` from the watch channel and checks support for that trigger key. Four regression tests land in `linux::tests`. |
 
-## Dependencies
+## Remaining blocker
 
-```
-RB-01 (live session race)
-  └── blocked by RB-04 (run_live_session monolith refactor)
-
-RB-03 (transcript-profile FK)
-  └── coupled with RB-02 (migrations atomicity)
-      — a v9 migration adding the FK constraint must be transactional
-```
+`RB-08` remains open pending manual runtime verification on a real macOS
+machine (`pmset -g assertions`, background live-session sanity check).
 
 ## How to convert to GitHub issues
 

docs/issues/c1-live-session-race.md

@@ -4,6 +4,31 @@
 **Path:** `src-tauri/src/commands/live.rs:193-338`
 **Source:** [2026-04-22 code review](../code-review-2026-04-22.md#c1--racy-single-session-guard-in-livers)
 **Labels:** release-blocker, critical, concurrency
+**Status:** RESOLVED (2026-04-22)
+
+## Resolution
+
+`LiveTranscriptionState` now includes a dedicated
+`tokio::sync::Mutex<()>` lifecycle gate. Both
+`start_live_transcription_session` and
+`stop_live_transcription_session` acquire that async mutex before
+touching `running`, and they keep it held across the awaited setup /
+join work that previously exposed the race windows.
+
+That changes the two failing interleavings from the review:
+
+- Two overlapping starts no longer race through the empty-slot check.
+  The second call waits for the first to finish setup, then observes
+  `running.is_some()` and returns the existing
+  `"A live transcription session is already running"` error.
+- A start launched during stop can no longer sneak in after
+  `running.take()` but before the previous worker has fully joined.
+  It blocks on the lifecycle mutex until the join completes.
+
+Regression tests in `commands::live::tests`:
+
+- `concurrent_starts_allow_only_one_session_to_claim_the_slot`
+- `start_waits_for_stop_to_finish_joining_before_reusing_slot`
 
 ## Problem
 
@@ -26,4 +51,4 @@ Large. Will likely require the `run_live_session` monolith refactor (RB-04) to l
 
 ## Dependencies
 
-- **Blocked by:** RB-04 (`run_live_session` monolith refactor)
+- Landed after RB-04 (`run_live_session` refactor) made the worker lifecycle explicit enough to guard safely.

docs/issues/c4-transcript-profile-fk.md

@@ -4,6 +4,33 @@
 **Path:** `crates/storage/src/migrations.rs:208-216`, `crates/storage/src/database.rs:61-89`, `:697-708`
 **Source:** [2026-04-22 code review](../code-review-2026-04-22.md#c4--transcript-provenance-can-reference-deleted-profiles)
 **Labels:** release-blocker, critical, data-integrity, storage
+**Status:** RESOLVED (2026-04-22)
+
+## Resolution
+
+Chose the strict provenance path:
+
+- Migration v9 rebuilds `transcripts` with
+  `profile_id REFERENCES profiles(id) ON DELETE RESTRICT`.
+- Existing orphaned transcript `profile_id` values are reconciled onto
+  `DEFAULT_PROFILE_ID` during the copy into the rebuilt table.
+- Because SQLite table renames rewrite dependent references, the
+  migration also rebuilds `segments`, recreates the transcript FTS
+  virtual table/triggers, and repopulates FTS from the rebuilt
+  transcript rows inside the same transaction.
+
+Application-layer behaviour now matches the schema:
+
+- `insert_transcript` rejects unknown `profile_id` values with a clear
+  storage error before attempting the insert.
+- `delete_profile` returns a human-readable reassign-first error when
+  transcripts still reference that profile.
+
+Regression tests:
+
+- `migration_v9_reconciles_orphaned_transcript_profiles_and_adds_fk`
+- `insert_transcript_rejects_unknown_profile_id`
+- `delete_profile_rejects_when_transcripts_reference_it`
 
 ## Problem
 

docs/issues/keystore-thread-safety.md

@@ -4,6 +4,28 @@
 **Path:** `crates/cloud-providers/src/keystore.rs:6-18`
 **Source:** [2026-04-22 code review](../code-review-2026-04-22.md)
 **Labels:** release-blocker, major, unsafe-api, cloud
+**Status:** RESOLVED (2026-04-22)
+
+## Resolution
+
+Chose acceptance option 2. The environment-mutation stub is gone;
+`store_api_key` now writes into a process-global
+`OnceLock<Mutex<HashMap<String, String>>>`, so the safe signature matches
+the actual safety properties.
+
+Additional details:
+
+- Stored keys now live in-memory only for the life of the process.
+- `retrieve_api_key` checks the in-memory keystore first, then falls
+  back to read-only `KON_API_KEY_<PROVIDER>` environment variables so
+  externally injected secrets still work.
+- Module docs now describe the real tradeoff clearly: safe from any
+  thread, but non-persistent until a proper OS keychain backend lands.
+
+Regression tests:
+
+- `stored_key_is_retrievable_without_env_mutation`
+- `providers_do_not_overlap`
 
 ## Problem
 

docs/issues/llm-prompt-preflight.md

@@ -4,6 +4,25 @@
 **Path:** `crates/llm/src/lib.rs:143-166`, `:317-321`
 **Source:** [2026-04-22 code review](../code-review-2026-04-22.md)
 **Labels:** release-blocker, major, llm
+**Status:** RESOLVED (2026-04-22)
+
+## Resolution
+
+`LlmEngine::generate` still tokenises the whole prompt up front, but it
+now runs a dedicated prompt-budget preflight before creating the llama
+context. The chosen behaviour is an early typed failure rather than
+silent truncation:
+
+- If `prompt_tokens + max_tokens + 64 reserve tokens` exceeds the
+  8192-token cap, generation returns
+  `EngineError::PromptTooLong { prompt_tokens, max_tokens, available_prompt_tokens, context_window }`.
+- Prompts that fit exactly within the available budget still proceed and
+  allocate an 8192-token context as before.
+
+Regression tests:
+
+- `prompt_preflight_rejects_oversized_prompt_tokens`
+- `prompt_preflight_keeps_prompts_within_budget`
 
 ## Problem
 

docs/issues/poll-inference-channel-fatality.md

@@ -4,6 +4,31 @@
 **Path:** `src-tauri/src/commands/live.rs:721-813`
 **Source:** [2026-04-22 code review](../code-review-2026-04-22.md)
 **Labels:** release-blocker, major, ipc-lifecycle
+**Status:** RESOLVED (2026-04-22)
+
+## Resolution
+
+`poll_inference` no longer propagates `result_channel.send(...)` with `?`.
+Instead, live-result delivery is routed through a small helper that
+tracks whether the frontend listener has already been lost:
+
+- First send failure: mark the result listener as unavailable, log a
+  warning, and best-effort send a `LiveStatusMessage::Warning`
+  explaining that transcription will continue in the background until
+  the user stops the session.
+- Subsequent chunks: skip re-sending to the dead result channel and
+  keep the worker running.
+
+Crucially, this path is now separate from actual transcription failure:
+inference errors still emit `LiveStatusMessage::Error` and stop the
+session, while listener-loss just stops live preview delivery.
+
+Regression test:
+
+- `result_listener_loss_is_warned_once_and_not_treated_as_inference_failure`
+  simulates a dead result channel, confirms the first processed chunk
+  downgrades to a warning, and confirms a second chunk still processes
+  successfully without a second warning.
 
 ## Problem
 

docs/issues/power-assertion-macos-objc2.md

@@ -5,6 +5,18 @@
 **Source:** [2026-04-22 code review](../code-review-2026-04-22.md), originally deferred during A.1 #9
 **Labels:** release-blocker, major, macos, platform
 
+**Current state (2026-04-23):** `objc2`/`objc2-foundation` have been
+added behind `cfg(target_os = "macos")`, and the `NSProcessInfo`
+bridge now calls `beginActivityWithOptions:reason:` / `endActivity:`
+with the retained activity handle. Isolated `cargo check` validation
+passes for both `x86_64-apple-darwin` and `aarch64-apple-darwin`.
+Remaining acceptance gap: manual runtime verification on a real macOS
+machine (`pmset -g assertions`, background live session). Diagnostic
+reports now also include a `## Power assertions` section that lists any
+currently active Kon assertion guards (`reason`, `backend`, `acquired`)
+at report time, which gives the tester an in-app breadcrumb alongside
+`pmset`.
+
 ## Problem
 
 `begin_activity` always returns `Err` on macOS, so `PowerAssertion::begin` converts to `None` and the guard never acquires an `NSProcessInfo beginActivityWithOptions:reason:` assertion. Live recording and LLM cleanup therefore run without App Nap protection on the one platform where it matters.
@@ -18,6 +30,21 @@ The stub was deliberate (A.1 #9 acceptance concession — untestable on Linux wi
 - `end_activity` calls `endActivity:` on the retained handle.
 - Manual-test on a real macOS box: 10-minute background live session completes without throttling; `pmset -g assertions` shows Kon's activity during capture.
 
+## Manual verification checklist
+
+1. Launch Kon on a real macOS machine and start a live transcription session.
+2. While capture is running, background the app for at least several minutes.
+3. In Terminal, run `pmset -g assertions` and confirm Kon appears with a
+   user-initiated / no-idle-style assertion while the session is active.
+4. While the session is still running, generate a Kon diagnostic report
+   and confirm the `## Power assertions` section lists an active entry
+   such as `reason=kon live dictation session`, `backend=macos`,
+   `acquired=true`.
+5. Stop the session and rerun `pmset -g assertions` or regenerate the
+   diagnostic report to confirm the assertion disappears.
+6. Repeat once for the LLM cleanup path if desired
+   (`reason=kon LLM cleanup`).
+
 ## Fix scope
 
 Medium. Dep addition + FFI glue + manual verification. Can be done from Linux with `cargo check --target=aarch64-apple-darwin` for compile validation, but runtime behaviour needs a macOS machine.

docs/issues/run-live-session-monolith.md

@@ -4,6 +4,33 @@
 **Path:** `src-tauri/src/commands/live.rs:349-579`
 **Source:** [2026-04-22 code review](../code-review-2026-04-22.md)
 **Labels:** release-blocker, major, refactor, concurrency
+**Status:** RESOLVED (2026-04-22)
+
+## Resolution
+
+`run_live_session` was split around two explicit state holders:
+
+- `ActiveCapture` owns the cpal stream handle, audio receiver, and
+  optional runtime-error channel.
+- `LiveLoopState` owns the mutable per-session loop state: resampler,
+  capture buffer, WAV writer, buffer offsets, dropped-audio accounting,
+  in-flight inference task, and duplicate-history buffer.
+
+The top-level worker is now `LiveSessionRuntime`, with focused methods
+for:
+
+- polling in-flight inference
+- draining microphone runtime warnings
+- receiving + resampling an audio chunk
+- dropping pending-buffer overflow
+- flushing the resampler tail when stop is requested
+- dispatching inference when enough audio is buffered
+- draining the last in-flight task
+- finalising the progressive WAV writer
+
+This keeps behaviour intact but removes the "everything in one mutable
+loop" shape that made concurrency review hard. The refactor also made
+RB-01 straightforward enough to land immediately afterward.
 
 ## Problem
 

src-tauri/Cargo.toml

@@ -74,3 +74,7 @@ webkit2gtk = "2.0"
 # transitively depends on (GTK 3).
 gtk = "0.18"
 gdk = "0.18"
+
+[target.'cfg(target_os = "macos")'.dependencies]
+objc2 = "0.6.4"
+objc2-foundation = { version = "0.3.2", default-features = false, features = ["std", "NSString", "NSProcessInfo"] }

src-tauri/build.rs

@@ -33,8 +33,8 @@ fn assert_localhost_llm_csp() {
 
     let raw = std::fs::read_to_string(conf_path)
         .expect("build.rs: failed to read tauri.conf.json for CSP regression guard");
-    let conf: serde_json::Value = serde_json::from_str(&raw)
-        .expect("build.rs: tauri.conf.json is not valid JSON");
+    let conf: serde_json::Value =
+        serde_json::from_str(&raw).expect("build.rs: tauri.conf.json is not valid JSON");
 
     let csp = conf
         .pointer("/app/security/csp")

src-tauri/gen/schemas/desktop-schema.json

@@ -2313,22 +2313,22 @@
           "markdownDescription": "Denies the unminimize command without any pre-configured scope."
         },
         {
-          "description": "This permission set configures the types of dialogs\navailable from the dialog plugin.\n\n#### Granted Permissions\n\nAll dialog types are enabled.\n\n\n\n#### This default permission set includes:\n\n- `allow-message`\n- `allow-save`\n- `allow-open`",
+          "description": "This permission set configures the types of dialogs\navailable from the dialog plugin.\n\n#### Granted Permissions\n\nAll dialog types are enabled.\n\n\n\n#### This default permission set includes:\n\n- `allow-ask`\n- `allow-confirm`\n- `allow-message`\n- `allow-save`\n- `allow-open`",
           "type": "string",
           "const": "dialog:default",
-          "markdownDescription": "This permission set configures the types of dialogs\navailable from the dialog plugin.\n\n#### Granted Permissions\n\nAll dialog types are enabled.\n\n\n\n#### This default permission set includes:\n\n- `allow-message`\n- `allow-save`\n- `allow-open`"
+          "markdownDescription": "This permission set configures the types of dialogs\navailable from the dialog plugin.\n\n#### Granted Permissions\n\nAll dialog types are enabled.\n\n\n\n#### This default permission set includes:\n\n- `allow-ask`\n- `allow-confirm`\n- `allow-message`\n- `allow-save`\n- `allow-open`"
         },
         {
-          "description": "Enables the ask command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `allow-message` and will be removed in v3)",
+          "description": "Enables the ask command without any pre-configured scope.",
           "type": "string",
           "const": "dialog:allow-ask",
-          "markdownDescription": "Enables the ask command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `allow-message` and will be removed in v3)"
+          "markdownDescription": "Enables the ask command without any pre-configured scope."
         },
         {
-          "description": "Enables the confirm command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `allow-message` and will be removed in v3)",
+          "description": "Enables the confirm command without any pre-configured scope.",
           "type": "string",
           "const": "dialog:allow-confirm",
-          "markdownDescription": "Enables the confirm command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `allow-message` and will be removed in v3)"
+          "markdownDescription": "Enables the confirm command without any pre-configured scope."
         },
         {
           "description": "Enables the message command without any pre-configured scope.",
@@ -2349,16 +2349,16 @@
           "markdownDescription": "Enables the save command without any pre-configured scope."
         },
         {
-          "description": "Denies the ask command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `deny-message` and will be removed in v3)",
+          "description": "Denies the ask command without any pre-configured scope.",
           "type": "string",
           "const": "dialog:deny-ask",
-          "markdownDescription": "Denies the ask command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `deny-message` and will be removed in v3)"
+          "markdownDescription": "Denies the ask command without any pre-configured scope."
         },
         {
-          "description": "Denies the confirm command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `deny-message` and will be removed in v3)",
+          "description": "Denies the confirm command without any pre-configured scope.",
           "type": "string",
           "const": "dialog:deny-confirm",
-          "markdownDescription": "Denies the confirm command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `deny-message` and will be removed in v3)"
+          "markdownDescription": "Denies the confirm command without any pre-configured scope."
         },
         {
           "description": "Denies the message command without any pre-configured scope.",

src-tauri/gen/schemas/linux-schema.json

@@ -2313,22 +2313,22 @@
           "markdownDescription": "Denies the unminimize command without any pre-configured scope."
         },
         {
-          "description": "This permission set configures the types of dialogs\navailable from the dialog plugin.\n\n#### Granted Permissions\n\nAll dialog types are enabled.\n\n\n\n#### This default permission set includes:\n\n- `allow-message`\n- `allow-save`\n- `allow-open`",
+          "description": "This permission set configures the types of dialogs\navailable from the dialog plugin.\n\n#### Granted Permissions\n\nAll dialog types are enabled.\n\n\n\n#### This default permission set includes:\n\n- `allow-ask`\n- `allow-confirm`\n- `allow-message`\n- `allow-save`\n- `allow-open`",
           "type": "string",
           "const": "dialog:default",
-          "markdownDescription": "This permission set configures the types of dialogs\navailable from the dialog plugin.\n\n#### Granted Permissions\n\nAll dialog types are enabled.\n\n\n\n#### This default permission set includes:\n\n- `allow-message`\n- `allow-save`\n- `allow-open`"
+          "markdownDescription": "This permission set configures the types of dialogs\navailable from the dialog plugin.\n\n#### Granted Permissions\n\nAll dialog types are enabled.\n\n\n\n#### This default permission set includes:\n\n- `allow-ask`\n- `allow-confirm`\n- `allow-message`\n- `allow-save`\n- `allow-open`"
         },
         {
-          "description": "Enables the ask command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `allow-message` and will be removed in v3)",
+          "description": "Enables the ask command without any pre-configured scope.",
           "type": "string",
           "const": "dialog:allow-ask",
-          "markdownDescription": "Enables the ask command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `allow-message` and will be removed in v3)"
+          "markdownDescription": "Enables the ask command without any pre-configured scope."
         },
         {
-          "description": "Enables the confirm command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `allow-message` and will be removed in v3)",
+          "description": "Enables the confirm command without any pre-configured scope.",
           "type": "string",
           "const": "dialog:allow-confirm",
-          "markdownDescription": "Enables the confirm command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `allow-message` and will be removed in v3)"
+          "markdownDescription": "Enables the confirm command without any pre-configured scope."
         },
         {
           "description": "Enables the message command without any pre-configured scope.",
@@ -2349,16 +2349,16 @@
           "markdownDescription": "Enables the save command without any pre-configured scope."
         },
         {
-          "description": "Denies the ask command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `deny-message` and will be removed in v3)",
+          "description": "Denies the ask command without any pre-configured scope.",
           "type": "string",
           "const": "dialog:deny-ask",
-          "markdownDescription": "Denies the ask command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `deny-message` and will be removed in v3)"
+          "markdownDescription": "Denies the ask command without any pre-configured scope."
         },
         {
-          "description": "Denies the confirm command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `deny-message` and will be removed in v3)",
+          "description": "Denies the confirm command without any pre-configured scope.",
           "type": "string",
           "const": "dialog:deny-confirm",
-          "markdownDescription": "Denies the confirm command without any pre-configured scope. (**DEPRECATED**: This is now an alias to `deny-message` and will be removed in v3)"
+          "markdownDescription": "Denies the confirm command without any pre-configured scope."
         },
         {
           "description": "Denies the message command without any pre-configured scope.",

src-tauri/src/commands/audio.rs

@@ -308,8 +308,7 @@ fn recording_filename() -> String {
 /// restarts, so cross-launch collisions are already impossible — the
 /// counter is the last-mile guarantee against within-launch same-tick
 /// collisions.
-static RECORDING_COUNTER: std::sync::atomic::AtomicU64 =
-    std::sync::atomic::AtomicU64::new(0);
+static RECORDING_COUNTER: std::sync::atomic::AtomicU64 = std::sync::atomic::AtomicU64::new(0);
 
 #[cfg(test)]
 mod tests {
@@ -353,10 +352,20 @@ mod tests {
             3,
             "expected three '-' separated parts, got {parts:?}"
         );
-        assert!(parts[0].chars().all(|c| c.is_ascii_digit()), "secs is digits");
-        assert_eq!(parts[1].len(), 9, "nanos component is zero-padded to 9 digits");
+        assert!(
+            parts[0].chars().all(|c| c.is_ascii_digit()),
+            "secs is digits"
+        );
+        assert_eq!(
+            parts[1].len(),
+            9,
+            "nanos component is zero-padded to 9 digits"
+        );
         assert!(parts[1].chars().all(|c| c.is_ascii_digit()));
-        assert!(parts[2].len() >= 4, "counter component is zero-padded to >=4 digits");
+        assert!(
+            parts[2].len() >= 4,
+            "counter component is zero-padded to >=4 digits"
+        );
         assert!(parts[2].chars().all(|c| c.is_ascii_digit()));
     }
 

src-tauri/src/commands/diagnostics.rs

@@ -19,6 +19,7 @@ use kon_storage::{
     app_data_dir, crashes_dir, list_recent_errors, log_error, logs_dir, ErrorLogRow,
 };
 
+use crate::commands::power::active_assertions_snapshot;
 use crate::AppState;
 
 const DEFAULT_RECENT_ERRORS: i64 = 50;
@@ -290,6 +291,20 @@ pub async fn generate_diagnostic_report(
         }
     }
 
+    out.push_str("## Power assertions\n\n");
+    let power_assertions = active_assertions_snapshot();
+    if power_assertions.is_empty() {
+        out.push_str("_(no active power assertions at report time)_\n\n");
+    } else {
+        for assertion in power_assertions {
+            out.push_str(&format!(
+                "- `#{}` reason=`{}` backend=`{}` acquired=`{}`\n",
+                assertion.id, assertion.reason, assertion.backend, assertion.acquired
+            ));
+        }
+        out.push('\n');
+    }
+
     if opts.include_crashes {
         out.push_str("## Crash dumps\n\n");
         let crashes = list_crash_files().await.unwrap_or_default();

src-tauri/src/commands/live.rs

@@ -11,6 +11,7 @@ use std::time::{Duration, Instant};
 
 use serde::{Deserialize, Serialize};
 use tauri::ipc::Channel;
+use tokio::sync::Mutex as AsyncMutex;
 
 use crate::commands::audio::resolve_recording_path;
 use crate::commands::build_initial_prompt;
@@ -18,7 +19,9 @@ use crate::commands::models::{default_model_id_for_engine, ensure_model_loaded};
 use crate::commands::power::PowerAssertion;
 use crate::AppState;
 use kon_ai_formatting::{post_process_segments, FormatMode, PostProcessOptions};
-use kon_audio::{MicrophoneCapture, StreamingResampler, WavWriter};
+use kon_audio::{
+    AudioChunk, CaptureRuntimeError, MicrophoneCapture, StreamingResampler, WavWriter,
+};
 use kon_core::constants::WHISPER_SAMPLE_RATE;
 use kon_core::types::{AudioSamples, Segment, TranscriptionOptions};
 use kon_transcription::LocalEngine;
@@ -57,6 +60,7 @@ const LOW_SIGNAL_TOKENS: &[&str] = &[
 #[derive(Default)]
 pub struct LiveTranscriptionState {
     next_session_id: AtomicU64,
+    lifecycle: AsyncMutex<()>,
     running: Mutex<Option<RunningLiveSession>>,
 }
 
@@ -153,6 +157,292 @@ struct LiveSessionSummary {
     audio_path: Option<String>,
 }
 
+/// Session worker state is thread-confined to the single blocking task spawned
+/// by `start_live_transcription_session`. Cross-thread coordination happens via
+/// the stop flag and mpsc channels only; RB-01 will tighten the outer
+/// `live_state.running` lock discipline now that this worker lifecycle is
+/// explicit and locally structured.
+struct ActiveCapture {
+    /// Keeping the capture handle alive keeps the underlying cpal stream alive.
+    _capture: MicrophoneCapture,
+    rx: std::sync::mpsc::Receiver<AudioChunk>,
+    mic_error_rx: Option<std::sync::mpsc::Receiver<CaptureRuntimeError>>,
+}
+
+impl ActiveCapture {
+    fn start(config: &StartLiveTranscriptionConfig) -> Result<Self, String> {
+        let (mut capture, rx) = match config.microphone_device.as_deref() {
+            Some(name) if !name.is_empty() => MicrophoneCapture::start_with_device(name),
+            _ => MicrophoneCapture::start(),
+        }
+        .map_err(|e| e.to_string())?;
+        let mic_error_rx = capture.take_error_rx();
+        Ok(Self {
+            _capture: capture,
+            rx,
+            mic_error_rx,
+        })
+    }
+
+    fn drain_runtime_errors(
+        &mut self,
+        session_id: u64,
+        status_channel: &Channel<LiveStatusMessage>,
+    ) {
+        let Some(err_rx) = &self.mic_error_rx else {
+            return;
+        };
+        while let Ok(err) = err_rx.try_recv() {
+            let _ = status_channel.send(LiveStatusMessage::Warning {
+                session_id,
+                message: format!(
+                    "Microphone '{}' reported an error: {}",
+                    err.device_name, err.message
+                ),
+            });
+        }
+    }
+}
+
+#[derive(Default)]
+struct LiveLoopState {
+    resampler: Option<StreamingResampler>,
+    capture_buffer: Vec<f32>,
+    wav_writer: Option<WavWriter>,
+    buffer_start_sample: u64,
+    dropped_audio_ms: u64,
+    chunk_id: u32,
+    inflight: Option<InferenceTask>,
+    resampler_flushed: bool,
+    result_listener_lost: bool,
+    recent_segments: Vec<RecentTranscriptSegment>,
+}
+
+impl LiveLoopState {
+    fn new(wav_writer: Option<WavWriter>) -> Self {
+        Self {
+            wav_writer,
+            ..Self::default()
+        }
+    }
+}
+
+struct LiveSessionRuntime {
+    session_id: u64,
+    engine: Arc<LocalEngine>,
+    config: StartLiveTranscriptionConfig,
+    audio_path: Option<PathBuf>,
+    dictionary_terms: Vec<String>,
+    result_channel: Channel<LiveResultMessage>,
+    status_channel: Channel<LiveStatusMessage>,
+    stop_flag: Arc<AtomicBool>,
+    capture: ActiveCapture,
+    state: LiveLoopState,
+}
+
+impl LiveSessionRuntime {
+    fn new(
+        session_id: u64,
+        engine: Arc<LocalEngine>,
+        config: StartLiveTranscriptionConfig,
+        audio_path: Option<PathBuf>,
+        dictionary_terms: Vec<String>,
+        result_channel: Channel<LiveResultMessage>,
+        status_channel: Channel<LiveStatusMessage>,
+        stop_flag: Arc<AtomicBool>,
+    ) -> Result<Self, String> {
+        let capture = ActiveCapture::start(&config)?;
+        let wav_writer = open_wav_writer(&engine, audio_path.as_ref(), session_id, &status_channel);
+        Ok(Self {
+            session_id,
+            engine,
+            config,
+            audio_path,
+            dictionary_terms,
+            result_channel,
+            status_channel,
+            stop_flag,
+            capture,
+            state: LiveLoopState::new(wav_writer),
+        })
+    }
+
+    fn run(mut self) -> Result<LiveSessionSummary, String> {
+        loop {
+            self.poll_inference()?;
+            self.capture
+                .drain_runtime_errors(self.session_id, &self.status_channel);
+            if let Some(chunk) = self.recv_audio()? {
+                self.process_audio_chunk(chunk)?;
+            }
+            self.drop_pending_overflow();
+            self.flush_tail_if_stopping()?;
+            if self.dispatch_inference_if_ready() {
+                continue;
+            }
+            if self.should_exit_loop() {
+                break;
+            }
+        }
+
+        self.drain_inference()?;
+        self.finish()
+    }
+
+    fn poll_inference(&mut self) -> Result<(), String> {
+        let _ = poll_inference(
+            &mut self.state.inflight,
+            &mut self.state.result_listener_lost,
+            self.session_id,
+            &self.config,
+            &mut self.state.recent_segments,
+            &self.dictionary_terms,
+            &self.result_channel,
+            &self.status_channel,
+        )?;
+        Ok(())
+    }
+
+    fn recv_audio(&mut self) -> Result<Option<AudioChunk>, String> {
+        match self.capture.rx.recv_timeout(Duration::from_millis(25)) {
+            Ok(chunk) => Ok(Some(chunk)),
+            Err(std::sync::mpsc::RecvTimeoutError::Timeout) => Ok(None),
+            Err(std::sync::mpsc::RecvTimeoutError::Disconnected) => {
+                let message = "Microphone capture disconnected unexpectedly".to_string();
+                let _ = self.status_channel.send(LiveStatusMessage::Error {
+                    session_id: self.session_id,
+                    message: message.clone(),
+                });
+                Err(message)
+            }
+        }
+    }
+
+    fn process_audio_chunk(&mut self, chunk: AudioChunk) -> Result<(), String> {
+        let mono = downmix_chunk(chunk.samples, chunk.channels as usize);
+        let resampler = match &mut self.state.resampler {
+            Some(resampler) => resampler,
+            None => {
+                self.state.resampler =
+                    Some(StreamingResampler::new(chunk.sample_rate).map_err(|e| e.to_string())?);
+                self.state.resampler.as_mut().expect("resampler just set")
+            }
+        };
+        let resampled = resampler.push_samples(&mono).map_err(|e| e.to_string())?;
+        append_resampled_audio(
+            &mut self.state.capture_buffer,
+            &mut self.state.wav_writer,
+            &resampled,
+            self.session_id,
+            &self.status_channel,
+        );
+        Ok(())
+    }
+
+    fn drop_pending_overflow(&mut self) {
+        if self.state.inflight.is_none() || self.state.capture_buffer.len() <= MAX_PENDING_SAMPLES {
+            return;
+        }
+        let overflow = self.state.capture_buffer.len() - MAX_PENDING_SAMPLES;
+        self.state.capture_buffer.drain(..overflow);
+        self.state.buffer_start_sample = self
+            .state
+            .buffer_start_sample
+            .saturating_add(overflow as u64);
+        self.state.dropped_audio_ms = self
+            .state
+            .dropped_audio_ms
+            .saturating_add((overflow as u64 * 1000) / WHISPER_SAMPLE_RATE as u64);
+        let _ = self.status_channel.send(LiveStatusMessage::Overload {
+            session_id: self.session_id,
+            dropped_audio_ms: self.state.dropped_audio_ms,
+            message: "Kon dropped older audio to keep live dictation responsive".into(),
+        });
+    }
+
+    fn flush_tail_if_stopping(&mut self) -> Result<(), String> {
+        if !self.stopping() || self.state.resampler_flushed {
+            return Ok(());
+        }
+        if let Some(resampler) = &mut self.state.resampler {
+            let tail = resampler.flush().map_err(|e| e.to_string())?;
+            append_resampled_audio(
+                &mut self.state.capture_buffer,
+                &mut self.state.wav_writer,
+                &tail,
+                self.session_id,
+                &self.status_channel,
+            );
+        }
+        self.flush_wav_header();
+        self.state.resampler_flushed = true;
+        Ok(())
+    }
+
+    fn flush_wav_header(&mut self) {
+        let Some(writer) = self.state.wav_writer.as_mut() else {
+            return;
+        };
+        if let Err(e) = writer.flush() {
+            let _ = self.status_channel.send(LiveStatusMessage::Warning {
+                session_id: self.session_id,
+                message: format!("WAV flush failed near session end: {e}"),
+            });
+        }
+    }
+
+    fn dispatch_inference_if_ready(&mut self) -> bool {
+        if self.state.inflight.is_some() {
+            return false;
+        }
+        let stopping = self.stopping();
+        if let Some(task) = maybe_dispatch_chunk(
+            &self.engine,
+            &self.config,
+            &mut self.state.capture_buffer,
+            &mut self.state.buffer_start_sample,
+            &mut self.state.chunk_id,
+            stopping,
+            &self.status_channel,
+            self.session_id,
+        ) {
+            self.state.inflight = Some(task);
+            return true;
+        }
+        false
+    }
+
+    fn stopping(&self) -> bool {
+        self.stop_flag.load(Ordering::Relaxed)
+    }
+
+    fn should_exit_loop(&self) -> bool {
+        self.stopping() && self.state.resampler_flushed && self.state.inflight.is_none()
+    }
+
+    fn drain_inference(&mut self) -> Result<(), String> {
+        while self.state.inflight.is_some() {
+            self.poll_inference()?;
+            thread::sleep(Duration::from_millis(10));
+        }
+        Ok(())
+    }
+
+    fn finish(mut self) -> Result<LiveSessionSummary, String> {
+        let audio_path = finalize_wav_writer(
+            self.state.wav_writer.take(),
+            self.audio_path.as_ref(),
+            self.session_id,
+            &self.status_channel,
+        );
+        Ok(LiveSessionSummary {
+            session_id: self.session_id,
+            dropped_audio_ms: self.state.dropped_audio_ms,
+            audio_path,
+        })
+    }
+}
+
 struct InferenceTask {
     chunk_id: u32,
     chunk_start_sample: u64,
@@ -198,6 +488,7 @@ pub async fn start_live_transcription_session(
     result_channel: Channel<LiveResultMessage>,
     status_channel: Channel<LiveStatusMessage>,
 ) -> Result<StartLiveTranscriptionResponse, String> {
+    let _lifecycle = live_state.lifecycle.lock().await;
     {
         let running = live_state.running.lock().unwrap();
         if running.is_some() {
@@ -227,11 +518,8 @@ pub async fn start_live_transcription_session(
     // `TranscriptionOptions` construction (see `maybe_dispatch_chunk`) picks
     // up profile fallback + vocabulary injection without further plumbing.
     let request_prompt = config.initial_prompt.clone().unwrap_or_default();
-    config.initial_prompt = build_initial_prompt(
-        &request_prompt,
-        &profile.initial_prompt,
-        &profile_terms,
-    );
+    config.initial_prompt =
+        build_initial_prompt(&request_prompt, &profile.initial_prompt, &profile_terms);
 
     let model_id = config
         .model_id
@@ -258,7 +546,10 @@ pub async fn start_live_transcription_session(
     // for save_audio=true and silently dropping the recording would
     // surprise them worse.
     let audio_path = if config.save_audio {
-        Some(resolve_recording_path(&app, config.output_folder.as_deref())?)
+        Some(resolve_recording_path(
+            &app,
+            config.output_folder.as_deref(),
+        )?)
     } else {
         None
     };
@@ -299,6 +590,7 @@ pub async fn stop_live_transcription_session(
     live_state: tauri::State<'_, LiveTranscriptionState>,
     session_id: u64,
 ) -> Result<StopLiveTranscriptionResponse, String> {
+    let _lifecycle = live_state.lifecycle.lock().await;
     let running = live_state.running.lock().unwrap().take();
     let Some(running) = running else {
         return Err("No live transcription session is running".into());
@@ -360,203 +652,54 @@ fn run_live_session(
     // lifetime to the session — when the function returns, the Drop
     // impl lifts it. Item #9 in docs/whisper-ecosystem/brief.md.
     let _power_guard = PowerAssertion::begin("kon live dictation session");
+    LiveSessionRuntime::new(
+        session_id,
+        engine,
+        config,
+        audio_path,
+        dictionary_terms,
+        result_channel,
+        status_channel,
+        stop_flag,
+    )?
+    .run()
+}
 
-    let (mut capture, rx) = match config.microphone_device.as_deref() {
-        Some(name) if !name.is_empty() => MicrophoneCapture::start_with_device(name),
-        _ => MicrophoneCapture::start(),
-    }
-    .map_err(|e| e.to_string())?;
-    // Drain runtime stream errors into the status channel so the user
-    // gets a toast when the device disconnects mid-recording instead of
-    // silently producing empty transcripts. The `_capture` binding keeps
-    // the cpal stream alive for the duration of the session.
-    let mic_error_rx = capture.take_error_rx();
-    let _capture = capture;
-
-    let mut resampler: Option<StreamingResampler> = None;
-    let mut capture_buffer: Vec<f32> = Vec::new();
-
-    // Progressive WAV writer (brief item #19). Sample rate comes from
-    // the loaded backend's capabilities (#13 wiring) so a future
-    // non-16kHz backend records at its native rate without further
-    // plumbing. The writer flushes its header every ~500 ms, so the
-    // file on disk is a playable WAV even if the process is killed.
+fn open_wav_writer(
+    engine: &Arc<LocalEngine>,
+    audio_path: Option<&PathBuf>,
+    session_id: u64,
+    status_channel: &Channel<LiveStatusMessage>,
+) -> Option<WavWriter> {
     let sample_rate = engine
         .capabilities()
         .map(|c| c.sample_rate)
         .unwrap_or(WHISPER_SAMPLE_RATE);
-    let mut wav_writer: Option<WavWriter> = match audio_path.as_ref() {
-        Some(path) => match WavWriter::create(path, sample_rate, 1) {
-            Ok(w) => Some(w),
-            Err(e) => {
-                let _ = status_channel.send(LiveStatusMessage::Warning {
-                    session_id,
-                    message: format!(
-                        "Failed to open audio recording file ({}); transcription will continue without saving audio.",
-                        e
-                    ),
-                });
-                None
-            }
-        },
-        None => None,
-    };
-    // `reported_audio_path` is decided at end-of-session based on
-    // whether the writer finalised successfully, not at open time.
-    // This way a writer that dies mid-session (append error clearing
-    // wav_writer, or finalise returning Err) does not leak a stale
-    // path back to the frontend that might point to a file whose
-    // header is out of sync with its data chunk.
-
-    let mut buffer_start_sample: u64 = 0;
-    let mut dropped_audio_ms: u64 = 0;
-    let mut chunk_id: u32 = 0;
-    let mut inflight: Option<InferenceTask> = None;
-    let mut resampler_flushed = false;
-    let mut recent_segments: Vec<RecentTranscriptSegment> = Vec::new();
-
-    loop {
-        if let Some(_done) = poll_inference(
-            &mut inflight,
-            session_id,
-            &config,
-            &mut recent_segments,
-            &dictionary_terms,
-            &result_channel,
-            &status_channel,
-        )? {}
-
-        // Surface any cpal runtime errors as warnings. Non-fatal: a hard
-        // disconnect will also drop the audio sender and be caught by
-        // the `Disconnected` arm below. This lets the user see a toast
-        // even when cpal recovers without tearing the stream down.
-        if let Some(err_rx) = &mic_error_rx {
-            while let Ok(err) = err_rx.try_recv() {
-                let _ = status_channel.send(LiveStatusMessage::Warning {
-                    session_id,
-                    message: format!(
-                        "Microphone '{}' reported an error: {}",
-                        err.device_name, err.message
-                    ),
-                });
-            }
-        }
-
-        match rx.recv_timeout(Duration::from_millis(25)) {
-            Ok(chunk) => {
-                let mono = downmix_chunk(chunk.samples, chunk.channels as usize);
-                let resampler = match &mut resampler {
-                    Some(resampler) => resampler,
-                    None => {
-                        resampler = Some(
-                            StreamingResampler::new(chunk.sample_rate)
-                                .map_err(|e| e.to_string())?,
-                        );
-                        resampler.as_mut().expect("resampler just set")
-                    }
-                };
-
-                let resampled = resampler.push_samples(&mono).map_err(|e| e.to_string())?;
-                append_resampled_audio(
-                    &mut capture_buffer,
-                    &mut wav_writer,
-                    &resampled,
-                    session_id,
-                    &status_channel,
-                );
-            }
-            Err(std::sync::mpsc::RecvTimeoutError::Timeout) => {}
-            Err(std::sync::mpsc::RecvTimeoutError::Disconnected) => {
-                let message = "Microphone capture disconnected unexpectedly".to_string();
-                let _ = status_channel.send(LiveStatusMessage::Error {
-                    session_id,
-                    message: message.clone(),
-                });
-                return Err(message);
-            }
-        }
-
-        if inflight.is_some() && capture_buffer.len() > MAX_PENDING_SAMPLES {
-            let overflow = capture_buffer.len() - MAX_PENDING_SAMPLES;
-            capture_buffer.drain(..overflow);
-            buffer_start_sample = buffer_start_sample.saturating_add(overflow as u64);
-            dropped_audio_ms = dropped_audio_ms
-                .saturating_add((overflow as u64 * 1000) / WHISPER_SAMPLE_RATE as u64);
-            let _ = status_channel.send(LiveStatusMessage::Overload {
+    let path = audio_path?;
+    match WavWriter::create(path, sample_rate, 1) {
+        Ok(writer) => Some(writer),
+        Err(e) => {
+            let _ = status_channel.send(LiveStatusMessage::Warning {
                 session_id,
-                dropped_audio_ms,
-                message: "Kon dropped older audio to keep live dictation responsive".into(),
+                message: format!(
+                    "Failed to open audio recording file ({}); transcription will continue without saving audio.",
+                    e
+                ),
             });
-        }
-
-        let stopping = stop_flag.load(Ordering::Relaxed);
-        if stopping && !resampler_flushed {
-            if let Some(resampler) = &mut resampler {
-                let tail = resampler.flush().map_err(|e| e.to_string())?;
-                append_resampled_audio(
-                    &mut capture_buffer,
-                    &mut wav_writer,
-                    &tail,
-                    session_id,
-                    &status_channel,
-                );
-            }
-            resampler_flushed = true;
-            // Final flush for the WAV header so the last chunk's header
-            // update is on disk before we drop into the inference drain.
-            if let Some(writer) = wav_writer.as_mut() {
-                if let Err(e) = writer.flush() {
-                    let _ = status_channel.send(LiveStatusMessage::Warning {
-                        session_id,
-                        message: format!("WAV flush failed near session end: {e}"),
-                    });
-                }
-            }
-        }
-
-        if inflight.is_none() {
-            if let Some(task) = maybe_dispatch_chunk(
-                &engine,
-                &config,
-                &mut capture_buffer,
-                &mut buffer_start_sample,
-                &mut chunk_id,
-                stopping,
-                &status_channel,
-                session_id,
-            ) {
-                inflight = Some(task);
-                continue;
-            }
-
-            if stopping && resampler_flushed {
-                break;
-            }
+            None
         }
     }
+}
 
-    while inflight.is_some() {
-        poll_inference(
-            &mut inflight,
-            session_id,
-            &config,
-            &mut recent_segments,
-            &dictionary_terms,
-            &result_channel,
-            &status_channel,
-        )?;
-        thread::sleep(Duration::from_millis(10));
-    }
-
-    // Finalise the progressive WAV writer and decide whether to
-    // report a path to the frontend. Only a clean finalise produces a
-    // reported path: a writer that died mid-session (wav_writer was
-    // already None) or a finalise that itself errored both yield
-    // `None`, so `StopLiveTranscriptionResponse.audio_path` reflects
-    // "recording is known-good" rather than "recording was attempted".
-    let audio_path = match wav_writer.take() {
+fn finalize_wav_writer(
+    wav_writer: Option<WavWriter>,
+    audio_path: Option<&PathBuf>,
+    session_id: u64,
+    status_channel: &Channel<LiveStatusMessage>,
+) -> Option<String> {
+    match wav_writer {
         Some(writer) => match writer.finalize() {
-            Ok(()) => audio_path.as_ref().map(|p| p.to_string_lossy().to_string()),
+            Ok(()) => audio_path.map(|path| path.to_string_lossy().to_string()),
             Err(e) => {
                 let _ = status_channel.send(LiveStatusMessage::Warning {
                     session_id,
@@ -568,13 +711,7 @@ fn run_live_session(
             }
         },
         None => None,
-    };
-
-    Ok(LiveSessionSummary {
-        session_id,
-        dropped_audio_ms,
-        audio_path,
-    })
+    }
 }
 
 fn append_resampled_audio(
@@ -719,6 +856,7 @@ fn maybe_dispatch_chunk(
 
 fn poll_inference(
     inflight: &mut Option<InferenceTask>,
+    result_listener_lost: &mut bool,
     session_id: u64,
     config: &StartLiveTranscriptionConfig,
     recent_segments: &mut Vec<RecentTranscriptSegment>,
@@ -761,22 +899,30 @@ fn poll_inference(
             );
             let segment_count = segments.len();
             let delivered_segments = segments.clone();
-
-            result_channel
-                .send(LiveResultMessage {
-                    session_id,
-                    chunk_id: task.chunk_id,
-                    chunk_start_secs,
-                    duration: task.duration_secs,
-                    language: timed.transcript.language().to_string(),
-                    inference_ms: timed.inference_ms,
-                    segments,
-                    raw_text,
-                })
-                .map_err(|e| e.to_string())?;
+            let result_message = LiveResultMessage {
+                session_id,
+                chunk_id: task.chunk_id,
+                chunk_start_secs,
+                duration: task.duration_secs,
+                language: timed.transcript.language().to_string(),
+                inference_ms: timed.inference_ms,
+                segments,
+                raw_text,
+            };
+            let delivered = emit_live_result(
+                result_channel,
+                status_channel,
+                result_listener_lost,
+                &result_message,
+            );
             remember_recent_segments(recent_segments, &delivered_segments, chunk_start_secs);
             eprintln!(
-                "[live] session {session_id}: delivered chunk {} with {} segments in {}ms{}",
+                "[live] session {session_id}: {} chunk {} with {} segments in {}ms{}",
+                if delivered {
+                    "delivered"
+                } else {
+                    "processed without listener for"
+                },
                 task.chunk_id,
                 segment_count,
                 timed.inference_ms,
@@ -813,6 +959,33 @@ fn poll_inference(
     }
 }
 
+fn emit_live_result(
+    result_channel: &Channel<LiveResultMessage>,
+    status_channel: &Channel<LiveStatusMessage>,
+    result_listener_lost: &mut bool,
+    result_message: &LiveResultMessage,
+) -> bool {
+    if *result_listener_lost {
+        return false;
+    }
+
+    match result_channel.send(result_message.clone()) {
+        Ok(()) => true,
+        Err(err) => {
+            *result_listener_lost = true;
+            eprintln!(
+                "[live] session {}: result listener unavailable on chunk {}: {}; continuing without live updates",
+                result_message.session_id, result_message.chunk_id, err
+            );
+            let _ = status_channel.send(LiveStatusMessage::Warning {
+                session_id: result_message.session_id,
+                message: "Live preview disconnected; transcription will continue in the background until you stop the session.".into(),
+            });
+            false
+        }
+    }
+}
+
 fn trim_overlap_segments(segments: &mut Vec<Segment>, trim_before_secs: f64) {
     if trim_before_secs <= 0.0 {
         return;
@@ -1150,6 +1323,82 @@ fn downmix_chunk(samples: Vec<f32>, channels: usize) -> Vec<f32> {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use tauri::ipc::InvokeResponseBody;
+
+    fn noop_status_channel() -> Channel<LiveStatusMessage> {
+        Channel::new(|_| Ok(()))
+    }
+
+    fn collecting_status_channel(payloads: Arc<Mutex<Vec<String>>>) -> Channel<LiveStatusMessage> {
+        Channel::new(move |body| {
+            if let InvokeResponseBody::Json(json) = body {
+                payloads.lock().unwrap().push(json);
+            }
+            Ok(())
+        })
+    }
+
+    fn dummy_running_session(
+        id: u64,
+        release_join: Option<Arc<tokio::sync::Notify>>,
+    ) -> RunningLiveSession {
+        let stop_flag = Arc::new(AtomicBool::new(false));
+        let handle = tokio::spawn(async move {
+            if let Some(notify) = release_join {
+                notify.notified().await;
+            }
+            Ok(LiveSessionSummary {
+                session_id: id,
+                dropped_audio_ms: 0,
+                audio_path: None,
+            })
+        });
+        RunningLiveSession {
+            id,
+            stop_flag,
+            handle,
+            status_channel: noop_status_channel(),
+        }
+    }
+
+    async fn test_begin_session_start(
+        live_state: Arc<LiveTranscriptionState>,
+        session_id: u64,
+        release_setup: Option<Arc<tokio::sync::Notify>>,
+    ) -> Result<u64, String> {
+        let _lifecycle = live_state.lifecycle.lock().await;
+        {
+            let running = live_state.running.lock().unwrap();
+            if running.is_some() {
+                return Err("A live transcription session is already running".into());
+            }
+        }
+        if let Some(notify) = release_setup {
+            notify.notified().await;
+        }
+        *live_state.running.lock().unwrap() = Some(dummy_running_session(session_id, None));
+        Ok(session_id)
+    }
+
+    async fn test_stop_session(
+        live_state: Arc<LiveTranscriptionState>,
+        session_id: u64,
+    ) -> Result<LiveSessionSummary, String> {
+        let _lifecycle = live_state.lifecycle.lock().await;
+        let running = live_state.running.lock().unwrap().take();
+        let Some(running) = running else {
+            return Err("No live transcription session is running".into());
+        };
+        if running.id != session_id {
+            *live_state.running.lock().unwrap() = Some(running);
+            return Err(format!("Session {session_id} is not active"));
+        }
+        running.stop_flag.store(true, Ordering::Relaxed);
+        running
+            .handle
+            .await
+            .map_err(|e| format!("Live session task failed: {e}"))?
+    }
 
     fn segment(start: f64, end: f64, text: &str) -> Segment {
         Segment {
@@ -1256,4 +1505,157 @@ mod tests {
         assert_eq!(decision.speech_window_count, 3);
         assert_eq!(decision.max_consecutive_speech_windows, 3);
     }
+
+    #[test]
+    fn result_listener_loss_is_warned_once_and_not_treated_as_inference_failure() {
+        let statuses = Arc::new(Mutex::new(Vec::new()));
+        let status_channel = collecting_status_channel(statuses.clone());
+        let result_channel = Channel::new(|_| Err(tauri::Error::FailedToReceiveMessage));
+        let config = StartLiveTranscriptionConfig {
+            engine: "whisper".into(),
+            model_id: None,
+            language: Some("en".into()),
+            initial_prompt: None,
+            save_audio: false,
+            output_folder: None,
+            remove_fillers: false,
+            british_english: false,
+            anti_hallucination: false,
+            format_mode: "Raw".into(),
+            microphone_device: None,
+            profile_id: None,
+        };
+        let mut recent_segments = Vec::new();
+        let mut result_listener_lost = false;
+
+        let (tx1, rx1) = std::sync::mpsc::channel();
+        tx1.send(Ok(kon_transcription::TimedTranscript {
+            transcript: kon_core::types::Transcript::new(
+                vec![segment(0.0, 0.8, "first chunk")],
+                "en".into(),
+                0.8,
+            ),
+            inference_ms: 12,
+        }))
+        .unwrap();
+        let mut inflight = Some(InferenceTask {
+            chunk_id: 1,
+            chunk_start_sample: 0,
+            trim_before_secs: 0.0,
+            duration_secs: 0.8,
+            rx: rx1,
+        });
+
+        let first = poll_inference(
+            &mut inflight,
+            &mut result_listener_lost,
+            77,
+            &config,
+            &mut recent_segments,
+            &[],
+            &result_channel,
+            &status_channel,
+        )
+        .unwrap();
+
+        assert_eq!(first, Some(true));
+        assert!(result_listener_lost);
+        assert!(inflight.is_none());
+        assert_eq!(recent_segments.len(), 1);
+        let warning_count_after_first = statuses.lock().unwrap().len();
+        assert_eq!(warning_count_after_first, 1);
+        assert!(
+            statuses.lock().unwrap()[0].contains("Live preview disconnected"),
+            "expected a warning about background continuation after listener loss"
+        );
+
+        let (tx2, rx2) = std::sync::mpsc::channel();
+        tx2.send(Ok(kon_transcription::TimedTranscript {
+            transcript: kon_core::types::Transcript::new(
+                vec![segment(0.0, 0.9, "second chunk")],
+                "en".into(),
+                0.9,
+            ),
+            inference_ms: 14,
+        }))
+        .unwrap();
+        inflight = Some(InferenceTask {
+            chunk_id: 2,
+            chunk_start_sample: 16_000,
+            trim_before_secs: 0.0,
+            duration_secs: 0.9,
+            rx: rx2,
+        });
+
+        let second = poll_inference(
+            &mut inflight,
+            &mut result_listener_lost,
+            77,
+            &config,
+            &mut recent_segments,
+            &[],
+            &result_channel,
+            &status_channel,
+        )
+        .unwrap();
+
+        assert_eq!(second, Some(true));
+        assert!(inflight.is_none());
+        assert_eq!(recent_segments.len(), 2);
+        assert_eq!(
+            statuses.lock().unwrap().len(),
+            warning_count_after_first,
+            "listener-loss warning should only be emitted once"
+        );
+    }
+
+    #[tokio::test]
+    async fn concurrent_starts_allow_only_one_session_to_claim_the_slot() {
+        let live_state = Arc::new(LiveTranscriptionState::default());
+        let release_setup = Arc::new(tokio::sync::Notify::new());
+
+        let first = tokio::spawn(test_begin_session_start(
+            live_state.clone(),
+            1,
+            Some(release_setup.clone()),
+        ));
+        tokio::time::sleep(Duration::from_millis(20)).await;
+
+        let second = tokio::spawn(test_begin_session_start(live_state.clone(), 2, None));
+        tokio::time::sleep(Duration::from_millis(20)).await;
+        assert!(
+            !second.is_finished(),
+            "second start should wait on the lifecycle lock"
+        );
+
+        release_setup.notify_one();
+
+        assert_eq!(first.await.unwrap().unwrap(), 1);
+        let err = second.await.unwrap().unwrap_err();
+        assert_eq!(err, "A live transcription session is already running");
+    }
+
+    #[tokio::test]
+    async fn start_waits_for_stop_to_finish_joining_before_reusing_slot() {
+        let live_state = Arc::new(LiveTranscriptionState::default());
+        let release_join = Arc::new(tokio::sync::Notify::new());
+        *live_state.running.lock().unwrap() =
+            Some(dummy_running_session(7, Some(release_join.clone())));
+
+        let stop = tokio::spawn(test_stop_session(live_state.clone(), 7));
+        tokio::time::sleep(Duration::from_millis(20)).await;
+
+        let start = tokio::spawn(test_begin_session_start(live_state.clone(), 8, None));
+        tokio::time::sleep(Duration::from_millis(20)).await;
+        assert!(
+            !start.is_finished(),
+            "new start should block until stop finishes joining the old worker"
+        );
+
+        release_join.notify_one();
+
+        let summary = stop.await.unwrap().unwrap();
+        assert_eq!(summary.session_id, 7);
+        assert_eq!(start.await.unwrap().unwrap(), 8);
+    }
 }

src-tauri/src/commands/models.rs

@@ -8,10 +8,10 @@ use kon_core::constants::WHISPER_SAMPLE_RATE;
 use kon_core::hardware::{self, CpuFeatures};
 use kon_core::model_registry::{self, Engine, LanguageSupport, ModelEntry};
 use kon_core::types::{AudioSamples, ModelId, TranscriptionOptions};
-use kon_transcription::model_manager;
-use kon_transcription::{load_parakeet, LocalEngine, Transcriber};
 #[cfg(feature = "whisper")]
 use kon_transcription::load_whisper;
+use kon_transcription::model_manager;
+use kon_transcription::{load_parakeet, LocalEngine, Transcriber};
 
 /// Map legacy size strings to ModelId.
 fn whisper_model_id(size: &str) -> ModelId {
@@ -73,9 +73,7 @@ fn model_capability(
     }
 }
 
-pub fn load_model_from_disk(
-    model_id: &ModelId,
-) -> Result<Box<dyn Transcriber + Send>, String> {
+pub fn load_model_from_disk(model_id: &ModelId) -> Result<Box<dyn Transcriber + Send>, String> {
     let entry =
         model_registry::find_model(model_id).ok_or_else(|| format!("Unknown model: {model_id}"))?;
 
@@ -205,8 +203,7 @@ pub fn prewarm_default_model(whisper_engine: Arc<LocalEngine>) {
                 // latency instead of the ~4–5s cold-start documented in
                 // ufal/whisper_streaming #96 and #135. Silence returns
                 // empty segments — the *work* is the context allocation.
-                let silence =
-                    AudioSamples::mono_16khz(vec![0.0_f32; WHISPER_SAMPLE_RATE as usize]);
+                let silence = AudioSamples::mono_16khz(vec![0.0_f32; WHISPER_SAMPLE_RATE as usize]);
                 let options = TranscriptionOptions::default();
                 match whisper_engine.transcribe_sync(&silence, &options) {
                     Ok(_) => eprintln!("[startup] Whisper warm-up inference complete"),
@@ -379,11 +376,7 @@ fn supported_accelerators() -> Vec<String> {
     } else {
         AcceleratorTarget::Other
     };
-    compose_accelerators(
-        cfg!(feature = "whisper"),
-        vulkan_loader_available(),
-        target,
-    )
+    compose_accelerators(cfg!(feature = "whisper"), vulkan_loader_available(), target)
 }
 
 /// Report which backend whisper.cpp was actually able to initialise
@@ -405,8 +398,7 @@ pub fn detect_active_compute_device() -> ActiveComputeDevice {
             kind: "cpu".into(),
             label: "CPU (fallback)".into(),
             reason: Some(
-                "MoltenVK / Vulkan loader not found — install the Vulkan SDK runtime."
-                    .into(),
+                "MoltenVK / Vulkan loader not found — install the Vulkan SDK runtime.".into(),
             ),
         };
     }

src-tauri/src/commands/paste.rs

@@ -396,7 +396,11 @@ fn detect_focused_window_class_macos() -> Option<String> {
         return None;
     }
     let name = String::from_utf8_lossy(&output.stdout).trim().to_string();
-    if name.is_empty() { None } else { Some(name) }
+    if name.is_empty() {
+        None
+    } else {
+        Some(name)
+    }
 }
 
 #[cfg(target_os = "windows")]
@@ -421,7 +425,11 @@ fn detect_focused_window_class_windows() -> Option<String> {
         return None;
     }
     let name = String::from_utf8_lossy(&output.stdout).trim().to_string();
-    if name.is_empty() { None } else { Some(name) }
+    if name.is_empty() {
+        None
+    } else {
+        Some(name)
+    }
 }
 
 fn trigger_paste_keystroke() -> Result<String, String> {
@@ -473,7 +481,10 @@ fn trigger_undo_keystroke() -> Result<String, String> {
 }
 
 #[cfg(target_os = "linux")]
-fn linux_paste(xdg_session_type: Option<&str>, wayland_display_set: bool) -> Result<String, String> {
+fn linux_paste(
+    xdg_session_type: Option<&str>,
+    wayland_display_set: bool,
+) -> Result<String, String> {
     for tool in pick_linux_backend_order(xdg_session_type, wayland_display_set) {
         match run_linux_tool(tool) {
             Ok(()) => return Ok(tool.to_string()),

src-tauri/src/commands/power.rs

@@ -21,7 +21,17 @@
 //! may still decide to idle us. We log when that happens so the
 //! diagnostics bundle has a breadcrumb.
 
+use std::collections::HashMap;
 use std::sync::atomic::{AtomicUsize, Ordering};
+use std::sync::{Mutex, OnceLock};
+
+#[derive(Debug, Clone)]
+pub struct PowerAssertionSnapshot {
+    pub id: usize,
+    pub reason: &'static str,
+    pub backend: &'static str,
+    pub acquired: bool,
+}
 
 /// Handle for a single power assertion. Dropping it releases the
 /// assertion. Holders are expected to keep it alive in a field for
@@ -32,12 +42,30 @@ pub struct PowerAssertion {
     #[allow(dead_code)]
     id: usize,
     reason: &'static str,
+    backend: &'static str,
+    acquired: bool,
     #[cfg(target_os = "macos")]
     activity: Option<objc_bridge::ActivityHandle>,
 }
 
 static NEXT_ID: AtomicUsize = AtomicUsize::new(1);
 
+fn assertion_registry() -> &'static Mutex<HashMap<usize, PowerAssertionSnapshot>> {
+    static REGISTRY: OnceLock<Mutex<HashMap<usize, PowerAssertionSnapshot>>> = OnceLock::new();
+    REGISTRY.get_or_init(|| Mutex::new(HashMap::new()))
+}
+
+pub fn active_assertions_snapshot() -> Vec<PowerAssertionSnapshot> {
+    let mut snapshots = assertion_registry()
+        .lock()
+        .unwrap()
+        .values()
+        .cloned()
+        .collect::<Vec<_>>();
+    snapshots.sort_by_key(|snapshot| snapshot.id);
+    snapshots
+}
+
 impl PowerAssertion {
     /// Begin a power assertion for the given reason. On macOS this
     /// pins beginActivityWithOptions; on Linux/Windows it logs only
@@ -47,12 +75,16 @@ impl PowerAssertion {
 
         #[cfg(target_os = "macos")]
         let activity = objc_bridge::begin_activity(reason).ok();
+        #[cfg(target_os = "macos")]
+        let backend = "macos";
+        #[cfg(target_os = "macos")]
+        let acquired = activity.is_some();
 
         #[cfg(target_os = "macos")]
-        if activity.is_none() {
-            eprintln!(
-                "[power] macOS App Nap guard could not begin activity for reason '{reason}'"
-            );
+        if acquired {
+            eprintln!("[power] began macOS App Nap guard #{id} for reason '{reason}'");
+        } else {
+            eprintln!("[power] macOS App Nap guard could not begin activity for reason '{reason}'");
         }
 
         #[cfg(not(target_os = "macos"))]
@@ -63,9 +95,26 @@ impl PowerAssertion {
             let _ = reason;
         }
 
+        #[cfg(not(target_os = "macos"))]
+        let backend = "noop";
+        #[cfg(not(target_os = "macos"))]
+        let acquired = false;
+
+        assertion_registry().lock().unwrap().insert(
+            id,
+            PowerAssertionSnapshot {
+                id,
+                reason,
+                backend,
+                acquired,
+            },
+        );
+
         Self {
             id,
             reason,
+            backend,
+            acquired,
             #[cfg(target_os = "macos")]
             activity,
         }
@@ -77,64 +126,83 @@ impl Drop for PowerAssertion {
         #[cfg(target_os = "macos")]
         if let Some(handle) = self.activity.take() {
             objc_bridge::end_activity(handle);
+            eprintln!(
+                "[power] ended macOS App Nap guard #{} for reason '{}'",
+                self.id, self.reason
+            );
         }
+        assertion_registry().lock().unwrap().remove(&self.id);
         let _ = (self.reason, self.id);
+        let _ = (self.backend, self.acquired);
     }
 }
 
 #[cfg(target_os = "macos")]
 mod objc_bridge {
-    //! Placeholder for the NSProcessInfo App-Nap bridge.
-    //!
-    //! A proper implementation calls:
-    //!   `NSProcessInfo *info = [NSProcessInfo processInfo];`
-    //!   `id activity = [info beginActivityWithOptions:
-    //!        (NSActivityUserInitiated | NSActivityLatencyCritical)
-    //!        reason:reasonNSString];`
-    //! and retains the returned object until `end_activity`.
-    //!
-    //! This workstream ships the PowerAssertion RAII guard + wiring
-    //! so `commands/live.rs` and `commands/llm.rs` can adopt it today
-    //! (matters on macOS, no-op elsewhere). The actual `objc2` bridge
-    //! lands in a follow-up commit that can introduce `objc2` +
-    //! `objc2-foundation` without touching the rest of the workspace
-    //! in the same change.
-    //!
-    //! Until then, `begin_activity` returns Err; callers (`begin()`)
-    //! log a warning but keep running, so recording continues to work
-    //! as today — the gap is just the App-Nap protection, not the
-    //! recording itself.
+    use objc2::rc::Retained;
+    use objc2::runtime::ProtocolObject;
+    use objc2_foundation::{NSActivityOptions, NSObjectProtocol, NSProcessInfo, NSString};
 
     pub struct ActivityHandle {
-        #[allow(dead_code)]
-        retained: *mut std::ffi::c_void,
+        activity: Retained<ProtocolObject<dyn NSObjectProtocol>>,
     }
 
-    // SAFETY: The pointer is opaque to Rust; Foundation manages its
-    // lifetime via retain/release. We never dereference it directly.
     unsafe impl Send for ActivityHandle {}
 
-    pub fn begin_activity(_reason: &str) -> Result<ActivityHandle, String> {
-        Err("macOS App Nap bridge not yet wired — objc2 integration tracked for a follow-up".into())
+    pub fn begin_activity(reason: &str) -> Result<ActivityHandle, String> {
+        let process_info = NSProcessInfo::processInfo();
+        let reason = NSString::from_str(reason);
+        let options = NSActivityOptions::UserInitiated | NSActivityOptions::LatencyCritical;
+        let activity = process_info.beginActivityWithOptions_reason(options, &reason);
+        Ok(ActivityHandle { activity })
     }
 
-    pub fn end_activity(_handle: ActivityHandle) {}
+    pub fn end_activity(handle: ActivityHandle) {
+        let process_info = NSProcessInfo::processInfo();
+        unsafe {
+            process_info.endActivity(&handle.activity);
+        }
+    }
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
+    use std::sync::{Mutex, MutexGuard, OnceLock};
+
+    fn power_test_guard() -> MutexGuard<'static, ()> {
+        static TEST_GUARD: OnceLock<Mutex<()>> = OnceLock::new();
+        TEST_GUARD.get_or_init(|| Mutex::new(())).lock().unwrap()
+    }
+
+    fn clear_assertion_registry() {
+        assertion_registry().lock().unwrap().clear();
+    }
 
     #[test]
     fn power_assertion_is_a_no_op_drop() {
+        let _guard = power_test_guard();
+        clear_assertion_registry();
         let guard = PowerAssertion::begin("test-reason");
+        let snapshots = active_assertions_snapshot();
+        assert!(snapshots.iter().any(|snapshot| snapshot.id == guard.id));
         drop(guard);
+        assert!(active_assertions_snapshot().is_empty());
     }
 
     #[test]
     fn multiple_assertions_get_unique_ids() {
+        let _guard = power_test_guard();
+        clear_assertion_registry();
         let a = PowerAssertion::begin("a");
         let b = PowerAssertion::begin("b");
         assert_ne!(a.id, b.id);
+        let snapshots = active_assertions_snapshot();
+        assert_eq!(snapshots.len(), 2);
+        assert_eq!(snapshots[0].reason, "a");
+        assert_eq!(snapshots[1].reason, "b");
+        drop(a);
+        drop(b);
+        assert!(active_assertions_snapshot().is_empty());
     }
 }

src-tauri/src/lib.rs

@@ -74,8 +74,10 @@ async fn save_preferences(
 /// known crashes that the HANDOVER documents working around with a manual
 /// env-var prefix:
 ///
-///     env GDK_BACKEND=x11 WINIT_UNIX_BACKEND=x11 \
-///         WEBKIT_DISABLE_DMABUF_RENDERER=1 npm run tauri dev
+/// ```sh
+/// env GDK_BACKEND=x11 WINIT_UNIX_BACKEND=x11 \
+///     WEBKIT_DISABLE_DMABUF_RENDERER=1 npm run tauri dev
+/// ```
 ///
 /// Detect the Wayland session at startup and apply the env vars before
 /// anything else loads, so users do not need to remember the prefix and