chore(release): prepare v0.8.45

CHANGELOG.md

@@ -7,6 +7,72 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.8.45] - 2026-05-25
+
+### Added
+
+- **RLM session objects.** `rlm_open` can now load `session://` refs,
+  exposing the active prompt, history, and session data as symbolic objects
+  inside RLM REPLs (#2047).
+- **Deterministic whale-species sub-agent names.** Sub-agents now get stable,
+  human-readable whale-species nicknames (e.g. "Beluga", "Orca") while
+  preserving the raw agent ID in the popup (#2035, #2016).
+- **`/balance` command scaffold.** Registered the `/balance` slash command
+  as a placeholder for future provider billing queries (#2035, #2019).
+- **Readable `/restore` snapshot labels.** Snapshot labels now include the
+  originating user prompt so restore listings are easier to identify. Thanks
+  @idling11 (#2111).
+- **Sidebar hover tooltips.** Truncated Work and Tasks sidebar lines now expose
+  their full text on hover. Thanks @idling11 (#2110).
+
+### Changed
+
+- **AGENTS.md is now maintainer-local.** The project instructions file no
+  longer ships as a tracked repo file; it lives in maintainer-local ignored
+  state (#2047).
+
+### Fixed
+
+- **Sub-agent completion handoff compatibility.** Completion handoffs now use a
+  chat-template-safe role and emit before terminal updates, fixing strict
+  OpenAI-compatible/self-hosted backends and preserving transcript ordering.
+  Thanks @h3c-hexin and @cyq1017 (#2057, #2120).
+- **Self-hosted context budgeting.** Sub-500K self-hosted model windows now keep
+  a usable input budget instead of disabling preflight compaction after output
+  reservation underflow. Thanks @h3c-hexin (#2060).
+- **Goal prompts start actionable.** Goal-start prompts now open in an
+  actionable state instead of requiring an extra nudge. Thanks @cyq1017
+  (#2097).
+- **Composer session title display.** The composer chrome shows the current
+  session title again and avoids grayscale luma overflow in debug builds.
+  Thanks @wdw8276 (#2108).
+- **Approval prompts use a one-step confirmation flow.** Enter now commits the
+  selected approval option directly, destructive warnings remain visible, and
+  abort cancels the active turn instead of only denying the current tool call.
+  Thanks @reidliu41 (#2143).
+- **Model picker selection survives Esc.** Dismissing the model picker with Esc
+  no longer loses the highlighted selection. Thanks @reidliu41 (#2056).
+- **Slash recovery no longer restores command tails in the composer.**
+  Resuming a session or recovering from a crash no longer leaves stale
+  slash-command text (e.g. `/sessions`) in the composer input (#2047, #2032).
+- **Remembered tool approvals now update the live active turn.**
+  When the "remember" checkbox is set on an approval dialog, the active
+  turn's auto-approve flag flips immediately instead of waiting for the
+  next turn. Thanks @gaord (#2047, #2041).
+- **YAML block scalars in SKILL.md frontmatter.** Multi-line descriptions
+  using `>` or `|` indicators are now parsed correctly — folded block
+  scalars join non-empty lines with spaces, literal scalars preserve
+  newlines, and all three chomping modes (strip/clip/keep) are supported.
+  Thanks @zlh124 (#1908, #1907).
+- **User messages highlighted in the transcript.** User-authored messages
+  now render with a full-row background in the live TUI transcript, making
+  it easier to scan prior turns. Assistant and system messages are
+  unaffected. Thanks @reidliu41 (#1995, #1672).
+- **Cancellable `list_dir` and `file_search`.** Long directory walks and
+  file searches now respond to user cancel/stop requests with a 30-second
+  fallback timeout, preventing the TUI from hanging on deep or slow
+  filesystems (#2035).
+
 ## [0.8.44] - 2026-05-24
 
 ### Added
@@ -4806,7 +4872,8 @@ Welcome — and thank you.
 - Hooks system and config profiles
 - Example skills and launch assets
 
-[Unreleased]: https://github.com/Hmbown/CodeWhale/compare/v0.8.44...HEAD
+[Unreleased]: https://github.com/Hmbown/CodeWhale/compare/v0.8.45...HEAD
+[0.8.45]: https://github.com/Hmbown/CodeWhale/compare/v0.8.44...v0.8.45
 [0.8.44]: https://github.com/Hmbown/CodeWhale/compare/v0.8.43...v0.8.44
 [0.8.43]: https://github.com/Hmbown/CodeWhale/compare/v0.8.42...v0.8.43
 [0.8.42]: https://github.com/Hmbown/CodeWhale/compare/v0.8.41...v0.8.42

Cargo.toml

@@ -19,7 +19,7 @@ default-members = ["crates/cli", "crates/app-server", "crates/tui"]
 resolver = "2"
 
 [workspace.package]
-version = "0.8.44"
+version = "0.8.45"
 edition = "2024"
 # Rust 1.88 stabilized `let_chains` in `if`/`while` conditions, which the
 # codebase relies on extensively. Cargo enforces this so users on older

README.md

@@ -279,9 +279,13 @@ codewhale --provider novita --model deepseek/deepseek-v4-pro
 codewhale auth set --provider fireworks --api-key "YOUR_FIREWORKS_API_KEY"
 codewhale --provider fireworks --model deepseek-v4-pro
 
+# Moonshot/Kimi
+codewhale auth set --provider moonshot --api-key "YOUR_MOONSHOT_OR_KIMI_API_KEY"
+codewhale --provider moonshot --model kimi-k2.6
+
 # Generic OpenAI-compatible endpoint
 codewhale auth set --provider openai --api-key "YOUR_OPENAI_COMPATIBLE_API_KEY"
-OPENAI_BASE_URL="https://openai-compatible.example/v4" codewhale --provider openai --model glm-5
+OPENAI_BASE_URL="https://openai-compatible.example/v4" codewhale --provider openai --model deepseek-v4-pro
 
 # Self-hosted SGLang
 SGLANG_BASE_URL="http://localhost:30000/v1" codewhale --provider sglang --model deepseek-v4-flash
@@ -429,11 +433,6 @@ ACP workflows outside the built-in Zed slice.
 | `@path` | Attach file/directory context in composer |
 | `↑` (at composer start) | Select attachment row for removal |
 
-Voice input is available from the command palette (`Ctrl+K`, then search
-`Voice input`) after configuring `voice_input_command`; the helper
-records/transcribes audio, CodeWhale shows a listening status while it runs, and
-the final transcript is inserted into the composer for editing.
-
 Full shortcut catalog: [docs/KEYBINDINGS.md](docs/KEYBINDINGS.md).
 
 ---
@@ -467,14 +466,15 @@ Key environment variables:
 | `DEEPSEEK_HTTP_HEADERS` | Optional custom model request headers, e.g. `X-Model-Provider-Id=your-model-provider` |
 | `DEEPSEEK_MODEL` | Default model |
 | `DEEPSEEK_STREAM_IDLE_TIMEOUT_SECS` | Stream idle timeout in seconds, default `300`, clamped to `1..=3600` |
-| `DEEPSEEK_PROVIDER` | `codewhale` (default), `nvidia-nim`, `openai`, `atlascloud`, `wanjie-ark`, `openrouter`, `novita`, `fireworks`, `sglang`, `vllm`, `ollama` |
+| `DEEPSEEK_PROVIDER` | `codewhale` (default), `nvidia-nim`, `openai`, `atlascloud`, `wanjie-ark`, `openrouter`, `novita`, `fireworks`, `moonshot`, `sglang`, `vllm`, `ollama` |
 | `DEEPSEEK_PROFILE` | Config profile name |
 | `DEEPSEEK_MEMORY` | Set to `on` to enable user memory |
 | `DEEPSEEK_ALLOW_INSECURE_HTTP=1` | Allow non-local `http://` API base URLs on trusted networks |
-| `NVIDIA_API_KEY` / `OPENAI_API_KEY` / `ATLASCLOUD_API_KEY` / `WANJIE_ARK_API_KEY` / `OPENROUTER_API_KEY` / `NOVITA_API_KEY` / `FIREWORKS_API_KEY` / `SGLANG_API_KEY` / `VLLM_API_KEY` / `OLLAMA_API_KEY` | Provider auth |
+| `NVIDIA_API_KEY` / `OPENAI_API_KEY` / `ATLASCLOUD_API_KEY` / `WANJIE_ARK_API_KEY` / `OPENROUTER_API_KEY` / `NOVITA_API_KEY` / `FIREWORKS_API_KEY` / `MOONSHOT_API_KEY` / `KIMI_API_KEY` / `SGLANG_API_KEY` / `VLLM_API_KEY` / `OLLAMA_API_KEY` | Provider auth |
 | `OPENAI_BASE_URL` / `OPENAI_MODEL` | Generic OpenAI-compatible endpoint and model ID |
 | `ATLASCLOUD_BASE_URL` / `ATLASCLOUD_MODEL` | AtlasCloud endpoint and model override |
 | `WANJIE_ARK_BASE_URL` / `WANJIE_ARK_MODEL` | Wanjie Ark endpoint and model override |
+| `MOONSHOT_BASE_URL` / `KIMI_BASE_URL` / `MOONSHOT_MODEL` / `KIMI_MODEL` | Moonshot/Kimi endpoint and model override |
 | `OPENROUTER_BASE_URL` | OpenRouter endpoint override |
 | `NOVITA_BASE_URL` | Novita endpoint override |
 | `FIREWORKS_BASE_URL` | Fireworks endpoint override |
@@ -604,7 +604,7 @@ This project ships with help from a growing community of contributors:
 - **[zichen0116](https://github.com/zichen0116)** — CODE_OF_CONDUCT.md (#686)
 - **[dfwqdyl-ui](https://github.com/dfwqdyl-ui)** — model ID case-sensitivity compatibility report (#729)
 - **[Oliver-ZPLiu](https://github.com/Oliver-ZPLiu)** — stale `working...` state bug report, Windows clipboard fallback, MCP Streamable HTTP session fixes, and Homebrew tap automation (#738, #850, #1643, #1631)
-- **[reidliu41](https://github.com/reidliu41)** — resume hint, workspace trust persistence, Ollama provider support, thinking-block stream finalization, CI cache hardening, streaming wrap, DeepSeek model completions, and help picker selection polish (#863, #870, #921, #1078, #1603, #1628, #1601, #1964)
+- **[reidliu41](https://github.com/reidliu41)** — resume hint, workspace trust persistence, Ollama provider support, thinking-block stream finalization, CI cache hardening, streaming wrap, DeepSeek model completions, help picker selection polish, and transcript user-message highlighting (#863, #870, #921, #1078, #1603, #1628, #1601, #1964, #1995)
 - **[cyq1017](https://github.com/cyq1017)** — Unicode `git_status` paths, local/configured skill discovery, and mode-switch toast dedupe (#1953, #1956, #1957)
 - **[xieshutao](https://github.com/xieshutao)** — plain Markdown skill fallback (#869)
 - **[GK012](https://github.com/GK012)** — npm wrapper `--version` fallback (#885)
@@ -637,7 +637,7 @@ This project ships with help from a growing community of contributors:
 - **[mdrkrg](https://github.com/mdrkrg)** — first-run onboarding crash fix when the API key is missing (#1598)
 - **[Aitensa](https://github.com/Aitensa)** — CJK wrapping propagation for diff and pager output (#1622)
 - **[qiyan233](https://github.com/qiyan233)** — legacy DeepSeek CN provider alias compatibility (#1645)
-- **[zlh124](https://github.com/zlh124)** — WSL2/headless startup report and clipboard-init fix (#1772, #1773)
+- **[zlh124](https://github.com/zlh124)** — WSL2/headless startup report, clipboard-init fix, and YAML block-scalar frontmatter parsing (#1772, #1773, #1908)
 - **[aboimpinto](https://github.com/aboimpinto)** — Windows alt-screen logging, Home/End composer, and runtime log follow-ups (#1774, #1776, #1748, #1749, #1782, #1783)
 - **[LeoLin990405](https://github.com/LeoLin990405)** — provider model passthrough, reasoning replay, thinking-only turn, and Windows quoting fixes (#1740, #1743, #1742, #1744)
 - **[nightt5879](https://github.com/nightt5879)** — Ctrl+C prompt restore fix (#1764)
@@ -707,6 +707,7 @@ This project ships with help from a growing community of contributors:
 - **[xulongzhe](https://github.com/xulongzhe)** — issue-template and vision-boundary follow-ups (#1530, #1544)
 - **[YaYII](https://github.com/YaYII)** — trusted media path work (#1462)
 - **[47Cid](https://github.com/47Cid)** and **[Jafar Akhondali](https://github.com/JafarAkhondali)** — responsible security disclosures and hardening reports
+- **[gaord](https://github.com/gaord)** — approval-remember live-turn sync fix (#2041)
 
 ---
 

crates/agent/Cargo.toml

@@ -7,5 +7,5 @@ repository.workspace = true
 description = "Model/provider registry and fallback strategy for DeepSeek workspace architecture"
 
 [dependencies]
-codewhale-config = { path = "../config", version = "0.8.44" }
+codewhale-config = { path = "../config", version = "0.8.45" }
 serde.workspace = true

crates/agent/src/lib.rs

@@ -74,18 +74,18 @@ impl Default for ModelRegistry {
                 supports_reasoning: true,
             },
             ModelInfo {
-                id: "gpt-4.1".to_string(),
+                id: "deepseek-v4-pro".to_string(),
                 provider: ProviderKind::Openai,
-                aliases: vec!["gpt4.1".to_string(), "gpt-4o".to_string()],
+                aliases: vec!["openai-compatible-deepseek-v4-pro".to_string()],
                 supports_tools: true,
                 supports_reasoning: true,
             },
             ModelInfo {
-                id: "gpt-4.1-mini".to_string(),
+                id: "deepseek-v4-flash".to_string(),
                 provider: ProviderKind::Openai,
-                aliases: vec!["gpt-4o-mini".to_string()],
+                aliases: vec!["openai-compatible-deepseek-v4-flash".to_string()],
                 supports_tools: true,
-                supports_reasoning: false,
+                supports_reasoning: true,
             },
             ModelInfo {
                 id: "deepseek-reasoner".to_string(),

crates/app-server/Cargo.toml

@@ -10,16 +10,21 @@ description = "Codex-style app-server transport for DeepSeek workspace architect
 anyhow.workspace = true
 axum.workspace = true
 clap.workspace = true
-codewhale-agent = { path = "../agent", version = "0.8.44" }
-codewhale-config = { path = "../config", version = "0.8.44" }
-codewhale-core = { path = "../core", version = "0.8.44" }
-codewhale-execpolicy = { path = "../execpolicy", version = "0.8.44" }
-codewhale-hooks = { path = "../hooks", version = "0.8.44" }
-codewhale-mcp = { path = "../mcp", version = "0.8.44" }
-codewhale-protocol = { path = "../protocol", version = "0.8.44" }
-codewhale-state = { path = "../state", version = "0.8.44" }
-codewhale-tools = { path = "../tools", version = "0.8.44" }
+codewhale-agent = { path = "../agent", version = "0.8.45" }
+codewhale-config = { path = "../config", version = "0.8.45" }
+codewhale-core = { path = "../core", version = "0.8.45" }
+codewhale-execpolicy = { path = "../execpolicy", version = "0.8.45" }
+codewhale-hooks = { path = "../hooks", version = "0.8.45" }
+codewhale-mcp = { path = "../mcp", version = "0.8.45" }
+codewhale-protocol = { path = "../protocol", version = "0.8.45" }
+codewhale-state = { path = "../state", version = "0.8.45" }
+codewhale-tools = { path = "../tools", version = "0.8.45" }
 serde.workspace = true
 serde_json.workspace = true
 tokio.workspace = true
 tower-http.workspace = true
+uuid.workspace = true
+
+[dev-dependencies]
+tempfile = "3.16"
+tower = "0.5"