Acceptance Criteria:\n- web.search proxies Ollama Cloud's /api/web_search via the configured provider endpoint\n- Tool is only registered when remote search is enabled and the cloud provider is active\n- Consent prompts, docs, and MCP tooling no longer reference DuckDuckGo or expose web_search_detailed
Test Notes:\n- cargo check
Acceptance Criteria:\n- header shows hourly/weekly usage with colored thresholds\n- :limits command prints persisted usage data and quotas\n- token usage survives restarts and emits 80%/95% toasts
Test Notes:\n- cargo test -p owlen-core usage
Acceptance Criteria:\n- tool descriptors from MCP are forwarded to Ollama chat requests\n- models advertise tool support when metadata or heuristics imply function calling\n- chat responses include provider metadata with final token metrics
Test Notes:\n- cargo test -p owlen-core providers::ollama::tests::prepare_chat_request_serializes_tool_descriptors\n- cargo test -p owlen-core providers::ollama::tests::convert_model_marks_tool_capability\n- cargo test -p owlen-core providers::ollama::tests::convert_response_attaches_provider_metadata
Acceptance Criteria:\n- streaming chunks retain leading whitespace and indentation\n- end-of-stream metadata is still propagated\n- malformed frames emit defensive logging without crashing
Test Notes:\n- cargo test -p owlen-providers
- Introduce `StreamingMessageState` to track full text, last tool calls, and completion.
- Add `StreamDiff`, `TextDelta`, and `TextDeltaKind` for describing incremental changes.
- SessionController now maintains a `stream_states` map keyed by response IDs.
- `apply_stream_chunk` uses the new state to emit append/replace text deltas and tool‑call updates, handling final chunks and cleanup.
- `Conversation` gains `set_stream_content` to replace streaming content and manage metadata.
- Ensure stream state is cleared on cancel, conversation reset, and controller clear.
Replaces the original overview with a comprehensive execution plan for Owlen v0.2, including:
- Provider health checks and resilient model listing for Ollama and Ollama Cloud
- Cloud key‑gating, rate‑limit handling, and usage tracking
- Multi‑provider model registry and UI aggregation
- Session pipeline refactor for tool calls and partial updates
- Robust streaming JSON parser
- UI header displaying context usage percentages
- Token usage tracker with hourly/weekly limits and toasts
- New web.search tool wrapper and related commands
- Expanded command set (`:provider`, `:model`, `:limits`, `:web`) and config sections
- Additional documentation, testing guidelines, and release notes for v0.2.
- Introduce built‑in Emacs keymap (`keymap_emacs.toml`) alongside existing Vim layout.
- Add `ui.keymap_profile` and `ui.keymap_path` configuration options; persist profile changes via `:keymap` command.
- Expose `KeymapProfile` enum (Vim, Emacs, Custom) and integrate it throughout state, UI rendering, and help overlay.
- Extend command registry with `keymap.set_vim` and `keymap.set_emacs` to allow profile switching.
- Update help overlay, command specs, and README to reflect new keybindings and profile commands.
- Adjust `Keymap::load` to honor preferred profile, custom paths, and fallback logic.
- Extend event handling to include `MouseEvent` and expose it via a new `Event::Mouse` variant.
- Introduce `LayoutSnapshot` to capture the geometry of UI panels each render cycle.
- Store the latest layout snapshot in `ChatApp` for mouse region lookup.
- Implement mouse click and scroll handling across panels (file tree, thinking, actions, code, model info, chat, input, etc.).
- Add utility functions for region detection, cursor placement from mouse position, and scrolling logic.
- Update UI rendering to populate the layout snapshot with panel rectangles.
Update pkgver in PKGBUILD, version badge in README, and workspace package version in Cargo.toml. Add changelog entry for 0.1.11 reflecting the metadata bump.
- New test suite in `crates/owlen-tui/tests` covering generation orchestration, message variant round‑trip, and background worker status updates.
- Extend `model_picker` to filter models by matching keywords against capabilities as well as provider names.
- Update `state_tests` to assert that suggestion lists are non‑empty instead of checking prefix matches.
- Re‑export `background_worker` from `app::mod.rs` for external consumption.
- Introduce `MockProvider` with configurable models, health status, generation handlers, and error simulation.
- Add common test utilities and integration tests covering provider registration, model aggregation, request routing, error handling, and health refresh.
- Add `MessageState` trait defining UI reaction callbacks for generation lifecycle, model updates, provider status, resize, and tick events.
- Implement `App::handle_message` to route `AppMessage` variants to the provided `MessageState` and determine exit condition.
- Add `handler.rs` module with the trait and dispatch logic; re-export `MessageState` in `app/mod.rs`.
- Extend `ActiveGeneration` with a public `request_id` getter and clean up dead code annotations.
- Implement empty `MessageState` for `ChatApp` to integrate UI handling.
- Add `log` crate dependency for warning messages.
Added `widgets::model_picker` containing the full model picker rendering logic and moved related helper functions there. Updated `ui.rs` to use `render_model_picker` and removed the now‑duplicate model selector implementation. This cleanly separates UI concerns and improves code reuse.
Introduce a `worker` module with `background_worker` that periodically refreshes provider health and emits status updates via the app's message channel. Add `spawn_background_worker` method to `App` for launching the worker as a Tokio task.
Introduce `App` with provider manager, unbounded message channel, and active generation tracking.
Add `AppMessage` enum covering UI events, generation lifecycle (start, chunk, complete, error), model refresh, and provider status updates.
Implement `start_generation` to spawn asynchronous generation tasks, stream results, handle errors, and abort any previous generation.
Expose the new module via `pub mod app` in the crate root.
Introduce `OllamaCloudProvider` that resolves the API key from configuration or the `OLLAMA_CLOUD_API_KEY` environment variable, constructs provider metadata (including timeout as numeric), and maps auth errors to `ProviderStatus::RequiresSetup`. Export the new provider in the `ollama` module. Add shared HTTP error mapping utilities (`map_http_error`, `truncated_body`) and update local provider metadata to store timeout as a number.
Introduce `OllamaLocalProvider` for communicating with a local Ollama daemon, including health checks, model listing, and stream generation. Export the provider in the Ollama module. Extend `OllamaClient` to accept an optional request timeout and apply it to the underlying HTTP client configuration.
- Introduce `owlen-providers` crate with Cargo.toml and lib entry.
- Expose `OllamaClient` handling HTTP communication, health checks, model listing, and streaming generation.
- Implement request building, endpoint handling, and error mapping.
- Parse Ollama tags response and generation stream lines into core types.
- Add shared module re-exports for easy integration with the provider layer.
- Introduce `ProviderManager` for registering providers, routing generate calls, listing models, and refreshing health in parallel.
- Maintain a status cache to expose the last known health of each provider.
- Update `provider` module to re‑export the new manager alongside existing types.
