v1.3.0: Bedrock translator refactor, usage metrics, session restore fixes, and predefined rules

Major changes:

- **Bedrock translator architecture**: Extract orchestration logic from `impl.rs` into
  a dedicated `translator.rs` module. Rename `convert_request.rs` → `request_translator.rs`
  and `stream.rs` → `response_translator.rs` for clarity. Remove `tool_docs.rs` (inlined).
  Remove `fallback_to_warp` setting and server fallback path — Bedrock is now the sole backend.

- **Unknown tool handling**: The response translator now detects hallucinated/unknown tool
  calls from the model and synthesizes error tool_results so the conversation doesn't
  deadlock waiting for a result that will never come.

- **Usage display overhaul**: Replace credit-based usage display with detailed token metrics
  showing context window %, cache hit rate (read/write/miss), and estimated cost in dollars.
  Add `total_input_tokens`, `total_cache_read_tokens`, `total_cache_write_tokens`, and
  `cache_miss_tokens` accessors to `AIConversation`.

- **Predefined rules system**: Add `predefined_rules.rs` with 11 system-defined behavioral
  rules that are auto-seeded on first launch. Add "Add Predefined Rules" button to the
  Rules UI for re-adding them later. Track seeding state via `has_seeded_predefined_rules`
  setting.

- **Session restore improvements**: Rename database file from `warp.sqlite` to
  `galaxy.sqlite` with automatic migration from both same-directory and state_dir legacy
  paths. Improve CWD persistence by falling back to `session_startup_path` for agent-mode
  and fresh tabs. Add extensive session-save/restore logging.

- **Shell bootstrap rebrand**: Rename `WARP_INITIAL_WORKING_DIR` environment variable to
  `GALAXY_INITIAL_WORKING_DIR` across bash, zsh, and fish bootstrap scripts.

- **Model defaults**: Change default Bedrock model from Opus 4.7 to Opus 4.6.
  Add `context_window_for_model()` helper with model-aware context sizes.
  Remove `is_bedrock_model()` (no longer needed without server fallback).

- **User query persistence**: The response translator now emits a `UserQuery` proto message
  at stream start so the user's prompt persists across sessions for conversation titles.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

app/src/ai/bedrock/request_translator_tests.rs

@@ -0,0 +1,47 @@
+use serde_json::json;
+
+use crate::ai::bedrock::convert::{ContentPart, ConversationMessage, MessageContent, MessageRole};
+use super::sanitize_messages_for_bedrock;
+
+#[test]
+fn test_sanitize_messages_prepends_synthetic_tool_result_before_existing_user_text() {
+    let tool_use_id = "tooluse_Pzmn1QfoWgJsA8sb4RHTM3".to_string();
+    let existing_user_text = "What happened?".to_string();
+
+    let mut messages = vec![
+        ConversationMessage {
+            role: MessageRole::User,
+            content: MessageContent::Text("Run a command.".to_string()),
+        },
+        ConversationMessage {
+            role: MessageRole::Assistant,
+            content: MessageContent::ToolUse {
+                tool_use_id: tool_use_id.clone(),
+                name: "run_shell_command".to_string(),
+                input: json!({ "command": "ls" }),
+            },
+        },
+        ConversationMessage {
+            role: MessageRole::User,
+            content: MessageContent::Text(existing_user_text.clone()),
+        },
+    ];
+
+    sanitize_messages_for_bedrock(&mut messages);
+
+    assert_eq!(messages.len(), 3);
+
+    let parts = match &messages[2].content {
+        MessageContent::MultiPart(parts) => parts,
+        other => panic!("Expected MultiPart content, got: {:?}", other),
+    };
+
+    assert_eq!(parts.len(), 2);
+    assert!(
+        matches!(&parts[0], ContentPart::ToolResult { tool_use_id: id, .. } if id == &tool_use_id)
+    );
+    assert!(matches!(
+        &parts[1],
+        ContentPart::Text(text) if text == &existing_user_text
+    ));
+}