mirror of
https://github.com/tinyhumansai/openhuman.git
synced 2026-07-28 13:32:23 +00:00
01a948c18d2815e7cb68eaf910da8d1fbef3360a
464
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Steven EnamakelandGitHub
|
01a948c18d |
feat: tree summarizer uses local AI exclusively (#518)
* refactor: update module visibility and enhance summarization logic
- Changed the visibility of the `ollama_api` module to `pub(crate)` to restrict its access to the current crate, improving encapsulation.
- Refactored the `run_summarization` and `propagate_node` functions to pass the chat model ID from the configuration, ensuring consistent usage of the model across summarization tasks.
- Enhanced the `summarize_to_limit` function to accept the model parameter, allowing for more flexible and dynamic summarization based on the specified model.
- Updated the `create_provider` function to enforce the requirement of enabling local AI for the tree summarizer, ensuring proper configuration before execution.
* fix: update Ollama provider credential handling
- Changed the credential parameter in the `create_local_ai_provider` function from `None` to `Some("ollama")`, clarifying that while Ollama does not require authentication, a non-None credential is necessary for the provider's configuration.
* feat: add tree summarization script for memory namespaces
- Introduced a new script `tree-summarizer-run-all.sh` that automates the process of running tree summarization across all memory namespaces.
- The script discovers namespaces from the specified workspace and supports various commands including `run`, `status`, `query`, and `rebuild`.
- Enhanced error handling and logging for improved usability and debugging during summarization tasks.
* style: apply cargo fmt to tree summarizer
* refactor: improve argument handling and output summary in tree summarizer script
- Refactored the argument construction in `tree-summarizer-run-all.sh` to use an array for better handling of command-line arguments.
- Enhanced the output summary to provide a clearer report of succeeded and failed namespace processing.
- Updated the while loop to read from `NAMESPACES` directly, improving readability and efficiency.
* fix: address PR review — array args, subshell loop, retry wrapper, narrow export
- Script: use bash array for args instead of string to prevent word-splitting
- Script: use here-string loop so SUCCEEDED/FAILED propagate to parent shell
- ops.rs: wrap Ollama provider in ReliableProvider for retry/backoff
- local_ai/mod.rs: keep ollama_api private, re-export only OLLAMA_BASE_URL
|
||
|
Steven EnamakelandGitHub
|
172cd0da4c |
Fix stale voice server state between dictation sessions (#517)
* Fix stale voice server state between dictation sessions * Enhance audio capture and dictation listener tests - Added new test utilities in `audio_capture.rs` for handling recording results in tests. - Introduced multiple tests for audio processing functions, including handling silence and RMS calculations. - Updated `dictation_listener.rs` with tests for normalizing hotkey aliases and ensuring proper serialization of dictation events. - Improved overall test coverage and reliability for audio processing and dictation functionalities. * Refactor audio processing functions and enhance test coverage - Simplified the `from_test_result` function in `audio_capture.rs` by removing unnecessary line breaks. - Consolidated assertions in `server.rs` for better readability. - Introduced new functions in `streaming.rs` for decoding PCM16 LE frames and appending stream samples, improving audio processing logic. - Added tests for the new audio processing functions, ensuring robust validation of their behavior and enhancing overall test coverage. |
||
|
Steven EnamakelandGitHub
|
08178b5ff3 |
feat(composio): incremental sync with per-item persistence for Gmail and Notion (#519)
* feat(composio): implement incremental sync and state management for Gmail and Notion providers - Enhanced the Gmail and Notion providers to support incremental synchronization with per-item persistence, improving data handling efficiency. - Introduced a new `SyncState` module to manage persistent sync state, including cursor tracking, synced IDs, and daily request budget management. - Updated sync logic to load state from a KV store, check daily budget limits, and handle paginated API requests, ensuring robust data retrieval and deduplication. - Refactored existing sync methods to utilize the new state management, enhancing overall reliability and performance of the providers. - Improved documentation for the sync process and state management, clarifying the operational flow and usage of the new features. * refactor(composio): improve error handling and logging in Gmail and Notion providers - Enhanced error handling in the Gmail provider to format error messages more clearly during email fetching. - Streamlined debug logging in both Gmail and Notion providers to improve readability by consolidating multiline statements into single lines. - Refactored the `extract_page_title` function in the Notion provider for better clarity in property extraction logic. - Overall, these changes aim to enhance maintainability and improve the clarity of error reporting and logging across the providers. |
||
|
Steven EnamakelandGitHub
|
a115758c6c |
Improve local voice readiness and add Composio trigger history (#516)
* feat: enhance local AI asset state management and error handling - Updated the Home component to improve readiness checks for local AI assets, ensuring a more robust UI experience. - Refactored the LocalAiService to provide clearer state management for STT and TTS models, including handling on-demand downloads and error logging. - Enhanced the voice status function to accurately reflect the availability of transcription backends, improving overall system reliability. - Introduced warnings for on-demand model downloads to inform users about potential delays in functionality. * feat: implement polling for voice server status in OverlayApp - Added a polling mechanism to periodically check the voice server status every 2 seconds, ensuring the overlay remains in sync with the server state. - Introduced logic to activate or dismiss the speech-to-text (STT) mode based on the server's recording or transcribing state, enhancing user experience and responsiveness. - Utilized the existing `callCoreRpc` function to fetch server status, improving reliability in state management during brief disconnects or reconnections. * feat: refine prompt handling in LocalAiService - Updated the prompt construction logic in `LocalAiService` to enhance clarity and functionality. - When `no_think` is set, the system prompt now includes a directive for the model to respond with only the final answer, improving response accuracy. - Refactored the prompt and system parameters to ensure they are correctly formatted and passed to the `OllamaGenerateRequest`, enhancing overall request handling. * feat: enhance STT readiness checks in VoicePanel and useVoiceSkillStatus - Updated the STT readiness logic in `VoicePanel` to account for both 'ready' and 'ondemand' states, improving the accuracy of readiness assessments. - Refined the `useVoiceSkillStatus` hook to ensure it only blocks when the local AI's STT state is explicitly 'missing', enhancing overall system reliability and user experience. * feat(composio): implement ComposeIO trigger history component and hook - Added `ComposeioTriggerHistory` component to display a list of ComposeIO trigger events with formatted timestamps and payloads. - Introduced `useComposeioTriggerHistory` hook to manage fetching and state of trigger history entries, including error handling and loading states. - Updated `Webhooks` page to integrate the new component and hook, replacing previous webhook activity display with ComposeIO trigger history. - Created utility functions for formatting timestamps and payloads for better readability in the UI. - Established backend support for fetching trigger history through new Tauri commands, ensuring robust data handling and storage. * style: apply repo formatting fixes * feat: add fs2 dependency and enhance ComposeIO trigger history handling - Introduced the `fs2` crate to manage file locking, improving the reliability of file operations in the ComposeIO trigger history. - Updated `ComposioTriggerHistoryStore` to utilize exclusive file locks during archive writing, ensuring data integrity. - Enhanced error handling for file operations, providing clearer logging for failures related to file access and locking. - Refactored the initialization logic for global trigger history to prevent duplicate setups, improving overall stability. |
||
|
Steven EnamakelandGitHub
|
0a09d72677 |
feat: native mouse and keyboard control tools (#515)
* feat: add native computer control tools for keyboard and mouse - Introduced `ComputerControlConfig` to manage mouse and keyboard tool activation. - Implemented `KeyboardTool` and `MouseTool` for native input control using platform-native APIs. - Updated configuration schema to include computer control settings. - Enhanced tool registration logic to conditionally include mouse and keyboard tools based on user configuration. - Added comprehensive documentation and tests for new functionalities, ensuring robust integration and usability. * style: apply cargo fmt to computer control tools * fix: harden computer control tools — safe cleanup, strict validation, gate tests - keyboard hotkey: track pressed keys and always release in reverse on error (prevents stuck modifiers); validate modifier-first pattern (reject ["a","Ctrl"], ["Ctrl"], ["Ctrl","Shift"]) - mouse drag: guarantee button release via best-effort cleanup after press, even when move_mouse fails - mouse parse_button: return Result, reject unknown/non-string values instead of silently defaulting to left - mouse scroll: use i32::try_from instead of silent `as i32` truncation - Add debug logs on security block branches (can_act / record_action) - Add ops.rs regression tests for computer_control enabled/disabled gate |
||
|
Steven EnamakelandGitHub
|
ef9c117e9e |
test: expand agent harness coverage (#513)
* feat(tests): add comprehensive unit tests for hooks and memory context - Introduced a suite of tests for the `fire_hooks` function, ensuring that all hooks are dispatched even if one fails, enhancing reliability in the hook execution flow. - Added tests for the `sanitize_tool_output` function to validate the correct mapping of success and failure messages for various tool outputs. - Implemented a mock memory structure to facilitate testing of memory context building, ensuring that working memory is prioritized and deduplication occurs correctly. - Enhanced the `build_memory_context` function tests to verify filtering and truncation of memory entries, improving the robustness of memory management in the system. - Overall, these tests aim to strengthen the codebase by ensuring that critical functionalities related to hooks and memory context are thoroughly validated. * feat(tests): enhance unit tests for provider alias resolution and prompt options - Updated the `provider_alias_and_route_selection_round_trip` test to dynamically resolve the first provider from the registry, ensuring accurate alias resolution. - Added new tests for `DumpPromptOptions` and `ComposioStubTools`, validating default settings and expected tool names. - Introduced tests for rendering main agent dumps, ensuring tool instructions and skill counts are correctly included in the output. - Enhanced prompt handling tests to cover cache boundary extraction and subagent render options, improving overall test coverage and reliability. * feat(tests): enhance error handling and formatting in unit tests - Added new tests for `AgentError` variants to validate string formatting and error recovery from `anyhow`. - Improved formatting consistency in existing tests for better readability. - Enhanced the `sanitize_tool_output` test to ensure accurate mapping of success and failure messages. - Updated memory loader tests to enforce minimum limits and budget constraints, ensuring robust memory management. - Overall, these changes aim to strengthen the test suite by improving coverage and clarity in error handling scenarios. * feat(tests): add unit tests for tool filtering and subagent dump rendering - Introduced new tests to validate the filtering of tools based on named scopes and disallowed tools, ensuring correct tool selection in debug dumps. - Added tests for rendering subagent dumps, including handling file prompt fallbacks and missing files without panicking. - Enhanced the workspace prompt handling to prefer custom prompt locations, improving the flexibility and reliability of agent prompt rendering. - Overall, these additions strengthen the test suite by covering critical functionalities related to tool filtering and prompt rendering. * feat(tests): add comprehensive unit tests for memory loader and multimodal helpers - Introduced new tests for the memory loader to validate behavior when the header exceeds budget and when recall fails, ensuring robust memory management. - Added tests for multimodal helpers, covering image marker counting, payload extraction, and MIME type normalization, enhancing the reliability of multimodal interactions. - Overall, these additions strengthen the test suite by improving coverage and ensuring correct functionality in memory handling and multimodal processing. * feat(tests): add unit tests for tool execution and agent behavior - Introduced new tests for the `run_tool_call_loop` function, validating the rejection of vision markers for non-vision providers and ensuring correct streaming of final text chunks. - Added tests to verify that CLI-only tools are blocked in prompt mode and that native tool results are persisted as tool messages. - Enhanced the `Agent` class with tests for error handling and event publishing during single runs, ensuring robust agent behavior in various scenarios. - Overall, these additions strengthen the test suite by improving coverage and reliability in tool execution and agent interactions. * feat(tests): enhance tool execution and agent behavior tests - Added new tests for the `run_tool_call_loop` function, including scenarios for auto-approving supervised tools on non-CLI channels and handling unknown tools with default max iterations. - Introduced `ErrorResultTool` and `FailingTool` to simulate error conditions during tool execution, improving coverage of error handling in the agent. - Updated the `ScriptedProvider` to return results wrapped in `anyhow::Result`, ensuring consistent error handling across test cases. - Overall, these enhancements strengthen the test suite by validating tool execution paths and agent behavior under various conditions. * refactor(tests): improve test readability and structure - Enhanced formatting in various test cases for better clarity and consistency, including the use of line breaks and indentation. - Updated assertions to improve readability by aligning them with Rust's idiomatic style. - Overall, these changes aim to strengthen the test suite by making it more maintainable and easier to understand. * docs(agent): enhance module documentation for agent domain - Added comprehensive documentation to the `mod.rs` file, detailing the agent domain's purpose, key components, and their functionalities. - Improved clarity on how LLMs interact with the system, manage conversation history, and handle autonomous behaviors. - This update aims to enhance understanding and maintainability of the agent domain within the OpenHuman project. * docs(agent): improve documentation and formatting across multiple files - Enhanced comments and documentation in `dispatcher.rs`, `error.rs`, `hooks.rs`, and `harness/mod.rs` for better clarity and consistency. - Adjusted formatting in the `TurnContext` and `ToolCallRecord` structs to improve readability and understanding of their purpose and functionality. - Overall, these changes aim to strengthen the documentation and maintainability of the agent domain within the OpenHuman project. * feat(tests): add comprehensive tests for memory loader and agent behavior - Introduced new tests for the `DefaultMemoryLoader`, validating error propagation during primary recall failures and ensuring correct context emission when working memory is present. - Added tests to verify behavior when the working memory section exceeds budget constraints, enhancing memory management robustness. - Overall, these additions strengthen the test suite by improving coverage and reliability in memory handling and agent interactions. * refactor(tests): improve formatting and readability in memory loader tests - Reformatted the `load_context` calls in memory loader tests for better readability by chaining method calls. - Enhanced documentation comments in the `pformat.rs` file to clarify the purpose and functionality of functions. - Improved consistency in spacing and formatting across various sections of the codebase, including the `interrupt.rs` and `builder.rs` files. - Overall, these changes aim to enhance code clarity and maintainability within the test suite and related modules. * feat(tests): add new tests for self-healing interceptor and local AI provider - Introduced tests to validate the detection of missing commands in the `SelfHealingInterceptor`, ensuring proper handling of recognized and unrecognized patterns. - Added tests for the `ensure_polyfill_dir` method to confirm directory creation and path exposure. - Enhanced local AI provider tests to verify correct behavior when the service is ready and the appropriate tier is set, as well as ensuring local metadata is utilized during provider resolution. - Overall, these additions strengthen the test suite by improving coverage and reliability in self-healing and local AI functionalities. * refactor(tests): enhance test structure and external ID handling in escalation tests - Updated the `envelope` function to accept an `external_id` parameter, improving flexibility in test scenarios. - Modified various test cases to utilize specific external IDs, enhancing clarity and ensuring accurate event assertions. - Introduced a mutex lock in local AI tests to prevent race conditions, ensuring reliable test execution. - Overall, these changes improve the robustness and maintainability of the test suite for escalation and local AI functionalities. * refactor(tests): remove redundant test modules and improve test organization - Eliminated unused test modules from `hooks.rs`, `memory_loader.rs`, `fork_context.rs`, `interrupt.rs`, and `parse.rs` to streamline the codebase. - Enhanced overall test organization by consolidating relevant tests into appropriate files, improving maintainability and readability. - These changes aim to simplify the test structure and focus on active test cases, ensuring a cleaner and more efficient testing environment. * refactor(tests): improve test formatting and readability - Reformatted assertions in multiple test cases for better readability by aligning them with Rust's idiomatic style. - Enhanced the structure of test cases by using line breaks and consistent indentation, improving overall clarity. - These changes aim to strengthen the test suite by making it more maintainable and easier to understand. * refactor(api): improve string containment check and formatting in transcript handling - Updated the `key_bytes_from_string` function to use a more concise containment check for special characters. - Changed the message writing in the `write_transcript` function to utilize `writeln!` for better formatting. - Enhanced the condition in `latest_in_dir` to use `is_none_or` for improved readability and clarity. - These changes aim to streamline code and enhance maintainability across the API and transcript handling modules. * refactor(code): streamline function implementations and improve readability - Removed unnecessary whitespace in `run_voice_server_command` for cleaner code. - Simplified directory search logic in `bundled_openclaw_prompts_dir` by using `find` instead of a loop. - Updated `request_accessibility_access` to use direct references for keys and values, enhancing clarity. - Improved documentation formatting in `mod.rs` and `types.rs` for better consistency. - Refactored `Config` initialization in `load.rs` to use struct update syntax for clarity. - Added `#[allow(clippy::too_many_arguments)]` annotations in multiple functions to address linter warnings. - Enhanced type definitions and function signatures for better type safety and readability in various modules. - Overall, these changes aim to improve code maintainability and readability across the project. * chore(ci): update typecheck workflow and pre-push hooks to include clippy checks - Modified the GitHub Actions workflow to run clippy with warnings treated as errors for the `openhuman` package. - Enhanced the pre-push hook to include clippy checks, ensuring code quality before pushing changes. - Updated package.json to define a new script for running clippy, integrating it into the format check process. - These changes aim to improve code quality and maintainability by enforcing stricter linting rules. * refactor(api): simplify condition in key_bytes_from_string function - Streamlined the condition in the `key_bytes_from_string` function to improve readability by consolidating the if statement into a single line. - This change enhances code clarity while maintaining the original functionality of the key validation process. * chore(package): update format:check script to remove clippy integration - Modified the `format:check` script in `package.json` to exclude the clippy check, streamlining the formatting process. - This change simplifies the formatting workflow while maintaining the integrity of Rust formatting checks. * refactor(core): enhance documentation and structure in core modules - Improved documentation across various core functions, including `build_registered_controllers`, `run_from_cli_args`, and `dispatch`, to clarify their purpose and usage. - Streamlined comments to provide clearer guidance on the flow of operations and error handling. - Enhanced the structure of the `EventBus` and `NativeRegistry` to improve readability and maintainability. - Overall, these changes aim to improve code clarity and facilitate easier navigation and understanding of the core components. * refactor(core): reorganize imports in engine.rs for clarity - Adjusted the import statements in `engine.rs` to improve organization and readability. - Moved the macOS-specific import of `validate_focused_target` to a more appropriate location and ensured consistent ordering of imports. - These changes aim to enhance code clarity and maintainability within the core module. * refactor(core): enhance WebChannelEvent structure and documentation - Introduced a new `WebChannelEvent` struct to standardize event payloads for chat-related activities, including fields for event name, client ID, thread ID, request ID, and optional response details. - Improved documentation for the `attach_socketio` function, clarifying its role in setting up Socket.IO event handlers and the associated chat logic. - Removed unused structs and streamlined the event handling process to improve code clarity and maintainability across the core module. * refactor(core): streamline Socket.IO event handlers for clarity and consistency - Refactored the Socket.IO event handlers in `attach_socketio` to improve readability by standardizing the formatting and structure of the code. - Enhanced the organization of the event handling logic for `rpc:request`, `chat:start`, and `chat:cancel` events, making it easier to follow the flow of operations. - These changes aim to improve code maintainability and facilitate easier navigation within the Socket.IO integration. * feat(core): add new structs for Socket RPC and chat events - Introduced `SocketRpcRequest`, `ChatStartPayload`, and `ChatCancelPayload` structs to facilitate handling of Socket.IO events related to chat functionality. - These additions enhance the structure and clarity of the event payloads, improving the maintainability of the Socket.IO integration. * refactor(core): remove unused json_type_name function from socketio.rs - Eliminated the `json_type_name` function from `socketio.rs` as it was not utilized in the current codebase. - This change helps to clean up the code and improve maintainability by removing unnecessary functions. * chore(ci): update clippy command in typecheck workflow - Modified the clippy command in the GitHub Actions workflow to remove the `-D warnings` flag for the `openhuman` package, allowing warnings to be displayed without failing the build. - This change aims to improve the development experience by providing more flexibility during code analysis while still encouraging code quality. * chore(husky): remove clippy check from pre-push hook - Eliminated the clippy command from the pre-push hook to streamline the pre-push checks. - Updated the failure message to reflect the removal of clippy, focusing on format, lint, TypeScript, and Rust errors only. - This change simplifies the pre-push process while maintaining essential checks for code quality. * refactor(tests): add macOS-specific imports for enhanced test coverage - Introduced conditional imports for macOS in the tests module of `engine.rs` to support platform-specific functionality. - This change improves the test setup for macOS environments, ensuring compatibility and enhancing overall test coverage. * refactor(tests): update tool call execution in test cases - Modified the `execute_tool_call` method calls in multiple test cases to include a second parameter, improving the accuracy of the tests. - This change ensures that the tests reflect the latest method signature and enhances the reliability of the test outcomes. |
||
|
Steven EnamakelandGitHub
|
8635ac16c5 |
feat: real-time inference progress events for web channel (#514)
* feat(conversations): implement real-time inference status tracking - Added new event listeners for inference start, iteration start, subagent spawning, and completion to track the live state of chat interactions. - Introduced an `InferenceStatus` interface to manage the current phase and active tools/subagents for each thread. - Updated the UI to display inference status indicators, enhancing user experience during chat interactions. - Created a new `progress` module in the Rust backend to emit real-time progress events, allowing for better integration with the web channel. - Refactored the `subscribeChatEvents` function to include new event handlers for managing inference and subagent events, improving clarity and maintainability of the event handling logic. * style: fix formatting from pre-push hook * fix(test): read SSE events until chat_done instead of first event The e2e test expected `chat_done` as the first SSE event, but now real-time progress events (inference_start, iteration_start) are emitted before it. Use `read_sse_event_by_type` to skip progress events and wait for the terminal `chat_done` event. |
||
|
Steven EnamakelandGitHub
|
ace0006c85 |
feat: session transcripts for LLM KV cache stability (#512)
* feat(transcript): implement session transcript management for KV cache stability - Added support for session transcript persistence, allowing the exact `Vec<ChatMessage>` to be stored as human-readable `.md` files. - Introduced methods for loading previous transcripts to pre-populate messages for KV cache reuse, enhancing session continuity. - Updated `AgentBuilder` to include an agent definition name for transcript file naming. - Refactored `Agent` to handle transcript loading and persistence during session turns, ensuring byte-identical message handling across sessions. - Created a new `transcript.rs` module to encapsulate transcript-related functionality, improving code organization and maintainability. * feat(usage): enhance API response structure with usage and billing metadata - Added `usage` and `openhuman` fields to the `ApiChatResponse` struct to capture standard OpenAI usage metrics and OpenHuman backend metadata. - Introduced `ApiUsage`, `OpenHumanMeta`, and related structs to encapsulate detailed usage and billing information. - Updated `parse_native_response` and `extract_usage` methods to process and return usage data, improving the integration of usage tracking in chat responses. - Modified the `UsageInfo` struct in traits to include new fields for cached input tokens and charged amount, enhancing the overall usage reporting capabilities. * feat(provider): integrate usage extraction into OpenAiCompatibleProvider responses - Added usage extraction functionality to the `OpenAiCompatibleProvider`, enhancing the API response structure to include usage metrics. - Updated the `parse_native_response` method to utilize a new `wrap_message` function for improved testability and clarity in response handling. - Refactored tests to accommodate the new usage extraction logic, ensuring comprehensive coverage of the updated response structure. * feat(transcript): implement sub-agent transcript persistence and usage tracking - Added functionality to persist sub-agent conversation transcripts, enabling inspection for debugging and KV cache analysis. - Introduced a new `persist_subagent_transcript` function to handle transcript writing, including metadata for input/output tokens and charged amounts. - Updated the `Agent` implementation to accumulate usage statistics across iterations and include them in the session transcript. - Enhanced the `write_transcript` function to include additional metadata fields, improving the detail of stored transcripts. - Refactored tests to validate the new transcript persistence and usage tracking features, ensuring comprehensive coverage. * refactor(transcript): improve code readability and structure - Reformatted the `write_transcript` and `read_transcript` functions for better clarity by adjusting line breaks and indentation. - Enhanced the `parse_meta` function to improve readability by restructuring the `get` closure. - Updated test cases to maintain consistency with the new formatting, ensuring clarity in the test structure. - Overall, these changes aim to enhance code maintainability and readability without altering functionality. * fix(provider): return Result from parse_native_response, use Option<u64> for OpenHumanUsage fields - parse_native_response now returns Result and propagates an error when choices is empty instead of silently returning text: None - OpenHumanUsage token fields changed to Option<u64> so missing keys yield None and allow fallback to standard OpenAI usage block - extract_usage now logs which source (openhuman vs standard) provided token counts via structured tracing - run_inner_loop returns AggregatedUsage so subagent transcripts reflect real usage instead of zeros - Document escape_content/unescape_content edge case with pre-existing escape sequences |
||
|
Steven EnamakelandGitHub
|
1cb70e3234 |
feat: P-Format tool calls, user memory injection, planner upgrades (#511)
* feat(agent): introduce debug agent prompts script and CLI for prompt inspection
- Added `scripts/debug-agent-prompts.sh` to dump system prompts for built-in agents, facilitating prompt engineering reviews.
- Implemented `openhuman agent` CLI commands for inspecting agent definitions and rendering prompts.
- Updated `.gitignore` to exclude local prompt dumps and added version bump for `openhuman` to 0.52.5.
- Introduced `debug_dump` module for shared prompt rendering logic, enhancing debugging capabilities across the application.
* feat(pformat): introduce P-Format tool calls for efficient parameter handling
- Added a new module `pformat` to implement P-Format ("Parameter-Format") tool calls, which significantly reduce token usage in tool invocations.
- Updated the agent module to include the new `pformat` module.
- Enhanced the context management by integrating user memory summaries from the tree summarizer, optimizing the prompt rendering process.
- Introduced constants for user memory character limits to ensure efficient memory usage across namespaces.
- Implemented a new `UserMemorySection` in the prompt to display distilled long-term context, improving the agent's ability to leverage learned information during interactions.
- Refactored the tree summarizer store to collect root-level summaries with character caps, ensuring manageable context sizes in prompts.
* feat(dispatch): implement PFormatToolDispatcher for efficient tool call handling
- Introduced `PFormatToolDispatcher`, a new dispatcher that utilizes P-Format for compact tool call syntax, significantly reducing token usage during interactions.
- Updated the agent's session builder to support the new dispatcher, allowing for a seamless transition to P-Format as the default for text-based providers.
- Enhanced the prompt rendering process to accommodate P-Format, ensuring backward compatibility with existing JSON tool calls.
- Modified the context management to reflect the new tool call format, improving the overall efficiency of prompt generation and tool interaction.
- Added tests to validate the correct rendering of tool signatures in P-Format, ensuring that the new format is correctly integrated into the system.
* feat(tests): add comprehensive tests for PFormatToolDispatcher functionality
- Introduced multiple tests for the `PFormatToolDispatcher`, validating its ability to parse tool calls from both P-Format and JSON formats.
- Implemented tests to ensure correct handling of multiple tool call tags and the dispatcher’s fallback behavior to JSON when P-Format is ignored.
- Enhanced the `render_main_agent_dump` function to include the dispatcher instructions, ensuring accurate context for tool usage in debug outputs.
- Updated the tree summarizer tests to verify namespace filtering and summary collection with respect to character limits, improving overall test coverage and reliability.
* feat(prompt): enhance tool signature rendering with P-Format support
- Introduced a new function `render_pformat_signature_for_box_tool` to generate P-Format signatures for tools, improving consistency in tool call formatting.
- Updated the `render_subagent_system_prompt` function to utilize the new P-Format signatures, ensuring alignment with the main agent's tool call protocol.
- Enhanced documentation to clarify the use of P-Format in tool calls, including detailed instructions for argument handling and formatting within the tool use protocol.
* feat(planner): update agent configuration and enhance planning context
- Revised the `when_to_use` description to emphasize the agent's ability to gather real context through memory recall and web searches.
- Increased `max_iterations` from 5 to 8 to allow for more complex planning scenarios.
- Changed `omit_memory_context` to false, enabling the agent to utilize memory context during planning.
- Updated the tools list to include `memory_recall`, `memory_store`, `memory_forget`, and `web_search_tool`, enhancing the agent's capabilities for context gathering.
- Expanded the prompt documentation to instruct users on gathering context before planning, ensuring more informed and effective task decomposition.
* style: apply cargo fmt to new and modified files
* feat(debug): enhance error handling and logging in debug-agent-prompts and tool dispatching
- Added error handling for missing output directory in `debug-agent-prompts.sh`, ensuring clearer feedback for users.
- Introduced a verbose flag in `agent_cli.rs` to control logging output, improving usability during debugging.
- Refactored tool response parsing in `dispatcher.rs` to prefer p-format calls while maintaining compatibility with JSON, enhancing response handling.
- Updated session builder in `builder.rs` to finalize dispatcher selection after tool list preparation, ensuring accurate tool handling.
- Improved debug dump functionality in `debug_dump.rs` to clarify the context of the dump process, ensuring better understanding of the output.
- Enhanced prompt rendering functions to support explicit tool call formats, improving flexibility in subagent interactions.
* feat(cli, prompt): enhance logging and tool call format handling
- Added debug logging for the agent subcommand in `cli.rs`, improving traceability during command execution.
- Updated the `render_subagent_system_prompt_with_format` function in `prompt.rs` to support multiple tool call formats (P-Format, JSON, Native), ensuring consistent output and flexibility for subagent interactions.
- Refactored tool call protocol documentation to clarify usage across different formats, enhancing user understanding and implementation.
* fix: address PR review — 8 findings
1. scripts/debug-agent-prompts.sh: validate --out argument exists
2. agent_cli.rs: silence logger in run_list before Config::load_or_init
3. dispatcher.rs: per-tag p-format/JSON selection (no all-or-nothing)
4. builder.rs: move pformat_registry build after orchestrator tools
5. debug_dump.rs: fall back to bundled prompt location for File sources
6. store.rs: fix char/byte mixing in total_cap computations
7. prompt.rs: thread ToolCallFormat into render_subagent_system_prompt
8. cli.rs: add debug trace on agent dispatch + lower dispatcher log
|
||
|
Steven EnamakelandGitHub
|
4c195e984a |
feat(composio): native Rust providers for per-toolkit profile, sync, triggers (#509)
* chore(composio): update Composio version and enhance periodic sync functionality - Bump Composio version to 0.52.5 in Cargo.lock. - Introduce periodic synchronization for Composio connections, allowing for regular updates based on defined intervals. - Register both Composio trigger and connection created subscribers to handle events effectively. - Implement a new periodic sync scheduler that manages sync operations for active connections, improving data freshness and integration reliability. - Enhance Composio provider implementations to support user profile fetching and sync operations, ensuring seamless integration with the backend. * fix(composio): address review feedback on provider system - bus: poll list_connections with exponential backoff (500ms→4s, 60s cap) until the connection is observed in ACTIVE/CONNECTED before firing on_connection_created, replacing the fixed 2s sleep that raced the OAuth handoff. - ops: parse_sync_reason now returns Result and rejects unrecognized reason strings instead of silently coercing them to Manual; new unit tests cover the happy path and rejection cases. - periodic: add a static OnceLock guard inside start_periodic_sync so the scheduler is only spawned once even when both startup paths call into it. - gmail/providers: redact PII in tracing output — log has_email + email_domain instead of the raw address, and drop display_name + email from the default on_connection_created log. - notion: align the comment with the actual filter (recently-edited pages, databases intentionally excluded for snapshot size reasons). * feat(composio): enhance sync handling and periodic scheduler - Introduced `record_sync_success` function to track successful syncs for connections, preventing redundant re-firing by the periodic scheduler. - Updated `ComposioTriggerSubscriber` and `ComposioConnectionCreatedSubscriber` to utilize the new sync recording mechanism. - Refactored periodic sync logic to share a process-wide map for last successful sync timestamps, improving synchronization efficiency across event-driven and periodic paths. - Adjusted imports in `mod.rs` to include the new sync recording function. * fix(notion): improve error handling in snapshot persistence - Updated the error handling for the `persist_snapshot` function to enhance clarity in error messages, ensuring that failures are logged with specific context for easier debugging. |
||
|
Steven EnamakelandGitHub
|
658a75b39e |
feat(triage): reusable trigger triage agent (commit 1 of 3) (#510)
* feat(triage): implement trigger triage agent for external event classification - Introduced a new `trigger_triage` agent to classify incoming external triggers (e.g., Composio webhooks, cron jobs) and determine appropriate actions (drop, acknowledge, react, escalate). - Added `TriggerEvaluated`, `TriggerEscalated`, and `TriggerEscalationFailed` events to the event bus for tracking triage decisions. - Implemented a `TriggerEnvelope` structure to standardize the input for the triage pipeline, ensuring source-agnostic handling of triggers. - Developed a decision parser to interpret classifier outputs and enforce response contracts. - Enhanced the event bus with functions to publish triage-related events, improving observability and logging. - Updated the Cargo.lock to version 0.52.5 to reflect the new changes. * feat(triage): implement trigger triage agent for external event classification - Introduced a new `trigger_triage` agent to classify incoming external triggers (e.g., Composio webhooks, cron jobs) and determine appropriate actions (drop, acknowledge, react, escalate). - Added `TriggerEvaluated`, `TriggerEscalated`, and `TriggerEscalationFailed` events to the event bus for tracking triage decisions. - Implemented a structured decision parser and a triage pipeline that processes triggers and applies decisions based on the classifier's output. - Enhanced the Composio integration to utilize the new triage functionality, ensuring seamless handling of incoming events. - Updated tests to validate the new triage logic and ensure correct behavior across various scenarios. * feat(triage): enhance triage evaluation with retry logic and error handling - Introduced a configuration-based approach to resolve providers for triage turns, allowing for retries on local failures by falling back to remote providers. - Added a `TurnOutcomeFailure` struct to encapsulate recoverable errors during triage processing, enabling clearer error reporting and decision-making for retries. - Implemented caching for provider decisions to optimize performance and reduce redundant configuration loads. - Enhanced the `run_triage` function to handle local and remote execution paths, improving resilience against transient failures. - Updated the `resolve_provider` function to support both local and remote provider resolution based on configuration settings, ensuring flexibility in triage operations. - Improved logging for error scenarios to aid in debugging and monitoring triage outcomes. * refactor(triage): improve error handling and code formatting in evaluator and routing - Enhanced error handling in the `run_triage` function to improve clarity when both local and remote executions fail. - Refactored code formatting in the `cache_snapshot` and `decide_fresh` functions for better readability. - Updated test assertions for improved clarity and consistency in formatting, ensuring better maintainability. * feat(triage): local routing + real subagent escalation + trigger_reactor agent (commit 2 of 3) - Rewrite routing.rs with local-vs-remote provider resolution: LocalAiService adapter wrapping Ollama behind the Provider trait, ModelTier floor check (>= Ram4To8Gb), 60s decision cache with Local/Remote/Degraded states, and mark_degraded() for the retry path. - Add parse-failure / local-failure → remote retry in evaluator.rs: TurnOutcomeFailure wrapper distinguishes local vs remote errors; run_triage retries once on remote when used_local=true and marks the routing cache Degraded so subsequent triggers skip local. - Wire real escalation in escalation.rs via run_subagent: builds a full Agent from config, extracts a ParentExecutionContext from its accessors, installs it via with_parent_context, and calls run_subagent for react (trigger_reactor) / escalate (orchestrator). - New trigger_reactor built-in agent (agents/trigger_reactor/): narrow tool scope (memory_recall, memory_store, read_workspace_state, spawn_subagent), agentic model hint, max 6 iterations. - 33 triage tests passing (routing cache, tier scoring, retry path with stateful stub, local parse failure eligibility). * feat(triage): add triage_evaluate schema and handler for trigger evaluation - Introduced a new controller schema for `triage_evaluate`, enabling the trigger-triage classifier to process synthetic trigger payloads for testing and replay. - Implemented the corresponding handler to manage the evaluation process, returning parsed decisions and timing metadata. - Enhanced the input structure to include required and optional fields for comprehensive trigger evaluation, including support for dry runs. * feat(triage): expose RPC surface + default-on (commit 3 of 3) - Add `openhuman.agent_triage_evaluate` JSON-RPC method to agent/schemas.rs: accepts a synthetic trigger payload with an optional `dry_run` flag. When dry_run=true the decision is not acted on (no sub-agent dispatch). Canonical test/replay hook for exercising the triage pipeline without forging a Socket.IO webhook. - Flip the composio subscriber from opt-in (`OPENHUMAN_TRIGGER_TRIAGE_ENABLED`) to default-on with an opt-out escape hatch (`OPENHUMAN_TRIGGER_TRIAGE_DISABLED`). Every Composio trigger now flows through the triage pipeline unless the env var is explicitly set. - Update composio/bus.rs tests to match the new opt-out semantics. |
||
|
Steven EnamakelandGitHub
|
403f239ca5 |
refactor: remove QuickJS skills runtime (#508)
* refactor: remove quickjs skills runtime * style: apply repo formatting * refactor: clean up error reporting and connection handling - Removed the 'skill' source option from the error report structure to streamline error reporting. - Refactored the ConnectionsPanel component to simplify connection status badge rendering and improve clarity. - Updated the CronJobsPanel to enhance logging for cron job loading processes. - Adjusted SkillCard component to use a more consistent type for icons. - Deleted outdated end-to-end tests for Gmail and Notion skills, improving test suite maintainability. * fix: remove unnecessary ESLint disable comment in Conversations component - Cleaned up the Conversations component by removing the ESLint disable comment for exhaustive dependencies in the useEffect hook, improving code clarity and maintainability. * fix: remove unnecessary whitespace in Conversations component - Eliminated an extra line of whitespace in the Conversations component, enhancing code readability and maintainability. * refactor: streamline SkillCard imports for improved clarity - Combined import statements in the SkillCard component to enhance code readability and maintainability. |
||
|
Steven EnamakelandGitHub
|
759691e380 |
feat(composio): improve toolkit sync and connection handling (#507)
* Enhance release workflow with build target input and improved job structure - Added a new input parameter `build_target` to specify the environment (production or staging) for the release process. - Made `release_type` input optional with a default value of `patch`. - Refactored job names and dependencies to reflect the new build target logic, including conditional steps for production and staging environments. - Introduced a `resolve` step to determine build outputs based on the selected environment, enhancing the workflow's flexibility and clarity. - Updated the `create-release` job to depend on the new `prepare-build` job, ensuring proper execution flow based on the build target. * feat(composio): enhance Composio integration with toolkit management and testing - Added `KNOWN_COMPOSIO_TOOLKITS` constant to facilitate access to available toolkits. - Implemented unit tests for `useComposioIntegrations` to ensure correct behavior during toolkit and connection fetching, including error handling scenarios. - Updated `Skills` page to utilize the new `KNOWN_COMPOSIO_TOOLKITS` for improved toolkit display logic. - Refactored hooks to handle connection errors gracefully and maintain toolkit visibility. - Enhanced backend integration by updating Composio client configuration to streamline toolkit management. * refactor(dispatch): remove channel delivery instructions for Telegram - Deleted the `channel_delivery_instructions` function, which provided response guidelines for Telegram messages. This change simplifies the message processing logic in the `process_channel_message` function by eliminating unnecessary instructions, enhancing clarity and maintainability. * refactor(composio): simplify Composio client configuration and remove toggles - Updated the `build_composio_client` function to remove unnecessary configuration checks, as Composio is always enabled when the user is signed in. - Revised the `resolve_client` function to clarify error handling related to user authentication. - Streamlined the `IntegrationsConfig` structure by removing toggles for Composio and related backend settings, ensuring a consistent configuration approach across integrations. - Adjusted tests to reflect the removal of integration toggles and focus on core API key usage. * refactor(composio): remove composio disabled state and improve error handling - Eliminated the `disabled` state from the `useComposioIntegrations` hook, as Composio is always enabled when the user is authenticated. - Updated error handling to surface backend connection issues directly, replacing previous checks for a disabled state. - Revised tests to reflect the new error handling logic, ensuring clarity in toolkit fetch error reporting. * refactor(integrations): update authentication handling for client configuration - Revised the `build_client` function to prioritize app-session JWT for user authentication, enhancing clarity in the fallback mechanism to `config.api_key`. - Improved error messages in `resolve_client` and `build_client` to provide clearer guidance on authentication issues related to session tokens. - Streamlined comments and documentation to reflect the updated authentication flow, ensuring consistency across integration components. * refactor(composio): unwrap CLI envelope for API responses - Introduced a new `unwrapCliEnvelope` function to handle the response format from the Rust side, allowing for easier access to the flat shapes defined in `./types`. - Updated `listToolkits`, `listConnections`, `listTools`, `authorize`, `deleteConnection`, and `execute` functions to utilize the new unwrapping logic, improving response handling consistency across the Composio API. - Enhanced error handling by ensuring that responses without logs pass through unchanged, maintaining backward compatibility. * refactor(skills_agent): update agent description and enhance Composio tool integration - Revised the `when_to_use` description in `agent.toml` to clarify the role of the Skills Agent as a service integration specialist, emphasizing its capability to execute both Composio and QuickJS skill tools. - Expanded the `prompt.md` documentation to detail available tool surfaces and typical Composio flow, improving clarity on how to interact with external services. - Implemented category overrides for Composio tools in `tools.rs` to ensure they are recognized as part of the Skill category, allowing proper access through the skills sub-agent. - Added tests to verify that Composio tools are correctly filtered and accessible by the skills sub-agent, ensuring robust integration and functionality. * style: apply formatter output from pre-push checks * refactor(tests): update Gmail and Notion integration tests for composio - Refactored tests for the Skills page to integrate Gmail and Notion as composio tools, enhancing the testing framework. - Removed mock data and streamlined the test setup to reflect the current state of available skills. - Updated assertions to verify the rendering of connected and disconnected states for Gmail and Notion integrations, respectively. - Improved clarity and maintainability of test cases by consolidating mock implementations and removing redundant code. * refactor(skills): update toolkit categorization and enhance test assertions - Modified the Skills component to assign categories dynamically based on toolkit metadata, improving organization of displayed tools. - Updated test cases to reflect the new categorization, ensuring accurate rendering of tools under their respective categories instead of a generic 'Other' group. - Enhanced assertions in tests to verify the presence of specific tools and their categories, improving test coverage and reliability. * refactor(skills): streamline item creation in Skills component - Simplified the item creation logic in the Skills component by removing unnecessary line breaks, enhancing code readability without altering functionality. - This change contributes to cleaner code structure and maintainability in the Skills page. * refactor(tests): enhance Gmail and Notion integration tests for improved clarity - Updated the integration tests for Gmail and Notion on the Skills page to utilize the `within` function for more precise querying of elements within their respective sections. - Improved test assertions to ensure that the connected and disconnected states are accurately verified, enhancing the reliability of the tests. - Streamlined the test setup to better reflect the current structure of the Skills component, contributing to overall test maintainability. * feat(skills): enhance Composio integration error handling and logging - Added error handling for Composio integrations in the Skills component, displaying a user-friendly message when integration status is stale or an error occurs. - Implemented logging in development mode to provide insights into the state of Composio toolkits and connections, aiding in debugging. - Updated the item rendering logic to reflect the error state, ensuring users can retry fetching integrations when an error is detected. - Enhanced tests to verify the display of error messages and the functionality of the retry mechanism, improving overall test coverage and reliability. |
||
|
Steven EnamakelandGitHub
|
362d0a014f |
fix(context): preserve cache-boundary metadata through prompt builders (#506)
* feat(prompt): enhance system prompt handling with cache boundary support - Updated the `SystemPromptBuilder` to include a new method for building prompts with cache metadata, returning a `RenderedPrompt` struct that contains the prompt text and an optional cache boundary index. - Introduced a constant for the cache boundary marker to improve readability and maintainability. - Modified the `extract_cache_boundary` function to cleanly remove the cache boundary marker from the rendered prompt while returning the relevant index. - Updated tests to validate the new cache boundary functionality and ensure that the system prompt does not leak internal markers. - Adjusted the agent's session management to track the cache boundary, enhancing the overall prompt handling and memory context management. * feat(context): add method to build system prompt with cache metadata - Introduced `build_system_prompt_with_cache_metadata` method in `ContextManager` to assemble the opening system prompt while preserving cache-boundary metadata for improved request prefix caching. - Updated imports to include `RenderedPrompt` for the new functionality, enhancing the context management capabilities. * feat(prompt): include cache boundary in subagent system prompt rendering - Updated `render_subagent_system_prompt` to insert a cache boundary marker before the workspace section, allowing typed sub-agents to maintain static instructions above this boundary for efficient prompt reuse. - Added a new test to verify that the cache boundary is correctly included in the rendered prompt, ensuring that the system prompt structure supports improved caching behavior. - Adjusted comments for clarity and updated the runtime banner numbering to reflect the new structure. |
||
|
Steven EnamakelandGitHub
|
afb95e72a5 |
refactor(event-bus): native typed request/response surface + channels encapsulation (#505)
* feat(event-bus): introduce typed request/response API for enhanced inter-module communication - Added a typed request/response surface to the existing event bus, allowing modules to execute requests through a shared controller registry. - Implemented `request_global` and `request_controller_global` functions for executing typed requests, enhancing the API's usability. - Updated documentation to reflect the new capabilities and usage patterns for the event bus, including when to use the request API versus traditional event publishing. - Added tests to validate the functionality of the new request/response features, ensuring robust integration with existing event bus operations. * refactor(event-bus): restructure event bus module and update references - Moved the event bus implementation from `src/openhuman/event_bus/` to `src/core/event_bus/`, establishing a clearer module hierarchy. - Updated all references throughout the codebase to reflect the new location of the event bus, ensuring consistency and reducing confusion. - Enhanced documentation to clarify the usage of the event bus and its core types, improving developer experience. - Introduced new files for event handling, requests, and subscribers, streamlining the event bus functionality and making it more modular. - Added tests to validate the new structure and ensure that the event bus operates correctly after the refactor. * refactor(event-bus): enhance event bus with native request/response surface - Updated the event bus to include a native, in-process typed request/response surface, allowing for zero serialization of Rust types and direct communication between modules. - Replaced the previous request API with a more streamlined approach using `register_native_global` and `request_native_global` functions. - Improved documentation to clarify the usage of the event bus, detailing when to use broadcast events versus native requests. - Removed the old request/response implementation to simplify the event bus structure and enhance maintainability. - Added examples and guidelines for registering and using native request handlers, improving developer experience and usability. * feat(agent): introduce native request handlers for agentic turns - Added a new `bus` module to encapsulate native event-bus handlers for the agent domain, including the `agent.run_turn` handler for executing agentic turns. - Updated the event bus registration process to include the new agent handlers, allowing for direct in-process request/response communication without serialization. - Refactored the channel message processing to dispatch agentic turns through the native bus, enhancing modularity and testability. - Improved documentation to clarify the usage of the new agent handlers and their integration with the event bus. - Added tests to validate the functionality of the new request handlers and ensure proper routing through the event bus. * refactor(tests): implement global bus handler lock for channel dispatch tests - Introduced a `use_real_agent_handler` function to manage the global bus handler lock during channel dispatch tests, ensuring exclusive access to the `agent.run_turn` handler. - Updated multiple test files to utilize the new handler function, improving test reliability by preventing race conditions during concurrent test execution. - Enhanced documentation to clarify the usage of the bus handler lock in tests that interact with the global native request registry. * feat(tests): add integration tests for Discord channel dispatch - Introduced a new test file `discord_integration.rs` to validate the end-to-end functionality of the Discord dispatch path within the channels module. - Implemented tests to ensure proper handling of inbound messages, reaction capabilities, and conversation history management specific to Discord. - Updated `mod.rs` to include the new Discord integration tests, enhancing overall test coverage for the channels module. * feat(tests): add Telegram integration tests for channel dispatch - Introduced new tests in `telegram_integration.rs` to validate the end-to-end functionality of the Telegram dispatch path within the channels module. - Implemented tests to ensure proper handling of threaded inbound messages, automatic acknowledgment reactions, and response routing through the agent bus handler. - Enhanced test coverage for Telegram, ensuring that the `supports_reactions()` capability is honored and that the dispatch pipeline operates correctly for both Telegram and Discord channels. * feat(tests): add testing utilities for event bus stubbing - Introduced a new `testing` module in the event bus to provide shared utilities for stubbing the global native bus registry. - Implemented `mock_bus_stub` and `MockBusGuard` to facilitate safe installation and restoration of stub handlers in tests, preventing race conditions. - Updated existing tests to utilize the new mocking utilities, enhancing test reliability and clarity in handling agent bus interactions. - Improved documentation to guide users on using the new testing features effectively. * style(event-bus): clean up formatting and remove unnecessary line breaks - Removed trailing whitespace and unnecessary line breaks in the event bus module files to improve code readability and maintainability. - Consolidated import statements and function definitions for a cleaner code structure across the event bus and agent modules. * fix(memory): point conversations/bus.rs at crate::core::event_bus Incoming `memory/conversations/bus.rs` from upstream/main still imports from the old `openhuman::event_bus` path. This branch relocated the bus to `core::event_bus`, so the merge left the import unresolved and the crate failed to compile. Rewire both references (`use` + fully-qualified `subscribe_global` call) to the canonical `crate::core::event_bus` path. |
||
|
Steven EnamakelandGitHub
|
986ff7ae4b |
feat(context): global context management module (#504)
* refactor(context): implement layered context pipeline with memory management - Introduced a new context pipeline orchestrator that manages context reduction stages before each provider call, including tool-result budgeting, microcompaction, and session memory management. - Added `ContextGuard` to monitor context utilization and trigger auto-compaction when thresholds are exceeded. - Implemented `microcompact` to replace older tool result payloads with placeholders, preserving API invariants while managing memory effectively. - Created `SessionMemory` to maintain persistent notes across sessions, updated by a background process to avoid impacting performance during user interactions. - Enhanced overall context management to improve memory efficiency and ensure smoother operation of the agent's functionality. * chore(context): add context module and refactor imports - Introduced a new `context` module to centralize context management for agent sessions, enhancing organization and maintainability. - Updated various files to replace references to the deprecated `context_pipeline` with the new `context` module, ensuring consistency across the codebase. - Bumped the version of the `openhuman` package to 0.52.4 in `Cargo.lock` to reflect these changes. * refactor(imports): update prompt module paths to new context structure - Refactored import statements across multiple files to replace references to the deprecated `agent::prompt` module with the new `context::prompt` module. - This change enhances code organization and aligns with the recent restructuring of the context management system. * feat(context): introduce comprehensive context management configuration - Added a new `ContextConfig` struct to manage global context settings, including budget thresholds, summarization triggers, and session-memory extraction parameters. - Implemented environment variable overrides for context management settings, allowing dynamic configuration. - Refactored the configuration loading process to accommodate the new context management structure, ensuring backward compatibility with existing configurations. - Introduced a `Summarizer` trait and default implementation for handling conversation summarization, enhancing the agent's ability to manage context effectively. - Updated related modules to integrate the new context management features, improving overall organization and maintainability of the codebase. * feat(context): implement ContextManager for enhanced session context handling - Introduced a new `ContextManager` struct to manage session context, including prompt assembly, context reduction, and summarization dispatch. - Added methods to `ContextGuard` for tracking input and output token counts, as well as the context window size. - Updated the `mod.rs` files to include the new `manager` module and its exports, improving organization and maintainability of the context management system. - Enhanced overall context management capabilities, allowing for more efficient handling of conversation context during agent interactions. * refactor(context): centralize system prompt assembly for channel runtimes - Moved the system prompt construction logic for channel runtimes into a new `channels_prompt` module within the `context` directory, ensuring all prompt-building code is organized in one location. - Updated various files to replace deprecated references to the old prompt module, enhancing code clarity and maintainability. - Introduced a new `build_system_prompt` function tailored for channel-specific requirements, including tool descriptions and channel-specific preambles, while maintaining byte-stability for cache efficiency. - Refactored related imports and tests to align with the new structure, improving overall organization of the context management system. * style(context): apply rustfmt to context module and integration sites Clippy caught a never-looping `while` in `snap_split_forward` that was really an `if` in disguise — collapse it. Everything else is pure `cargo fmt` cleanup on files touched during the context/ refactor. Full `cargo test --lib` sweep: 2253 tests passing. * delete(config): remove obsolete user configuration file - Deleted the `config.toml` file for user `69ccc8e95692bb0ddd56c10f`, which was no longer needed, streamlining the user configuration management. * refactor(SOUL.md): remove emoji usage guidelines to streamline prompt instructions - Deleted the section on emoji usage to simplify the prompt guidelines, focusing on clarity and direct communication with users. This change aims to enhance the overall effectiveness of the prompts by reducing unnecessary complexity. * refactor(config): enhance environment variable handling for context compaction settings - Improved the parsing and validation of environment variables for `OPENHUMAN_CONTEXT_COMPACTION_TRIGGER_PCT` and `OPENHUMAN_CONTEXT_HARD_LIMIT_PCT`, ensuring that the compaction trigger percentage is strictly less than the hard limit. - Added warnings for invalid percentage values and retained existing configuration values on failure. - Updated the context management logic to handle migration from deprecated fields, ensuring backward compatibility and clearer user guidance. * refactor(context): update tool result budget handling in Agent - Changed the source of the tool result budget to be derived from the ContextManager, ensuring it reflects the resolved `context.tool_result_budget_bytes` with any environment or configuration overrides. - This update removes reliance on the deprecated `agent.tool_result_budget_bytes` field, centralizing budget management for improved consistency across the context management system. * refactor(prompt): enhance subagent rendering options and system prompt construction - Introduced `SubagentRenderOptions` to manage per-definition rendering flags, allowing for more flexible control over the inclusion of identity, safety preamble, and skills catalog in the system prompt. - Updated `render_subagent_system_prompt` to utilize these options, ensuring that the rendering behavior aligns with the specified flags. - Modified `build_system_prompt` to accept an optional `channel_name`, improving clarity in channel capabilities messaging and removing hardcoded references to "Discord". - Adjusted tests to reflect changes in prompt construction, ensuring comprehensive coverage of the new rendering logic. * refactor(context): improve session memory handling in ContextManager - Updated session memory methods in `ContextManager` to use a locked reference for thread safety during extraction state changes. - Introduced a new method `session_memory_handle` to facilitate background task management of session memory extraction. - Adjusted the context statistics to utilize a snapshot of session memory, enhancing data integrity and consistency. * refactor(turn): improve extraction state management in Agent - Updated the extraction state handling to transition to "in-progress" instead of "complete" immediately, allowing for better control during background extraction tasks. - Introduced a shared handle for session memory to manage extraction completion and failure states, ensuring deltas are preserved for retries on failure. - Enhanced logging to provide clearer insights into the extraction process outcomes. |
||
|
Steven EnamakelandGitHub
|
462b4d2895 |
Move conversation persistence into workspace memory store (#503)
* Move conversation persistence into workspace memory store * Apply formatter updates for conversation persistence * Enhance conversation persistence by registering a new subscriber for channel events. Update domain subscriber registration to include workspace directory, ensuring proper message handling and persistence across channels. Refactor event structure to include message ID and reply target for improved tracking. Additionally, adjust module visibility for context management. |
||
|
Steven EnamakelandGitHub
|
73f8d1287a |
refactor: remove hardware-related components and streamline service management (#502)
* feat(config): introduce pre-login user directory structure - Added support for a pre-login user directory to encapsulate configuration, memory, and state before any user logs in. This ensures that all initial data is scoped under a dedicated user directory (`users/local`), preventing direct writes to the root `.openhuman` path. - Implemented the `pre_login_user_dir` function to return the appropriate path for the pre-login user. - Updated configuration loading logic to defer disk state creation until the first successful login, enhancing user data management and isolation. - Added tests to verify the correct behavior of the pre-login directory structure. * refactor: remove hardware-related components and streamline service management - Deleted hardware configuration and related tools from the codebase, including `HardwareConfig`, `HardwareTransport`, and associated memory management tools. - Introduced a new `service.ts` module for managing service and daemon commands, consolidating service-related functionalities. - Updated import paths across the application to reflect the removal of hardware references and the addition of the new service management module. - Refactored the `build_system_prompt` function to remove hardware access instructions, focusing on action instructions instead. - Cleaned up the Cargo.toml and Cargo.lock files by removing unused dependencies related to hardware management. * chore: apply formatting and tauri lockfile sync * refactor(tests): extract config file writing logic into a reusable function - Introduced a `write_config_file` function to encapsulate the logic for creating directories and writing configuration files, improving code reuse and readability. - Updated test cases to utilize the new function for writing configuration files, ensuring consistency and reducing duplication. - Added handling for pre-login user directory structure to ensure configuration is correctly written to the appropriate paths. |
||
|
Steven EnamakelandGitHub
|
1c7318603e |
feat(composio): backend-proxied Composio integration end-to-end (#501)
* feat(composio): add Composio integration module with OAuth support - Introduced a new Composio module for backend-proxied access to various OAuth integrations. - Implemented ComposioClient for handling API requests related to toolkits, connections, and actions. - Added RPC operations for listing toolkits, managing connections, and executing actions. - Registered Composio controllers and schemas for integration with the existing system. - Created a debug script for testing Composio OAuth flow against the live backend. - Updated Cargo.lock to version 0.52.3 to reflect the new changes. * feat(composio): implement Composio connection modal and API integration - Added ComposioConnectModal for managing Composio toolkit connections, mirroring the user experience of existing modals. - Introduced composioApi for backend communication, including functions for listing toolkits, managing connections, and handling OAuth authorization. - Created toolkitMeta for displaying metadata of Composio toolkits in the Skills grid. - Developed hooks for fetching and managing Composio integrations, ensuring real-time updates on connection status. - Updated Skills page to integrate Composio toolkits, providing a seamless user experience for connecting and managing integrations. * chore: update OpenHuman version to 0.52.3 and add debug-composio-trigger script - Bumped OpenHuman package version in Cargo.lock to 0.52.3. - Introduced a new script, debug-composio-trigger.mjs, for Socket.IO live listening of Composio trigger events, facilitating testing and debugging of webhook interactions. * style(composio): apply Prettier + rustfmt from pre-push hook * feat(composio): enhance ComposioConnectModal and improve polling logic - Updated ComposioConnectModal to handle various connection phases more effectively, including 'waiting' for pending connections. - Introduced new refs for managing polling state and in-flight requests to prevent overlapping executions. - Improved error handling during polling, providing clearer feedback on OAuth timeouts. - Added logic to resume polling if the modal opens while an OAuth handoff is in progress. - Refactored connection handling in the modal for better clarity and maintainability. * refactor(composio): improve JSON payload handling and connection verification - Updated debug-composio-login.sh to build JSON payloads using jq for safer handling of toolkit data. - Enhanced connection verification logic in debug-composio-trigger.mjs to prioritize newly created connections and provide warnings for missing toolkits. - Refactored composio operations in ops.rs to return a more explicit error type, improving clarity in error handling across RPC operations. |
||
|
Steven EnamakelandGitHub
|
57d307ad1e |
feat(agent): simplify harness + trim bundled prompts (#500)
* Add built-in agent definitions and prompts for orchestrator, planner, code executor, skills agent, researcher, critic, archivist, and tool maker - Introduced a new module for built-in agent definitions, allowing for easy addition of agents through a structured format. - Created TOML configuration files for each agent, detailing their properties such as id, display name, usage context, and tool specifications. - Developed corresponding prompt files that outline the responsibilities and rules for each agent, enhancing their functionality and usability. - Implemented a loading function to parse these definitions into usable agent structures, ensuring all agents are correctly initialized and validated. * Remove deprecated archetypes and related components from the multi-agent harness - Deleted the `archetypes.rs`, `dag.rs`, `executor.rs`, and `types.rs` files, which contained the definitions and implementations for agent archetypes, task DAGs, and execution logic. - Updated the `builtin_definitions.rs` and `definition.rs` files to remove references to the now-removed archetypes, streamlining the agent definition process. - Refactored the `mod.rs` file to eliminate unused modules and clarify the structure of the multi-agent harness. - Adjusted comments and documentation to reflect the removal of the DAG orchestration flow, emphasizing the current sub-agent delegation model. * Remove unused `ArchetypeConfig` from schema exports in `mod.rs` to streamline configuration management. * Implement context guard and memory management features in the harness module - Introduced `ContextGuard` to monitor context utilization and trigger auto-compaction when usage exceeds defined thresholds. - Added `scrub_credentials` function to sanitize sensitive information from tool outputs. - Implemented history management functions to trim conversation history and build compaction transcripts. - Created `build_tool_instructions` to generate tool usage guidelines for the system prompt. - Developed `memory_context` functions to manage user memory and relevant context for conversations. - Enhanced the `tool_loop` to integrate the new context management and tool invocation logic. This update improves the agent's ability to manage context effectively, ensuring efficient memory usage and secure handling of sensitive data. * Refactor agent module imports to use the harness instead of loop_ - Updated import paths in `dispatcher.rs`, `memory_loader.rs`, `mod.rs`, `dispatch.rs`, and `startup.rs` to replace references from the `loop_` module to the `harness` module. - This change enhances module organization and aligns with the recent architectural updates in the agent structure. * Remove cost tracking and context assembly modules from the agent structure - Deleted `cost.rs` and `context_assembly.rs` files, which handled token cost tracking and context assembly for the multi-agent harness, respectively. - Updated `mod.rs` files to remove references to the deleted modules, streamlining the agent's organization and focusing on essential components. - This cleanup enhances maintainability and aligns with the current architectural direction of the project. * Remove identity module and related configurations from the agent structure - Deleted the `identity.rs` file, which contained the AIEOS identity handling logic and related structures. - Updated `mod.rs` and other files to remove references to the deleted identity module, streamlining the agent's organization. - This change simplifies the codebase and aligns with the decision to rely solely on OpenClaw markdown files for identity management. * Enhance agent prompts with improved formatting and clarity - Added spacing for better readability in the prompts of the Archivist, Code Executor, Critic, Orchestrator, Researcher, Skills Agent, and Tool Maker agents. - Updated the table formatting in the Orchestrator prompt for consistency and clarity. - These changes improve the overall presentation and usability of agent documentation, making it easier for users to understand agent responsibilities and rules. * Remove REPL functionality and related components from the agent structure - Deleted the `repl.rs` file, which contained the implementation for the interactive REPL. - Removed references to the REPL in `cli.rs`, `mod.rs`, and other related files, streamlining the agent's organization. - Eliminated unused REPL session handling logic from the agent schemas and local AI operations, enhancing maintainability and focusing on essential components. - This cleanup aligns with the current architectural direction of the project, simplifying the codebase. * Refactor imports and clean up configuration exports - Updated import paths in `startup.rs` to include `host_runtime` from the correct module. - Streamlined the export statements in `mod.rs` and `schema/mod.rs` for better organization and clarity. - Removed unnecessary line breaks in the export lists to enhance readability and maintainability of the configuration schema. * Remove unused history management functions and clean up agent module exports - Deleted the `history.rs` and `session.rs` files, which contained functions for managing conversation history and session handling. - Updated `mod.rs` to remove references to the deleted modules and streamline the agent's organization. - Cleaned up import statements in `mod.rs` and other files to enhance clarity and maintainability of the codebase. * Add agent harness module with builder, runtime, and turn management - Introduced a new `harness` module for the `Agent`, encapsulating the `AgentBuilder`, runtime accessors, and turn lifecycle management. - Implemented the `AgentBuilder` fluent API for constructing `Agent` instances with customizable configurations. - Developed the `turn` method to handle user interactions, tool execution, and context management within the agent. - Created a `runtime` module for public accessors and utility functions related to agent operations. - Added comprehensive unit and integration tests to ensure the functionality of the new agent structure and its components. * Remove classifier and traits modules from the agent structure - Deleted the `classifier.rs` and `traits.rs` files, which contained the classification logic and core agent traits, respectively. - Updated `mod.rs` to remove references to the deleted modules, streamlining the agent's organization. - This cleanup enhances maintainability and focuses on essential components of the agent architecture. * Refactor agent prompt structure and remove unused files - Updated the `prompt.rs` file to streamline the orchestrator's logic by removing unnecessary tool documentation references and simplifying the file list. - Deleted several prompt files (`AGENTS.md`, `BOOTSTRAP.md`, `CONSCIOUS_LOOP.md`, `MEMORY.md`, `README.md`, `TOOLS.md`) to declutter the project and focus on essential components. - Adjusted the `harness/mod.rs` file to change module visibility from public to crate-level for better encapsulation. - These changes enhance maintainability and align with the current architectural direction of the project. * Refactor bootstrap file handling and update tests - Simplified the list of bundled prompt files in `prompt.rs` by removing references to `AGENTS.md` and `TOOLS.md`, focusing on essential identity files. - Adjusted the logic for injecting `MEMORY.md` to be optional, ensuring it only appears if it exists. - Updated test cases in `common.rs`, `identity.rs`, and `prompt.rs` to reflect the changes in the bootstrap file structure and ensure accurate validation of the new logic. - These modifications enhance clarity and maintainability of the codebase while aligning with the current project architecture. * Implement agent delegation tools and browser automation features - Introduced new tools for agent delegation, including `ArchetypeDelegationTool`, `AskClarificationTool`, `DelegateTool`, and `SkillDelegationTool`, enhancing the agent's ability to manage tasks through specialized sub-agents. - Added `SpawnSubagentTool` for delegating tasks to sub-agents, allowing for more complex workflows and improved task management. - Implemented browser automation capabilities with `BrowserOpenTool`, enabling secure opening of approved URLs in the Brave Browser. - Enhanced the `BrowserTool` with pluggable backends for improved automation and user interaction. - Added `ImageInfoTool` for extracting metadata from images, supporting future multimodal capabilities. - Organized tools into a new `impl` module structure for better maintainability and clarity in the codebase. * Refactor imports and clean up tool implementations - Updated import statements across various tool implementations to ensure consistency and clarity, particularly in the `traits.rs` file. - Removed unnecessary line breaks and adjusted module paths for better organization. - Cleaned up test files by removing trailing whitespace, enhancing code readability and maintainability. - These changes streamline the codebase and improve the overall structure of tool-related components. * Update built-in definitions and prompt handling for clarity and consistency - Revised the test for built-in agent definitions to dynamically reference the length of `BUILTINS`, enhancing maintainability. - Clarified documentation for the `system_prompt` field in `AgentDefinition`, emphasizing the default behavior and usage of inline prompts. - Simplified the `build_system_prompt` function by removing unnecessary conditional logic, ensuring a more straightforward return of the prompt string. * Enhance agent definition loading and documentation clarity - Updated the `load_file` function to reject definitions with missing or empty `system_prompt`, ensuring custom definitions are properly validated. - Added a new test to verify that definitions lacking a `system_prompt` are correctly rejected, improving robustness. - Clarified documentation for built-in definitions and TOML parsing, emphasizing compile-time guarantees and runtime checks. - Improved the logic for checking the existence of `MEMORY.md` to prevent errors from stray directories, enhancing file handling reliability. |
||
|
Steven EnamakelandGitHub
|
31297ad19d |
refactor(memory): remove GLiNER/GLiREL ingestion phase (#499)
* refactor(memory): replace GLiNER model with heuristic extraction - Removed GLiNER-related code and dependencies from the memory ingestion pipeline, transitioning to a heuristic-only extraction approach. - Updated documentation and comments to reflect changes in extraction methods. - Adjusted tests to ensure compatibility with the new heuristic extraction configuration. - Bumped version of the tokenizers dependency and updated Cargo.lock accordingly. * chore: apply formatting and tauri lockfile sync |
||
|
Mega MindandGitHub
|
9118bfb5d6 |
Fix/skill start issue (#498)
* chore: update .gitignore and bump openhuman version to 0.52.2 - Added `overlay/src-tauri/target/` to .gitignore to prevent tracking of build artifacts. - Updated the openhuman package version from 0.52.0 to 0.52.2 in Cargo.lock files for both the main and app/src-tauri directories. - Enhanced entitlements for macOS Hardened Runtime to allow outbound HTTPS calls and server connections. - Refactored registry operations to use rustls explicitly, improving network reliability on macOS. * refactor(logging): improve debug message formatting in fetch_url_bytes function - Updated the logging statement in the fetch_url_bytes function to enhance readability by formatting the debug message across multiple lines. This change improves clarity in log outputs, making it easier to track the number of bytes fetched from URLs. * feat(skill-setup): enhance OAuth handling and skill status synchronization - Introduced a managed OAuth auto-advance mechanism to ensure it runs only once per login attempt, improving user experience during authentication. - Updated the SkillSetupWizard to handle skill runtime checks more effectively, ensuring that the skill starts correctly and transitions to the setup phase seamlessly. - Enhanced the useSkillSnapshot hook to provide a synthesized offline snapshot when the skill is not yet running, preventing UI stalls during loading. - Implemented background synchronization after OAuth completion to ensure users see fresh data immediately without blocking the UI. - Added tests to validate the new behavior for skills setup completion and status retrieval without requiring the skill to be started first. * refactor(skills): streamline setup_complete retrieval in handle_skills_status function - Simplified the retrieval of the `setup_complete` variable by removing unnecessary line breaks, enhancing code readability and maintainability. - This change improves the clarity of the function's logic without altering its functionality. * refactor(skills): simplify success message and remove initial sync from OAuth flow - Updated the success message in the SkillSetupWizard to remove references to background syncing, streamlining user communication. - Removed the initial sync trigger from the SkillManager after OAuth completion, shifting the responsibility for data synchronization to the user interface or cron jobs. - Adjusted comments in the desktopDeepLinkListener to reflect the new sync behavior, clarifying that initial data sync is no longer automatic. * fix(pr-498): address CodeRabbit review and CI failures - SkillSetupWizard: only show complete after startSetup succeeds; error on failures - hooks: merge prior snapshot into offline fallback; use const arrow for helper - E2E: reset skills_set_setup_complete in finally for isolation - json_rpc_e2e: assert oauth/complete returns start() result; add minimal start() - Skills page tests: mock screen-intelligence/autocomplete/voice hooks (CoreStateProvider) Made-with: Cursor * fix: address follow-up CodeRabbit (readiness poll, shared test mocks) - SkillSetupWizard: waitForSkillRunning after startSkill before startSetup/auth RPC - json_rpc_e2e: poll skills_status until running instead of fixed 400ms sleep - Consolidate Skills page vi.mocks in test/mockDefaultSkillStatusHooks.ts Made-with: Cursor * fix: CodeRabbit — legacy OAuth awaits setSetupComplete, const waitForSkillRunning, mock base - Legacy OAuth: await persistence before complete; error on failure; guard ref + reset on skillId - waitForSkillRunning: const arrow per TS style - mockDefaultSkillStatusHooks: offlineStatusBase spread for shared literals Made-with: Cursor |
||
|
|
7b457aa27d |
feat(agent): pure orchestrator pattern with per-skill delegation tools (#496)
* feat(agent): pure orchestrator pattern with per-skill delegation tools (#478) Refactors the main agent from a direct tool-calling model to a pure orchestrator that delegates all work through dynamically generated tools. Architecture changes: - Orchestrator only sees generated tools (notion, gmail, research, run_code, review_code, plan, spawn_subagent) — skill tools are architecturally unreachable from the main agent - Each installed skill auto-generates a delegation tool at build time (SkillDelegationTool) that routes to skills_agent with the correct skill_filter - Static archetype tools (research, run_code, etc.) delegate to their respective sub-agents - visible_tool_specs filters the function-calling schema sent to the provider, enforcing the orchestrator boundary at the API level Prompt changes: - Rewrote AGENTS.md as a lean orchestrator prompt — no more routing tables or agent_id instructions - Orchestrator skips TOOLS.md, MEMORY.md, HEARTBEAT.md (~6k tokens saved per turn) — subagents get tool specs from the registry - Workspace .md files auto-sync via builtin-hash mechanism so prompt updates ship automatically to existing installs Bug fixes: - ModelSpec::Hint now resolves to {hint}-v1 (e.g. agentic-v1) instead of hint:agentic which the backend rejected - validate_skill_filter now uses skill_id from the engine tuple instead of splitting on __ in the raw tool name (which always failed) - Memory context forwarded to subagents via ParentExecutionContext Observability: - Added [agent] tagged logs for tool responses, agent state transitions, and delegation decisions throughout turn.rs See docs/agent-prompt-architecture.excalidraw for the visual diagram. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: rustfmt orchestrator_tools.rs Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: address CodeRabbit review — dispatch guard, fork specs, decouple sync - Enforce visible-tool allowlist at dispatch time (not just schema) - Fork mode uses visible_tool_specs (not full registry) - De-duplicate spawn_subagent when extending orchestrator tools - Raw tool output moved to debug level, info level logs metadata only - Decouple workspace file sync from prompt rendering so skipped files still get synced to disk Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
|
8e8da17ad9 |
fix(voice): cross-platform microphone permission handling (#489) (#491)
* fix(voice): add cross-platform microphone permission handling (#489) Voice dictation in release DMG silently fails because the macOS hardened runtime enforces entitlements and the sidecar plist lacked the audio-input entitlement. This adds the entitlement, NSMicrophoneUsageDescription for the system permission prompt, and cross-platform microphone permission detection (CPAL device probe) with clear error messages on macOS, Windows, and Linux. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(permissions): use plist file for infoPlist and fix cross-platform warnings (#489) - infoPlist expects a file path, not inline JSON — create Info.plist with NSMicrophoneUsageDescription and reference it as a string - Move Microphone permission request out of macOS-only cfg block since request_microphone_access() is cross-platform (fixes unused import warning on Linux CI) - Treat persistent Unknown mic permission as Denied per CodeRabbit review Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Cyrus Gray <144336577+graycyrus@users.noreply.github.com> |
||
|
Mega MindandGitHub
|
49cbbbebaf |
Fix/skill start issue (#493)
* chore: update .gitignore and bump openhuman version to 0.52.2 - Added `overlay/src-tauri/target/` to .gitignore to prevent tracking of build artifacts. - Updated the openhuman package version from 0.52.0 to 0.52.2 in Cargo.lock files for both the main and app/src-tauri directories. - Enhanced entitlements for macOS Hardened Runtime to allow outbound HTTPS calls and server connections. - Refactored registry operations to use rustls explicitly, improving network reliability on macOS. * refactor(logging): improve debug message formatting in fetch_url_bytes function - Updated the logging statement in the fetch_url_bytes function to enhance readability by formatting the debug message across multiple lines. This change improves clarity in log outputs, making it easier to track the number of bytes fetched from URLs. |
||
|
Steven EnamakelandGitHub
|
a2fb1119ea |
refactor(skills): unify auth/oauth handshake on start({validate}) and drop enabled flag (#484)
* refactor(preferences): streamline skill preference management by removing the enabled toggle - Removed the `enabled` field from `SkillPreference`, simplifying the preference model to focus solely on `setup_complete`. - Updated related methods and RPC handlers to reflect this change, ensuring that skills are automatically started based on the completion of their setup process. - Adjusted tests to validate the new behavior, ensuring consistent functionality without the `enabled` toggle. - Enhanced documentation to clarify the new preference management approach. * refactor(auth): simplify authentication flow by removing onAuthComplete hook - Updated the `handle_auth_complete` function to eliminate the separate `onAuthComplete` JavaScript hook, streamlining the authentication process. - Revised the flow to directly inject new credentials and validate them using the `start` function, which now handles both validation and activation. - Enhanced rollback logic to ensure temporary credentials are cleared if validation fails, preventing persistence on disk. - Improved documentation to clarify the new authentication steps and their implications for credential management. * refactor(oauth): streamline OAuth credential handling in `handle_oauth_complete` - Removed the `build_start_credentials_arg` function and integrated its logic directly into `handle_oauth_complete`, simplifying the flow. - Updated the OAuth handling to validate credentials before persisting them, ensuring that only successful validations are saved. - Enhanced rollback logic to clear temporary credentials if validation fails, preventing incorrect state persistence. - Improved documentation to clarify the new steps in the OAuth process and their implications for credential management. |
||
|
|
0cd0f7a670 |
feat(voice): sync overlay orb with chat voice button state (#487) (#490)
* feat(voice): sync overlay orb with chat voice button state (#487) The overlay orb already reacts to hotkey-based dictation via Socket.IO events, but the chat "Start Talking" button used local React state only. Add a new RPC method `openhuman.overlay_stt_notify` that the chat button calls at each voice state transition, which publishes to the existing DICTATION_BUS / TRANSCRIPTION_BUS broadcast channels — so the overlay reflects recording/transcribing/idle from both input paths with zero changes to the Socket.IO bridge or overlay event handlers. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(voice): address CI formatting and CodeRabbit review feedback - Run cargo fmt and prettier to fix formatting violations - Use typed enum OverlaySttState instead of raw String for state param (serde rejects invalid states at deserialization, eliminating the unknown state branch) - Require `text` field for transcription_done state (return error if missing instead of silently ignoring) - Replace raw transcript logging with metadata-only (has_text, text_len) to avoid logging sensitive user speech content - Use "Voice input active" aria-label (covers recording + linger phases) - Convert notifyOverlaySttState to arrow function with async/await per repo TS conventions Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
YellowSnnowmannandGitHub
|
aee9c52e88 |
fix(channels): Telegram threading, live listeners, core restart, and webhook cleanup (#485)
* feat(config): enhance world-readable config warning mechanism - Introduced a new static variable to track previously warned world-readable config files, preventing duplicate warnings. - Updated the warning logic to only log a warning for each unique world-readable config file, improving log clarity and reducing noise. - Added new `ChannelReactionReceived` and `ChannelReactionSent` events to the DomainEvent enum, expanding event handling capabilities in the event bus. - Included tests for the new reaction events to ensure proper functionality and integration. * feat(logging): add log file constraints and event filtering - Introduced functions to parse log file constraints from environment variables and filter log events based on these constraints. - Enhanced the `init_for_cli_run` function to apply the new filtering logic, improving log management and clarity. - Updated the `conversation_history_key` function to include thread context for Telegram, ensuring accurate message targeting. - Added a new trait method `supports_reactions` to the `Channel` trait, indicating support for emoji reactions. - Implemented integration tests for Telegram channel features, including reaction handling and thread message forwarding. * feat(telegram): enhance message handling with reactions and typing indicators - Added support for emoji reactions in Telegram responses, allowing for contextual acknowledgment of user messages. - Implemented a decision heuristic for when to use reactions, improving user interaction quality. - Introduced a typing indicator that activates immediately upon receiving a message, providing instant feedback to users. - Updated the channel delivery instructions to include new reaction syntax and guidelines for usage. - Enhanced tests to cover new reaction handling and message acknowledgment features, ensuring robust functionality. * fix(tests): update route key for Telegram message handling tests - Changed the route key in tests from `telegram_alice` to `telegram_alice_chat-1` to match the updated `conversation_history_key` format for Telegram. - This adjustment ensures accurate routing and consistency in message handling tests. * refactor(tests): streamline message handling in runtime tool calls - Refactored the message handling tests to utilize a `ChannelMessage` struct for improved clarity and maintainability. - Updated the route key generation to use the `conversation_history_key` function, ensuring consistency in message routing. - Simplified the invocation of `process_channel_message` by directly passing the constructed message, enhancing readability. * fix(telegram): enhance finalize_draft method to support thread context - Updated the `finalize_draft` method in the `Channel` trait and its implementation for `TelegramChannel` to accept an optional `thread_ts` parameter, allowing for message threading. - Adjusted related message handling functions to utilize the new parameter, ensuring proper message context during sending. - Modified tests to reflect changes in the `finalize_draft` method signature, enhancing the robustness of message handling in threaded conversations. * refactor(tests): ran format * feat(discord, telegram): implement core process restart on channel connection - Added functionality to restart the core process when a channel connection requires a restart, enhancing the user experience by automating the process. - Implemented error handling to log any issues during the restart, ensuring users are informed to restart the app if necessary. - Updated both Discord and Telegram configuration components to include this new behavior, improving consistency across channel integrations. * feat(core-update): enhance core update logging and error handling - Added warnings for outdated sidecar versions and potential mismatches in UI features, improving user awareness of version compatibility. - Implemented detailed error logging for failed attempts to fetch the latest core release, providing users with clear instructions for manual updates if necessary. - Enhanced logging for reusing existing core RPC endpoints, alerting users to potential issues with stale connections. * feat(channels): implement real-time channel listeners and enhance logging - Added support for real-time channel listeners for Telegram and Discord, ensuring inbound bot messages are polled during `openhuman run`. - Introduced a method to check for configured listening integrations, preventing unnecessary listener spawning when not needed. - Enhanced logging for channel connection events and message handling, providing better visibility into channel operations and user interactions. - Updated the Telegram channel connection to log the count of allowed users and mention-only settings for improved debugging. * chore(dependencies): update openhuman version to 0.51.18 and refactor imports in channel config components - Bumped the openhuman package version from 0.49.17 to 0.51.18 in Cargo.toml and Cargo.lock. - Refactored import statements in DiscordConfig.tsx and TelegramConfig.tsx to maintain consistency and ensure proper functionality. * Implement webhook deletion for long polling in TelegramChannel - Added `delete_webhook_for_long_polling` method to clear the Bot API webhook, enabling `getUpdates` long polling. - Updated error handling in `fetch_bot_username` to call the new method when a 409 conflict indicates an active webhook, allowing for retries after webhook deletion. - Enhanced logging for better traceability of webhook deletion and polling conflicts. * Refactor Discord and Telegram connection handling to ensure channel connection updates are dispatched regardless of restart requirement. Improved error handling during core process restart and enhanced logging for connection status. |
||
|
Steven EnamakelandGitHub
|
6410db1fad |
feat(thu-fullrun): overlay attention, skills sync, credits & settings refresh (#479)
* Update Conversations component to enhance user messaging for budget limits. Changed the warning text for exhausted weekly inference budget to improve clarity and user experience. * feat(schemas): add new configuration option for vision model usage - Introduced a new optional boolean field `use_vision_model` in the schemas for enabling vision LLM for screenshot analysis. - Updated the screen intelligence schemas to include a required `consent` field for starting sessions, replacing the previous `sample_interval_ms` field. - Enhanced the `ttl_secs` field description for clarity and modified the `capture_policy` to `screen_monitoring` for better understanding of its purpose. * feat(CoreStateProvider): enhance state management with optimistic updates and error handling - Implemented optimistic local commits for `setAnalyticsEnabled` and `setOnboardingCompletedFlag` to provide instant UI feedback while ensuring state consistency through authoritative snapshot refreshes. - Added error handling for the `refresh` function calls in `setAnalyticsEnabled`, `setOnboardingCompletedFlag`, and `clearSession` to log failures, improving robustness in state management during user interactions. - Updated dependencies in the `useCallback` hooks to include `refresh`, ensuring proper state updates and synchronization with the core. * feat(paths): centralize runtime path resolution for user-scoped skills data - Introduced a new module `paths.rs` to handle the resolution of runtime paths for skills, ensuring that `skills_data` and `workspace` directories are scoped per user. - Updated `bootstrap_skill_runtime` and `bootstrap_skills_runtime` functions to utilize the new path resolution logic, improving consistency and clarity in directory management. - Enhanced error logging for directory creation failures to include the specific path that failed, aiding in debugging. - Added a new optional field `overlay_ttl_ms` in the autocomplete schemas to support overlay time-to-live configuration. * feat(ScreenIntelligencePanel): optimize config synchronization to prevent user edit clobbering - Introduced a reference to track the last synced configuration signature, ensuring that user edits are preserved during periodic updates from the CoreStateProvider. - Updated the effect to compare serialized configuration values, allowing for re-sync only when actual changes occur, enhancing user experience and preventing unintended data loss. * feat(SkillManager): implement initial sync after OAuth completion - Added functionality to trigger an initial data sync immediately after OAuth completion, ensuring users see fresh data without waiting for the next scheduled sync. - Updated comments to clarify the change in sync behavior due to recent modifications in the Rust core, which no longer auto-triggers sync on OAuth completion. * fix(UsageLimitModal, Conversations): enhance user messaging for budget limits - Updated warning messages in both UsageLimitModal and Conversations components to provide clearer information regarding weekly limits and reset times. - Improved clarity in user notifications to enhance overall experience when budget limits are reached. * refactor(SkillSetupModal): improve session mode handling for skill configuration - Updated the SkillSetupModal component to lock the mode at mount time, ensuring users remain in the setup wizard during their session even if the skill is marked as complete. - Simplified mode management by replacing the forceSetup state with a sessionMode state, allowing explicit mode switching while maintaining a consistent user experience. * feat(SkillManager): enhance setup flow for OAuth-based skills - Updated the `startSetup` method to handle OAuth-based skills more effectively by implementing a fallback to core RPC for skills without a frontend runtime. - Improved error handling to treat missing `onSetupStart` implementations as successful completion for pure OAuth skills, allowing the setup wizard to display the "Connected!" screen. - Added detailed logging for both local runtime and core RPC fallback scenarios to improve traceability during the setup process. * feat(Home): enhance local AI status handling and asset management - Introduced a new state for local AI assets, allowing for better tracking of model file readiness. - Updated the loading logic to fetch both local AI status and assets concurrently, improving performance and error handling. - Implemented a mechanism to hide the Local Model Runtime card once all models are fully downloaded, enhancing user experience. - Added comprehensive comments to clarify the logic behind model readiness checks based on asset states. * refactor(Credits): update credit balance structure and terminology - Renamed credit categories in the RewardsCouponSection and PayAsYouGoCard components for clarity, changing "General credits" to "Promo credits" and "Top-up credits" to "Team top-up." - Updated the credit balance API to reflect the new structure, replacing `balanceUsd` and `topUpBalanceUsd` with `promotionBalanceUsd` and `teamTopupUsd`. - Adjusted normalization logic in the credits API to accommodate the new credit balance fields. - Modified tests to ensure correct handling of the updated credit balance structure. * feat(Settings): reorganize billing settings and update descriptions - Added a new top-level billing section to the settings, promoting it out of the Account & Security category for better visibility. - Updated the description for the Account & Security section to remove billing references, focusing on recovery phrase, team management, and linked account access. - Adjusted the settings navigation to accommodate the new billing section, ensuring proper routing and user experience. * refactor(Config): change logging level from info to debug for environment overrides - Updated logging statements in the Config implementation to use debug level instead of info, reducing verbosity during runtime while maintaining necessary traceability for configuration loading. * feat(Overlay): implement overlay attention event handling and refactor overlay app structure - Introduced a new overlay module to manage attention events, allowing the core to publish messages to the overlay window. - Enhanced the OverlayApp component to handle dictation and attention events, improving user interaction with the overlay. - Refactored the overlay state management to support different modes (idle, stt, attention) and added auto-dismiss functionality for attention messages. - Removed the Browser Access Toggle from the Skills page, streamlining the UI and focusing on core functionalities. - Updated tests to reflect changes in the Skills component and removed unnecessary mocks related to browser access. * fix(OverlayBubbleChip): reset typewriter animation on new bubble identity - Updated the OverlayBubbleChip component to reset the typewriter animation correctly when a new bubble is displayed by using the `key` prop. - Refactored the cleanup logic in the useEffect hook to ensure proper interval management and state reset, enhancing the user experience with bubble transitions. * refactor(rest): streamline key_bytes_from_string function and improve readability - Simplified the condition for checking the ASCII key length and character restrictions in the key_bytes_from_string function. - Consolidated the import statements for base64 engines into a single line for better clarity. - Adjusted test data formatting for improved readability in the key_bytes_from_string_tests module. * enhance(logging): improve color detection logic for terminal output - Updated the color detection logic in the logging module to prioritize environment variables (`NO_COLOR`, `FORCE_COLOR`, `CLICOLOR_FORCE`) for better control over color output. - Added detailed comments explaining the color resolution order, enhancing code clarity and maintainability. * test(Home): add mock for openhumanLocalAiAssetsStatus in tests - Enhanced the Home and HomeBootstrapButtons test files by adding a mock implementation for openhumanLocalAiAssetsStatus, which resolves to an object with null result and empty logs. This improves the test setup for local AI asset status handling. * refactor(SkillSetupModal): improve session mode handling and loading state - Updated the SkillSetupModal component to ensure session mode is determined after the first snapshot resolution, preventing premature defaults to the setup wizard. - Introduced a loading state to display a message while waiting for the skill setup status, enhancing user experience during the modal's initial render. - Refactored the SkillManager to throw errors for real failures during setup, ensuring proper error handling and user feedback. * refactor(Config): simplify logging for invalid proxy scope values - Consolidated the logging statement for invalid OPENHUMAN_PROXY_SCOPE values into a single line, improving code readability while maintaining the warning functionality. |
||
|
Steven EnamakelandGitHub
|
6465f3d314 |
feat(agent): sub-agents, reasoning→agentic routing, layered context pipeline (#474)
* Enhance agent architecture with sub-agent support and memory optimizations - Refactored the `Agent` struct to use `Arc` for shared ownership of the provider, tools, and tool specifications, enabling efficient memory management and concurrent access. - Introduced a `NullMemoryLoader` to optimize memory usage for sub-agents, allowing them to operate without incurring the cost of memory recall. - Added new methods in the `Agent` implementation to facilitate sharing of the provider, tools, and tool specifications with sub-agents, enhancing their operational efficiency. - Implemented a new `SystemPromptBuilder` method for constructing prompts specifically for sub-agents, ensuring they receive tailored context while minimizing unnecessary information. - Established a framework for loading custom agent definitions from TOML files, allowing for dynamic agent configuration and specialization. - Introduced a `ForkContext` to support efficient sub-agent execution in fork mode, leveraging shared resources for improved performance and reduced token usage. * Enhance agent definition management and sub-agent functionality - Introduced a global `AgentDefinitionRegistry` to manage built-in and custom agent definitions from TOML files, ensuring idempotent initialization. - Added new RPC handlers for listing, fetching, and reloading agent definitions, improving the flexibility of agent management. - Refactored the `Agent` struct to streamline sub-agent execution, including enhancements to the task execution flow and context handling. - Updated the orchestrator configuration to support fork mode for sub-agents, optimizing resource usage and performance. - Improved error handling and logging for agent definition loading and initialization processes, enhancing system reliability. * Add end-to-end test for sub-agent spawning and response integration - Implemented a new asynchronous test to validate the full path of a parent agent issuing a `spawn_subagent` tool call. - The test ensures that the sub-agent's output is correctly folded into the parent's response, verifying the interaction between the parent agent and the sub-agent. - Enhanced the `AgentDefinitionRegistry` to support global initialization of built-in agents, ensuring consistent behavior across tests. - Updated the handling of tool calls and memory configuration to facilitate the new test scenario, improving overall test coverage for agent interactions. * Enhance agent tool filtering with category support - Introduced a new `category_filter` in `AgentDefinition` to restrict tool visibility based on their category (System or Skill). - Updated the `from_archetype` function to apply the category filter for the `SkillsAgent` archetype. - Modified `SubagentRunOptions` to include a `category_filter_override` for dynamic filtering during sub-agent execution. - Enhanced the `filter_tool_indices` function to incorporate category filtering logic, ensuring tools are correctly filtered based on their defined categories. - Updated relevant tests to validate the new category filtering functionality, improving overall test coverage for agent interactions. * Implement layered context reduction pipeline for agent - Introduced a new `context_pipeline` module to manage a layered context reduction strategy, enhancing memory efficiency during agent interactions. - Added stages for tool-result budgeting, history trimming, microcompaction, autocompaction, and session memory extraction, each with specific triggers and cache implications. - Updated the `Agent` struct to include a `context_pipeline` field, ensuring state persistence across turns. - Enhanced the `AgentBuilder` to initialize the context pipeline by default. - Implemented tests to validate the functionality and stability of the context pipeline, ensuring consistent behavior across agent sessions. - Refactored relevant components to integrate the new context management features, improving overall agent performance and memory handling. * Enhance agent context pipeline with tool result budgeting and microcompaction - Renamed variable for clarity in tool execution result handling. - Implemented a new stage in the context pipeline to apply a byte budget to tool results, ensuring efficient memory usage. - Added logging for budget application, including details on original and final byte sizes. - Integrated microcompaction stages before tool calls to manage history and reduce memory footprint, with appropriate logging for outcomes. - Updated the agent's session memory management to track turn counts, facilitating better resource handling across iterations. * Refactor agent context pipeline for session memory extraction and tool call management - Simplified method calls in the `Agent` struct for clarity and efficiency. - Enhanced session memory extraction logic to spawn a background archivist sub-agent when thresholds are met. - Improved context pipeline handling for tool call recording and usage tracking. - Updated documentation and comments for better understanding of session memory extraction process. - Refactored microcompact function for cleaner code structure and readability. * refactor(agent): split agent.rs into focused submodules - Convert agent.rs (1988 lines) into agent/ folder with six files: * types.rs — Agent + AgentBuilder struct defs * builder.rs — AgentBuilder fluent API + Agent::from_config factory * turn.rs — turn lifecycle, tool dispatch, context pipeline wiring * runtime.rs — public accessors, run_single/run_interactive, helpers * tests.rs — integration tests with shared fakes * mod.rs — glue + top-level `run` convenience function - Drop misc external inspiration references from doc comments in the context_pipeline module and fork_context — the files now stand on their own design language. * fix(agent): address review comments on sub-agent + context pipeline PR Inline comment fixes: - definition.rs: YAML/TOML inconsistency — module doc, PromptSource, source bookkeeping, and load() all now uniformly document the TOML format. - subagent_runner.rs: render_subagent_system_prompt previously only appended PromptSource::Inline bodies, silently dropping PromptSource::File content. Thread the preloaded archetype_body through as an explicit &str parameter so both source variants render. Drops the unused SystemPromptBuilder + tools_for_prompt wiring while we're here. - prompt.rs: remove DateTimeSection from SystemPromptBuilder::for_subagent. Local::now() would make the sub-agent system prompt change per call and break KV-prefix cache stability. Document the invariant. Nitpick fixes: - agent/turn.rs: drop the no-op mark_extraction_started() call — the immediately-following mark_extraction_complete() clears the in-flight flag anyway. - context_pipeline/pipeline.rs: call guard.record_compaction_success() on microcompact success so a prior streak of autocompaction failures doesn't leave the circuit breaker tripped after a successful reduction. - context_pipeline/tool_result_budget.rs: remove the unnecessary out.clone() in the truncation return — capture final_bytes first, then move out. - definition_loader.rs: replace brittle reg.len() == 10 with assert!(reg.len() > 1) plus the existing targeted .get() checks. - executor.rs: tracing::warn! on unknown sandbox override values so typos surface during development; explicitly accept "none" and empty string as valid defaults. - fork_context.rs: add parent_context_visible_inside_scope test mirroring fork_context_visible_inside_scope, with minimal stub Provider/Memory impls so the test stays self-contained. - schemas.rs: drop redundant serde_json::to_value(serde_json::json!(...)) wrapping in handle_list_definitions + handle_get_definition. - event_bus/events.rs: add SubagentSpawned/SubagentCompleted/SubagentFailed cases to all_variants_have_correct_domain. - tools/ops.rs: add all_tools_includes_spawn_subagent regression test. - tools/spawn_subagent.rs: sort/dedup the known skill list in place instead of cloning into a second vec. Tests: 2316 passed / 0 failed (up from 2314; two new tests added). fmt + clippy clean on all touched files. * udpate prompts * Enhance AgentBuilder and runtime with event context and interactive CLI improvements - Added `event_context` method to `AgentBuilder` for setting `session_id` and `channel` for `DomainEvent`s, improving event tagging and correlation. - Updated `run_interactive` method in `Agent` to dispatch messages through `run_single`, ensuring consistent lifecycle event handling and error sanitization for interactive turns. * Optimize configuration handling in AgentBuilder by lazily creating Arc for full config in reflection hook. This change reduces unnecessary cloning when learning is enabled, improving performance. * Add fork-mode test for sub-agent spawning in agent - Introduced a new test, `turn_dispatches_spawn_subagent_in_fork_mode`, to validate the behavior of the agent when spawning a sub-agent in fork mode. - The test ensures that the parent agent correctly processes the sub-agent's output and maintains the expected response sequence. - Enhanced the test setup with a mock provider and memory configuration to simulate the agent's environment effectively. * Refactor sync RPC handling in skills to treat missing onSync as no-op - Updated the `handle_sync` function to log a debug message and return a no-op response when a skill does not implement the `onSync` handler, preventing unnecessary RPC errors for skills that do not require periodic syncs. - This change improves logging clarity and reduces error noise in logs and dashboards for skills that are not designed to handle sync operations. |
||
|
Steven EnamakelandGitHub
|
a1f8bc55c4 |
Improve upsell flow and retire legacy overlay app (#473)
* fix(autocomplete): disable autocomplete feature by default - Updated the default configuration for the Autocomplete feature to be disabled instead of enabled in both the frontend and backend configurations. This change aims to improve user experience by preventing unintended activations of the autocomplete functionality upon application startup. * feat(overlay): enhance overlay window functionality and responsiveness - Updated the OverlayApp component to dynamically adjust its size and position based on the overlay status (idle/active), improving user interaction. - Introduced new constants for overlay dimensions and margins, enhancing visual consistency. - Implemented hover effects to adjust opacity, providing better visual feedback. - Refactored window resizing and positioning logic to ensure the overlay remains user-friendly and visually appealing across different scenarios. - Updated macOS window level to NSScreenSaverWindowLevel for improved behavior in fullscreen and multi-space environments. * feat(dependencies): add objc2-core-graphics and related packages - Introduced `objc2-core-graphics` as a new dependency in the Cargo.toml for macOS support. - Updated Cargo.lock to include `objc2-metal`, `block2`, and `libc` as dependencies for enhanced functionality. - Refactored overlay window configuration to utilize `CGShieldingWindowLevel`, improving window behavior in macOS environments. * refactor(billing): remove storage limits and update plan budgets - Removed `storageLimitBytes` from the `PlanMeta` interface and all plan definitions, simplifying the billing structure. - Updated the `Free` plan to have zero budgets for monthly and weekly usage, aligning with the new billing strategy. - Adjusted the `BillingPanel` and related components to conditionally display budget information based on the updated plan values. - Enhanced the `InferenceBudget` and `PayAsYouGoCard` components to reflect changes in budget handling and improve user messaging. - Updated tests to ensure consistency with the new billing logic and removed references to storage limits. * feat(upsell): enhance GlobalUpsellBanner and PayAsYouGoCard components - Added the GlobalUpsellBanner component to the App, improving user visibility of upgrade options. - Refactored PayAsYouGoCard to better handle credit balance calculations, separating promo and top-up credits for clarity. - Updated the UpsellBanner styles for a more consistent visual presentation. - Introduced normalization functions in creditsApi to ensure robust handling of credit balance data. - Added tests for creditsApi to validate the normalization logic and prevent UI crashes with missing data. * feat(upsell): reintroduce GlobalUpsellBanner in App and enhance UpsellBanner styling - Added the GlobalUpsellBanner back into the App component to improve user visibility of upgrade options. - Updated the UpsellBanner component to include a new `rounded` prop for customizable styling. - Removed dismissible functionality from the GlobalUpsellBanner, streamlining the user experience. - Enhanced visual presentation by adjusting CSS styles for better consistency. * refactor(overlay): remove obsolete overlay files and configurations - Deleted unused files including .gitignore, index.html, package.json, postcss.config.js, README.md, tailwind.config.js, tsconfig.json, vite.config.ts, and yarn.lock from the overlay directory. - Removed all source files related to the overlay functionality, including App.tsx, main.tsx, parentCoreRpc.ts, styles.css, and various components. - Cleaned up the src-tauri directory by removing configuration files, icons, and capabilities related to the overlay, streamlining the project structure. - This commit enhances maintainability by eliminating legacy code and unused resources. * refactor(rewards): move DISCORD_INVITE_URL to a separate utility file - Refactored the Rewards component to import the DISCORD_INVITE_URL from a new links utility file, improving code organization and maintainability. - Created a new links.ts file to centralize URL constants, enhancing clarity and reusability across the application. * style(app): apply formatter hook fixes * chore(dependencies): remove @heroicons/react from yarn.lock - Deleted the entry for @heroicons/react@^2.2.0 from yarn.lock, streamlining dependency management and reducing potential conflicts. |
||
|
Steven EnamakelandGitHub
|
3d17bfb23d |
Refactor core cross-domain flows onto event bus (#468)
* Refactor core cross-domain flows onto event bus * feat(agent): enhance error handling and message processing - Introduced a new constant for maximum error message length in the Agent. - Added methods for comparing conversation messages and determining new entries for turns. - Implemented a function to sanitize error messages, improving clarity and consistency in error reporting. - Updated the `run_single` method to utilize the new error handling and message processing logic, ensuring better tracking of conversation history and error states. * feat(supervision): initialize global event bus and register health subscriber - Added initialization of the global event bus with default capacity to ensure channel health events have a live bus and subscriber target. - Registered a health subscriber to enhance monitoring capabilities within the supervised listener context. |
||
|
Steven EnamakelandGitHub
|
63b17ca55c |
refactor: remove dead frontend modules and obsolete API layers (#469)
* refactor: remove unused socket, agent tool registry, daemon health, and API service files - Deleted the `useSocket` hook, `AgentToolRegistry`, `DaemonHealthService`, and various API service files including `actionableItemsApi`, `apiKeysApi`, `feedbackApi`, `inferenceApi`, `managedDmApi`, and `settingsApi`. - This cleanup reduces code complexity and improves maintainability by removing obsolete components that are no longer in use. * feat: add knip configuration and commands to package.json - Introduced new scripts for running knip in development and production modes in both package.json files. - Added a knip.json configuration file to specify entry points and project files for dependency analysis. - Updated yarn.lock to include new dependencies related to knip, enhancing the project's dependency management capabilities. This commit improves the project's tooling for managing dependencies and ensures better code quality through automated checks. * refactor: remove unused components and clean up dependencies - Deleted several unused components related to intelligence features, including ActionPanel, InputGroup, SectionCard, and ValidatedField, to streamline the codebase. - Removed mock data and country data files that are no longer in use, enhancing maintainability. - Cleaned up the package.json by removing the @heroicons/react dependency, which is no longer required. - This commit improves the overall project structure and reduces complexity by eliminating obsolete code. * refactor: remove IntelligenceApiService and redefine ConnectedTool interface - Deleted the `IntelligenceApiService` class and its associated backend API methods to streamline the codebase. - Introduced a local definition of the `ConnectedTool` interface in `useIntelligenceApiFallback.ts` for better encapsulation and clarity. - This refactor enhances maintainability by eliminating unused code and consolidating relevant types within the appropriate context. * style: format knip config * chore(dependencies): update OpenHuman to version 0.52.0 in Cargo.lock * feat: implement Daemon Health Service for polling and state management - Introduced the `DaemonHealthService` class to poll the Rust core health snapshot and synchronize the frontend daemon store. - Added methods for setting up a health listener, parsing health snapshots, and updating the daemon store based on health data. - Implemented a timeout mechanism to handle disconnection scenarios, enhancing the reliability of the daemon's health monitoring. - This addition improves the application's ability to maintain an accurate representation of the daemon's health status in real-time. * chore(knip): update entry points in knip configuration - Modified the `entry` field in `knip.json` to include `src/main.tsx` alongside existing test specifications. - This change ensures that the main application file is included in dependency analysis, improving project structure and tooling. * refactor: streamline code and enhance readability across multiple modules - Consolidated multiple `replace` calls into single calls using arrays for improved efficiency in text processing. - Simplified default implementations for several structs, removing redundant code. - Updated query mapping in database interactions to enhance clarity and maintainability. - Improved logging and error handling by refining how state and error messages are processed. - Enhanced the readability of various functions by restructuring conditional checks and simplifying logic. These changes collectively improve code maintainability and performance across the application. * Merge remote-tracking branch 'origin/fix/cleanup' into fix/cleanup * fix: update error handling in bootstrap_after_login function - Changed the error parameter in the inspect_err closure to an underscore to indicate it is unused. - This minor adjustment improves code clarity and adheres to Rust conventions for unused variables. |
||
|
Steven EnamakelandGitHub
|
30eec2ad88 |
docs: comprehensive documentation for core Rust modules (#470)
* feat(core): enhance RPC controller and dispatch logic - Added comprehensive documentation for the core RPC controller and dispatch modules, detailing their purpose and functionality. - Introduced new functions for managing registered controllers and schemas, including validation and invocation methods. - Improved the structure of the `RpcOutcome` type to standardize response formats across domain-specific handlers. - Enhanced the local AI operations module with additional functionalities for agent interactions, model management, and audio processing. - Updated the dispatcher to better route RPC calls to their respective handlers, ensuring a more robust and maintainable architecture. These changes improve the clarity and usability of the RPC system, facilitating easier integration and interaction with various components of the OpenHuman platform. * docs: comprehensive documentation for core Rust modules * chore(dependencies): update OpenHuman to version 0.52.0 in Cargo.lock and add knip dependency in package.json |
||
|
Steven EnamakelandGitHub
|
acc6246e59 |
Refactor core-polled app state and screen intelligence status (#464)
* refactor(accessibility): remove device control and predictive input features from accessibility settings - Updated accessibility-related components and tests to eliminate device control and predictive input features. - Adjusted AccessibilityPanel and ScreenIntelligencePanel to reflect the removal of these features. - Modified related tests to ensure consistency with the updated accessibility status structure. - Cleaned up accessibility session parameters and state management to focus solely on screen monitoring. * refactor(accessibility): streamline featureOverrides state initialization - Simplified the initialization of featureOverrides state in AccessibilityPanel and ScreenIntelligencePanel components for better readability. - Consolidated parameter definitions in startAccessibilitySession to enhance clarity and maintainability. - Removed unnecessary re-exports in the screen_intelligence engine module to clean up the codebase. * chore(dependencies): update OpenHuman to version 0.51.19 in Cargo.lock * chore(dependencies): update OpenHuman version to 0.51.19 in Cargo.lock * feat(restart): implement core process restart functionality - Added a new `SystemRestartRequested` event to the `DomainEvent` enum to handle restart requests. - Introduced a `RestartSubscriber` that listens for restart events and manages the process respawn. - Created a `service_restart` function to publish restart requests via the event bus. - Updated service schemas to include a new `restart` controller with parameters for source and reason. - Enhanced documentation to reflect changes in behavior and added necessary code comments. * feat(accessibility): add last restart summary to Screen Intelligence Panel - Introduced `lastRestartSummary` to the accessibility state and updated relevant components to display the last successful core restart information. - Modified `PermissionsSection` and `ScreenIntelligencePanel` to include the new summary. - Updated tests to validate the display of the last restart summary and ensure proper state management during core restarts. - Refactored accessibility slice to handle the new restart summary in state updates. * feat(core): enhance startup process with restart delay and subscriber registration - Added a call to apply startup restart delay from environment variables in `run_core_from_args`. - Updated the `bootstrap_skill_runtime` function to register a `RestartSubscriber` for handling restart requests, ensuring consistent respawn logic across triggers. - Introduced a new `core_process` field in the `AccessibilityEngine` to track the core process status, including its PID and start time. - Implemented a helper function to capture the core process start time using `OnceLock` for efficient initialization. * feat(screen-intelligence): refactor accessibility state management and UI components - Replaced direct Redux state access with a new `useScreenIntelligenceState` hook across multiple components, including `AccessibilityPanel`, `ScreenIntelligencePanel`, and their respective subcomponents. - Streamlined permission and session handling by consolidating related functions and removing unnecessary dispatch calls. - Updated tests to mock the new state management approach, ensuring consistent behavior and validation of UI elements. - Removed the `SessionAndVisionSection` component to simplify the structure and improve maintainability. - Introduced a new API file for screen intelligence to encapsulate related functionality and improve code organization. * refactor(tests): clean up and optimize test files for accessibility and screen intelligence panels - Removed redundant imports and streamlined the structure of test files for `AccessibilityPanel` and `ScreenIntelligencePanel`. - Consolidated core process state initialization in test mocks for better readability. - Updated dependency imports and ensured consistent mocking of state management hooks across tests. - Enhanced the `ScreenPermissionsStep` component by improving the dependency array in the useEffect hook for better performance. * refactor(store): remove unused authentication and user management code - Deleted the `UserProvider`, `authSlice`, `authSelectors`, `userSlice`, `teamSlice`, and related test files to streamline the codebase. - This cleanup enhances maintainability by removing legacy code that is no longer in use. - Updated the store configuration to reflect the removal of these slices and ensure proper state management. * refactor(webhooks): reorganize types and remove legacy state management - Moved `TunnelRegistration` and `WebhookActivityEntry` types to a new `types.ts` file for better organization. - Updated imports in `TunnelList` and `WebhookActivity` components to reference the new types location. - Refactored `useWebhooks` hook to eliminate Redux state management in favor of local state, enhancing performance and reducing complexity. - Removed unused `aiSlice`, `inviteSlice`, and `webhooksSlice` along with their associated tests to streamline the codebase. * refactor(daemon): migrate state management from Redux to a custom store - Introduced a new `store.ts` file to manage daemon state, replacing the previous Redux slice. - Updated components and hooks to utilize the new state management approach, enhancing performance and reducing complexity. - Removed the legacy `daemonSlice` and associated Redux logic, streamlining the codebase. - Adjusted imports in various components and hooks to reference the new store structure. * refactor(screen-intelligence): integrate core state management and enhance status handling - Replaced direct state management in `useScreenIntelligenceState` with a new core state approach, utilizing `useCoreState` for improved performance and consistency. - Updated status fetching and permission handling to leverage the core state snapshot, streamlining the logic and reducing redundant API calls. - Introduced a new `CoreRuntimeSnapshot` interface to encapsulate runtime statuses, including screen intelligence, local AI, autocomplete, and service states. - Adjusted related components and hooks to align with the new state management structure, enhancing maintainability and readability. - Updated tests to validate the new runtime state structure and ensure proper functionality across the application. * refactor(components): reorganize imports and streamline function formatting - Moved the import of `Tunnel` and `tunnelsApi` in `TunnelList.tsx` for better organization. - Reformatted function definitions in `store.ts`, `useDaemonHealth.ts`, `useDaemonLifecycle.ts`, `useWebhooks.ts` for improved readability. - Cleaned up the structure of test files in `coreRpcClient.test.ts` by consolidating object properties for clarity. - These changes enhance code maintainability and readability across the application. * test(screen-intelligence): fix duplicate hook imports * fix(tests): update ScreenIntelligenceDebugPanel test to use baseState for refresh status and vision calls * refactor(invites): simplify error message rendering in Invites component - Consolidated the conditional rendering of the load error message in the Invites component for improved readability. - This change enhances the clarity of the code without altering functionality. * refactor(daemon): streamline state management and function definitions - Removed the `healthTimeoutId` from the `DaemonUserState` interface and related functions to simplify state management. - Converted several functions in `store.ts` to arrow function syntax for consistency and improved readability. - Updated the `Invites` component to handle asynchronous loading and error states more effectively, ensuring that in-flight requests are properly managed. - Refactored the `CoreStateProvider` to enhance the refresh logic and prevent multiple simultaneous refreshes. - Introduced a new `register_domain_subscribers` function in `jsonrpc.rs` to centralize event bus subscriber registration, improving code organization and maintainability. * fix: add debug logging, atomic restart guard, and idempotent subscriber registration - CoreStateProvider: add namespaced debug logger for polling failure diagnostics - service/bus.rs: add AtomicBool gate to prevent duplicate restart spawns - service/bus.rs: use OnceLock for idempotent RestartSubscriber registration - Invites.tsx: add debug log in loadInviteCodes catch block * style: apply prettier formatting to CoreStateProvider * fix: sanitize error logging, serialize refresh, and demote restart logs - CoreStateProvider: sanitize error objects in poll failure logs to avoid leaking tokens/headers - CoreStateProvider: move in-flight guard into refresh() via shared promise so all callers (poll, updateLocalState, storeSessionToken) are serialized - CoreStateProvider: log refreshTeams errors instead of swallowing them - service/bus.rs: demote duplicate-restart log to debug, omit reason from log output to avoid free-form text emission * style: apply cargo fmt to service/bus.rs |
||
|
Steven EnamakelandGitHub
|
d66ee0d4de |
feat: consolidate overlay into desktop app and add compact orb demo (#450)
* feat(overlay): implement overlay window functionality and related RPC integration - Added a new OverlayApp component to handle overlay-specific UI and functionality. - Introduced an overlay window configuration in tauri.conf.json, allowing for a transparent, always-on-top overlay. - Implemented parent RPC communication for the overlay to interact with the main application. - Updated main.tsx to conditionally render the OverlayApp based on the current window context. - Enhanced CSS styles to support the overlay's visual requirements. This commit establishes the foundation for overlay functionality, improving user experience with a dedicated interface for specific tasks. * refactor(overlay): remove overlay functionality and related configurations - Deleted the overlay module and its associated files, including process management and configuration settings. - Removed environment variable checks and overlay-related logic from the core process and configuration schema. - Updated documentation to reflect the removal of overlay features, simplifying the codebase and improving maintainability. This commit streamlines the application by eliminating unused overlay components, enhancing overall performance. * feat(overlay): enhance overlay bubble functionality and styling - Added a new CSS animation for overlay bubble appearance, improving visual feedback. - Introduced an OverlayBubble interface to manage bubble properties such as tone and text. - Updated OverlayApp component to include a new OverlayBubbleChip for displaying messages with dynamic styling based on tone. - Adjusted overlay window dimensions in tauri.conf.json for a more compact design. This commit improves the user experience by providing visually distinct overlay messages and a refined interface. * feat(rotating-tetrahedron): add inverted color support and refactor canvas component - Introduced an optional `inverted` prop to the `RotatingTetrahedronCanvas` component, allowing for dynamic color changes based on the prop value. - Updated fill and edge materials to reflect the inverted state, enhancing visual customization. - Refactored the component to improve readability and maintainability by utilizing the new prop in the rendering logic. - Adjusted the effect dependencies to include the `inverted` prop for proper reactivity. This commit enhances the user experience by providing a more flexible and visually appealing tetrahedron display. * fix(rotating-tetrahedron): adjust opacity and emissive intensity for inverted colors - Updated the opacity of the fill material in the RotatingTetrahedronCanvas component to enhance visual clarity when the inverted prop is true. - Reduced the emissive intensity for the inverted state to improve the overall appearance of the tetrahedron. This commit refines the visual representation of the rotating tetrahedron, ensuring better contrast and aesthetics based on user preferences. * feat(rotating-tetrahedron): enhance dynamic color handling and performance - Implemented useRef hooks for fill and edge materials in the RotatingTetrahedronCanvas component to optimize rendering performance. - Updated the useEffect hook to adjust material properties based on the inverted state, improving visual consistency. - Refactored animation speed handling to utilize a reference for smoother updates. - Cleaned up resource management by ensuring materials are disposed of correctly when the component unmounts. This commit enhances the visual fidelity and performance of the rotating tetrahedron, providing a more responsive and visually appealing experience. * fix(overlay): adjust bubble alignment and overlay positioning - Changed the text alignment of the OverlayBubbleChip component from left to right for improved readability. - Updated the vertical positioning logic in the Tauri overlay to account for a right margin, ensuring consistent placement of the overlay window. These adjustments enhance the visual presentation and positioning of overlay elements, contributing to a better user experience. * fix(overlay): update overlay dimensions and bubble styling - Adjusted the overlay dimensions for a more refined appearance. - Modified the bubble tone classes for improved color consistency and readability. - Enhanced the text size and line height in the OverlayBubbleChip component for better visual clarity. - Updated the orb button size and styling to enhance user interaction. These changes contribute to a more polished and user-friendly overlay experience. * feat(overlay): enhance overlay scenario handling and text display - Introduced a new scenario management system in the OverlayApp component, allowing for dynamic cycling between different overlay states. - Added a new text display feature for scenario two, providing real-time feedback as the text is typed out. - Refactored the bubble rendering logic to accommodate the new scenario structure, improving the overall user interaction experience. These changes enhance the functionality and interactivity of the overlay, making it more engaging for users. * fix(overlay): reorder demo scenarios * fix(overlay): update overlay dimensions and improve text display logic - Adjusted overlay dimensions for better visual consistency. - Enhanced text display in OverlayBubbleChip to show text progressively based on bubble content. - Refactored the handling of scenario text in OverlayApp to streamline the display logic. These changes contribute to a more polished and engaging user experience in the overlay. * refactor(overlay): simplify type parameters in RPC functions - Removed unnecessary generic type parameter from `unwrapCliCompatibleJson` and `callParentCoreRpc` functions for improved clarity and conciseness. - These changes enhance code readability and maintainability without altering functionality. |
||
|
|
0b23ae6b96 |
fix(voice): resolve dictation pipeline in embedded Tauri app (#466)
* fix(voice): guard dictation_listener when voice_server is active macOS only supports one rdev::listen() global event tap per process. When voice_server.auto_start is true, skip starting the separate dictation_listener — the voice server owns the single listener and forwards hotkey events itself. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(voice): add TRANSCRIPTION_BUS broadcast channel Make publish_dictation_event public so the voice server can forward hotkey events. Add a new TRANSCRIPTION_BUS broadcast channel with subscribe_transcription_results() and publish_transcription() for delivering completed transcriptions to frontend clients via Socket.IO. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(voice): forward hotkey events and route transcription delivery In the voice server's hotkey handler, forward events to the dictation bus so Socket.IO clients receive dictation:toggle even without the separate dictation_listener running. In process_recording_bg, detect when the OpenHuman app is focused and deliver transcription via Socket.IO instead of OS-level Cmd+V paste, preventing text from disappearing into the unfocused WebView. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(voice): bridge transcription results to Socket.IO Subscribe to TRANSCRIPTION_BUS and emit dictation:transcription events to all connected Socket.IO clients. This completes the Rust-side pipeline for delivering transcribed text to the frontend. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(socket): queue listeners registered before socket connects Add a pendingListeners queue to socketService so that on()/once() calls made before the socket is established are replayed once the connection opens, preventing silently dropped event listeners. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(voice): use dedicated unauthenticated socket for dictation events Replace the auth-gated socketService dependency with a direct Socket.IO connection to the core process (127.0.0.1:7788). This bypasses the SocketProvider auth requirement and ensures dictation:toggle and dictation:transcription events are received regardless of login state. Dispatches the existing dictation://insert-text DOM event to bridge transcribed text into the Conversations chat input. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(voice): fallback to default audio config when preferred config fails macOS may advertise a 16kHz F32 config as supported but reject it at stream creation time (known cpal quirk). Add a fallback path that retries with the device's default_input_config(), handling F32, I16, and U16 sample formats with proper resampling. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(voice): add 3s timeout on Ollama LLM cleanup Wrap the Ollama inference call in a 3-second tokio::time::timeout so dictation feels responsive. If cleanup doesn't complete in time, fall back to raw Whisper text immediately instead of blocking for 2+ minutes. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
|
f0118ab674 |
fix(autocomplete): graceful shutdown on app exit (#460)
* fix(autocomplete): graceful shutdown on app exit Stop the autocomplete engine and quit the Swift overlay helper process when the core receives a shutdown signal, preventing orphan processes. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor(core): extract shutdown logic into generic facility Move domain-specific autocomplete cleanup out of the jsonrpc adapter into a new `core::shutdown` module with a hook registry. Adds SIGTERM handling alongside SIGINT via `tokio::select!` on Unix platforms. Addresses CodeRabbit review feedback on PR #460: - jsonrpc.rs stays transport-only (no domain logic) - Process responds to both SIGINT and SIGTERM gracefully Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(autocomplete): suppress duplicate error notifications and auto-stop after repeated failures The autocomplete polling loop was showing an error notification badge on every single refresh cycle when a dependency was unavailable (e.g. Ollama not running, macOS Automation permission denied). This caused floods of identical macOS notifications. Changes: - Track last notified error message; skip badge if identical to previous - Count consecutive errors; auto-stop engine after 5 failures with a clear log message, preventing endless notification spam - Reset counters on successful refresh or engine restart Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
Mega MindandGitHub
|
dc5e7adeb6 |
fix(auth): update RPC method names for authentication calls (#463)
* fix(auth): update RPC method names for authentication calls Refactor authentication-related RPC method names to use underscores instead of dots for consistency. Updated methods include `get_state`, `get_session_token`, `clear_session`, and `store_session`. chore: update OpenHuman version to 0.51.19 style: standardize string formatting in quickjs_libs/bootstrap.js and other files - Replace single quotes with double quotes for string literals in various functions. - Ensure consistent formatting across console logging and error handling. fix(config): improve token retrieval logic in ops_core.rs - Enhance the logic for retrieving the active session token from the credentials store, accommodating user-specific directories. * test: align auth and OAuth assertions with current behavior Update stale test expectations for underscore-style auth RPC methods and light-theme OAuth button classes, and make the bypass-login E2E assertion resilient to the current auth persistence model. Made-with: Cursor * chore: apply formatter output for login flow spec Include Prettier formatting adjustments produced by the pre-push hook so the branch can pass repository push checks cleanly. Made-with: Cursor |
||
|
|
9764a875e8 |
fix(subconscious): seed defaults into per-user workspace + fix Intelligence page stale log (#462)
* fix(subconscious): seed defaults and spawn heartbeat on startup The subconscious engine was only constructed lazily on the first engine-routed RPC (trigger, tasks_add, status). Because handle_tasks_list bypasses the engine and reads the store directly, a fresh install showed an empty Subconscious panel until the user clicked "Run now", even though SubconsciousEngine::new() seeds the 3 default system tasks on construction. Separately, HeartbeatEngine::run() — the periodic tick loop — was never spawned in production code. The only callers of HeartbeatEngine were tests, so ticks never fired automatically; users had to trigger each evaluation manually. Both issues are fixed together in run_server_inner, following the existing start_if_enabled pattern used by voice, screen_intelligence, and autocomplete: 1. Call get_or_init_engine() at startup to construct the SubconsciousEngine eagerly, which runs seed_default_tasks via from_heartbeat_config. Construction is idempotent via OnceLock; seeding is idempotent by title match, so repeat startups do not duplicate the defaults. 2. Construct HeartbeatEngine with the heartbeat config and workspace_dir, then tokio::spawn heartbeat.run() so the periodic tick loop runs for the process lifetime. The loop re-acquires the shared engine via get_or_init_engine() on each tick. Guarded by config.heartbeat.enabled so users who disable the heartbeat get neither startup seeding nor the background loop. Add engine_construction_seeds_default_tasks integration test that locks in the invariant: constructing SubconsciousEngine on a fresh workspace_dir must leave the 3 default system tasks in the store, with no tick, trigger, or explicit seed call. Also asserts that reconstructing the engine on the same workspace does not duplicate the defaults. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(subconscious): defer engine bootstrap until after login Default system tasks seeded at sidecar startup into the pre-login global workspace (`~/.openhuman/workspace/`) instead of the per-user workspace (`~/.openhuman/users/<id>/workspace/`) the UI reads from after login. The engine singleton is built lazily via `get_or_init_engine()` and cached in a `OnceLock`. `Config::load_or_init` resolves `workspace_dir` from `active_user.toml` — which does not exist until after login. When the engine was constructed on startup it therefore seeded into the global default, then the frozen singleton kept pointing at that path for the rest of the session while RPC handlers like `tasks_list` re-loaded config per call and read from the correct per-user path, silently returning an empty list. Fix: - `subconscious/global.rs`: add `bootstrap_after_login()` (idempotent via `BOOTSTRAPPED: AtomicBool`) which builds the engine against the now-correct per-user workspace and spawns the heartbeat loop. Track the heartbeat `JoinHandle` in a static so it can be aborted cleanly. Add `reset_engine_for_user_switch()` that aborts the heartbeat, clears the engine option, and resets the bootstrap flag. - `core/jsonrpc.rs`: replace the unconditional eager init on startup with a conditional one that only bootstraps if `active_user.toml` already exists (so a user logged in from a previous session still gets the engine up immediately after restart). - `credentials/ops.rs`: call `bootstrap_after_login()` at the end of `verify_and_store_session` so a fresh login triggers seeding against the per-user workspace. Call `reset_engine_for_user_switch()` in `clear_session` so logout tears down the engine + heartbeat loop and a subsequent login rebuilds them against the new user. Verified locally: sidecar restart with no `active_user.toml` logs "bootstrap deferred — waiting for login"; post-login logs "seeded 3 tasks on init" + "heartbeat periodic loop spawned"; and `subconscious.tasks_list` returns the 3 system defaults from the per-user DB. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(subconscious): bound config load + guard frontend poll Two related fixes for the Intelligence page freezing on a stale subconscious activity-log snapshot while ticks kept progressing in the sidecar. Root cause (backend): the subconscious RPC handlers were the only outlier in the entire JSON-RPC surface that called the raw `Config::load_or_init()` instead of the shared `load_config_with_timeout()` wrapper that every other domain schemas.rs uses (cron, webhooks, voice, team, skills, service, referral, doctor, …). `load_or_init` constructs a fresh `SecretStore` and runs a chain of `decrypt_optional_secret` calls on every invocation, which may IPC to the OS keychain — slow, unbounded, no caching. Under the Intelligence page's 3-second poll (4 parallel RPCs × ~7 keychain round-trips each = ~28 keychain calls every 3s), this pileup was enough to pin the frontend's `Promise.all` past the poll interval. Root cause (frontend): `useSubconscious.refresh()` uses `fetchingRef` as an in-flight guard. The ref is only cleared inside the `finally` block that runs after `Promise.all` settles. With no per-RPC timeout on the client side either, a single slow backend call would leave the ref stuck `true`, and every subsequent 3s `setInterval` tick would silently early-return at the top of `refresh`. The poller kept firing, but every call was a no-op — so the UI froze on whatever snapshot it last successfully fetched, even though the backend was still ticking through new decisions. Backend fix (`src/openhuman/subconscious/schemas.rs`): - Replace the local `load_config()` helper body to delegate to `crate::openhuman::config::load_config_with_timeout()`. Matches the 28 other domain schemas.rs files and brings subconscious handlers under the same 30s bound used everywhere else. Frontend fix (`app/src/hooks/useSubconscious.ts`): - Add a `withTimeout` helper (2.5s per-RPC, strictly less than the 3s poll interval) that races each of the 4 parallel RPCs against a timeout and resolves `null` on timeout — matching the existing `.catch(() => null)` contract so downstream setState logic is unchanged. - Clear `fetchingRef.current = false` in the useEffect cleanup so a late-returning request or a React Strict Mode double-mount in dev can't leave the ref stuck `true` for the next mount. Defense in depth: the backend bound prevents a permanent hang and matches repo conventions, while the frontend bound guarantees the 3s poll loop can never be pinned beyond one tick regardless of server-side latency. Verified locally — `cargo check` clean, `tsc --noEmit` clean, all 18 pre-existing warnings in unrelated modules. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style(jsonrpc): cargo fmt the startup bootstrap block CI ran `cargo fmt --all -- --check` and flagged the conditional bootstrap block in `run_server_inner` — `let already_logged_in` should fold onto one line, the `.and_then` closure body should inline, the `match ... .await` chain should fold, and the short log!() calls should not break across lines. No behavior change. Fixes three jobs on PR #462 that were all failing at the same `cargo fmt --all -- --check` step (Rust Quality, Rust Tests, Type Check TypeScript — the last one chains cargo fmt after its prettier check). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
|
fa5f822f95 |
feat(subconscious): stabilize heartbeat + subconscious loop (#392) (#437)
* feat(subconscious): stabilize heartbeat + subconscious loop (#392) - Enable heartbeat by default (enabled=true, inference_enabled=true, 5min interval) - Seed system tasks on engine init, not first tick - SQLite-backed task/log/escalation persistence - Overlap guard with generation counter — stale ticks are cancelled - Single log entry per task per tick, updated in place (in_progress → act/noop/escalate/failed/cancelled) - Rate-limit retry (429 only) for agentic-v1 cloud model calls - Approval gate: unsolicited write actions on read-only tasks require user approval - Analysis-only mode for agentic-v1 on read-only escalations - Non-blocking status RPC — reads from DB, never blocks on engine mutex - Frontend: system vs user task distinction, toggle switches, expandable activity log - Frontend: 3s auto-poll on Subconscious tab, skill-related escalation navigation - Consecutive failure counter in status (resets on success) - last_tick_at only advances on successful evaluation - Missing LLM evaluation fallback — unevaluated tasks default to noop - Docs: subconscious.md architecture guide, memory-sync-functions.md reference Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: fix Prettier formatting for subconscious frontend files Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ci: retrigger checks Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(heartbeat): use disabled config in run_returns_immediately_when_disabled test HeartbeatConfig::default() has enabled: true, so run() entered the infinite loop and never returned — hanging the test (and CI) indefinitely. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(subconscious): remove HEARTBEAT.md task import, use SQLite as sole task source Tasks are now managed exclusively in SQLite via the Subconscious UI. HEARTBEAT.md is retained for instructions/context only, not as a task list. Situation report now reads pending tasks from SQLite instead of HEARTBEAT.md. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: cargo fmt on subconscious engine Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
|
0f578382d1 |
fix(autocomplete): auto-start engine when config enabled (#412) (#442)
* fix(autocomplete): add start_if_enabled for engine auto-start at boot (#412) The autocomplete engine was never started automatically when config had autocomplete.enabled = true. Add start_if_enabled() that checks config and starts the global engine singleton during core process startup. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(autocomplete): wire engine startup into core server init (#412) Call start_if_enabled() after config load in the JSON-RPC server so the autocomplete engine runs automatically when the core process boots with autocomplete enabled. Remove stale E2E test assertions that conflicted with the new startup path. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix(autocomplete): auto-start engine when enabled via set_style RPC (#412) When the frontend enables autocomplete through set_style(enabled=true), automatically start the engine so suggestions begin immediately without requiring a separate start call or app restart. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> |
||
|
Mega MindandGitHub
|
371bcd34ea |
Feat/chat issue (#441)
* feat: display app version in settings panel * fix(onboarding): auto-refresh accessibility state after grant (#351) * style(onboarding): apply formatter for issue #351 fix * fix(onboarding): ESLint + typed mock for ScreenPermissionsStep; clear flag in handler Consolidate tauriCommands imports and drop redundant mock cast. Handle granted accessibility in focus/visibility callback instead of a follow-up effect. Made-with: Cursor * feat(env): add support for custom dotenv path and update dependencies - Introduced an optional environment variable `OPENHUMAN_DOTENV_PATH` to specify a custom path for dotenv files, enhancing configuration flexibility. - Updated `Cargo.toml` to include the `dotenvy` dependency for improved dotenv file handling. - Enhanced the `.env.example` file with a new comment for the custom dotenv path. - Added data-testid attributes and button types in `SkillDebugModal` and `Skills` components for better testability. - Created new tests for Gmail and Notion third-party skills to ensure proper functionality of sync and debug tools. - Added documentation for memory sync functions to clarify usage patterns and function details. * fix: address CodeRabbit review on PR #441 - Dotenv: treat empty OPENHUMAN_DOTENV_PATH as unset; propagate from_path errors - Document OPENHUMAN_DOTENV_PATH parent-env requirement in .env.example - Memory docs: MD040 fence language; clarify skill namespace vs integration id - QuickJS bootstrap: modern helpers, generic platform.notify log, template URLs - Skills UI: type=button on close/settings; async waitFor in sync tests - Gmail OAuth e2e: workspace env matches MemoryClient; env/engine drop guards; redact secrets from logs - Add replace_global_engine for test teardown Made-with: Cursor |
||
|
YellowSnnowmannandGitHub
|
90fac95d7a |
Fix: telegram replies (#436)
* feat(config): enhance world-readable config warning mechanism - Introduced a new static variable to track previously warned world-readable config files, preventing duplicate warnings. - Updated the warning logic to only log a warning for each unique world-readable config file, improving log clarity and reducing noise. - Added new `ChannelReactionReceived` and `ChannelReactionSent` events to the DomainEvent enum, expanding event handling capabilities in the event bus. - Included tests for the new reaction events to ensure proper functionality and integration. * feat(logging): add log file constraints and event filtering - Introduced functions to parse log file constraints from environment variables and filter log events based on these constraints. - Enhanced the `init_for_cli_run` function to apply the new filtering logic, improving log management and clarity. - Updated the `conversation_history_key` function to include thread context for Telegram, ensuring accurate message targeting. - Added a new trait method `supports_reactions` to the `Channel` trait, indicating support for emoji reactions. - Implemented integration tests for Telegram channel features, including reaction handling and thread message forwarding. * feat(telegram): enhance message handling with reactions and typing indicators - Added support for emoji reactions in Telegram responses, allowing for contextual acknowledgment of user messages. - Implemented a decision heuristic for when to use reactions, improving user interaction quality. - Introduced a typing indicator that activates immediately upon receiving a message, providing instant feedback to users. - Updated the channel delivery instructions to include new reaction syntax and guidelines for usage. - Enhanced tests to cover new reaction handling and message acknowledgment features, ensuring robust functionality. * fix(tests): update route key for Telegram message handling tests - Changed the route key in tests from `telegram_alice` to `telegram_alice_chat-1` to match the updated `conversation_history_key` format for Telegram. - This adjustment ensures accurate routing and consistency in message handling tests. * refactor(tests): streamline message handling in runtime tool calls - Refactored the message handling tests to utilize a `ChannelMessage` struct for improved clarity and maintainability. - Updated the route key generation to use the `conversation_history_key` function, ensuring consistency in message routing. - Simplified the invocation of `process_channel_message` by directly passing the constructed message, enhancing readability. * fix(telegram): enhance finalize_draft method to support thread context - Updated the `finalize_draft` method in the `Channel` trait and its implementation for `TelegramChannel` to accept an optional `thread_ts` parameter, allowing for message threading. - Adjusted related message handling functions to utilize the new parameter, ensuring proper message context during sending. - Modified tests to reflect changes in the `finalize_draft` method signature, enhancing the robustness of message handling in threaded conversations. * refactor(tests): ran format |
||
|
YellowSnnowmannandGitHub
|
45a821645a |
feat(refer) : Implement referral system with UI components and API integration (#430)
* Implement referral system with UI components and API integration - Added to document the referral system, including reward structure, rules, data model, migration, core services, and API endpoints. - Created component to display referral stats and allow users to apply referral codes. - Integrated referral functionality into the onboarding process with for applying referral codes. - Updated page to include the new . - Implemented API calls in for fetching referral stats and applying referral codes. - Added tests for the referral API to ensure proper functionality and data normalization. - Introduced device fingerprinting for referral code application to prevent abuse. This commit establishes a comprehensive referral system, enhancing user engagement and incentivizing referrals. * Update OLLAMA_BASE_URL to local development address * Enhance referral system and onboarding process - Added a new function to format reward rates from basis points to percentage for better display in the ReferralRewardsSection. - Improved loading state management in the referral stats loading process to prevent race conditions. - Updated the Onboarding component to handle referral step skipping more effectively, ensuring a smoother user experience. - Fixed a typo in the WelcomeStep component's button label for clarity. - Enhanced error handling in the referral API to provide clearer feedback on failures. These changes improve the usability and reliability of the referral system and onboarding experience. |
||
|
Steven EnamakelandGitHub
|
4ee518cf31 |
feat(tree-summarizer): hierarchical summary tree module with CLI (#423)
* feat(tree-summarizer): implement hierarchical summarization engine and event handling - Introduced a new `tree_summarizer` module to manage hierarchical time-based summaries, organizing data into a tree structure (root → year → month → day → hour). - Added functionality to ingest raw content, summarize it into hour leaves, and propagate summaries upward through the tree. - Implemented event handling for summarization completion and tree rebuild events, enhancing observability and modularity. - Created RPC operations for ingesting content, triggering summarization, querying the tree, and retrieving tree status. - Added comprehensive tests to ensure the reliability of the summarization process and event handling. This update significantly enhances the summarization capabilities of the system, allowing for efficient data organization and retrieval. * feat(tree-summarizer): add CLI support for tree summarization commands - Introduced a new `tree-summarizer` command to the CLI, allowing users to ingest content, run summarization jobs, query the summary tree, check status, and rebuild the tree. - Updated the CLI help documentation to include the new command and its subcommands. - Added a new module `tree_summarizer_cli` to encapsulate the tree summarization functionality. This enhancement improves the usability of the summarization features, providing a streamlined interface for managing hierarchical summaries directly from the command line. * style: apply cargo fmt to tree_summarizer module * feat(tree-summarizer): implement TreeSummarizerEventSubscriber for observability logging - Added a new `TreeSummarizerEventSubscriber` to log events related to tree summarization, enhancing observability. - Updated the `start_channels` function to register the new subscriber. - Refactored the `run_summarization` function to group buffered entries by hour and publish events upon completion of summarization. - Improved documentation and added tests for the new subscriber functionality. This update aims to provide better insights into the summarization process and facilitate future cross-module workflows. * refactor(tree_summarizer): streamline buffer backup and function signature - Simplified the buffer backup process by consolidating the rename operation with context handling for better error reporting. - Cleaned up the function signature of `derive_node_ids_from_hour_id` for improved readability. These changes enhance code clarity and maintainability within the tree summarization engine. * feat(tree_summarizer): enhance tree summarization with metadata support - Updated the `tree_summarizer_ingest` function to accept an optional metadata parameter, allowing users to include additional context during content ingestion. - Refactored related functions to validate and handle metadata, improving the overall robustness of the summarization process. - Adjusted the buffer write functionality to store metadata alongside content, enhancing the data structure for future retrieval and processing. These changes aim to enrich the summarization capabilities and provide more context for ingested content. * refactor(tree_summarizer): improve error message formatting in node ID validation - Enhanced the formatting of error messages in the `validate_node_id` function for better readability and consistency. - Adjusted the string formatting to use multi-line syntax, improving clarity in error reporting. - Minor formatting changes in the `strip_buffer_frontmatter` function to enhance code readability. These changes aim to improve the maintainability and clarity of error handling within the tree summarization module. * refactor(tree_summarizer): enhance buffer management and summarization process - Replaced the buffer draining mechanism with a non-destructive read approach, allowing for safer data handling during summarization. - Introduced a new `buffer_delete` function to explicitly manage the deletion of buffer entries after successful processing. - Updated the `run_summarization` function to reflect these changes, ensuring that buffer entries are only deleted after durable writes are confirmed. - Improved the backup process for the buffer directory during tree rebuilds, ensuring it is preserved outside the tree structure. These modifications aim to improve data integrity and clarity in the summarization workflow. * refactor(tree_summarizer): improve markdown parsing and timestamp handling - Updated the `parse_node_markdown` function to trim trailing whitespace from the body after splitting frontmatter, enhancing data cleanliness. - Modified test cases to use specific timestamps instead of the current time, ensuring consistent and predictable test results. - Adjusted assertions in tests to reflect the new timestamp-based ordering of entries. These changes aim to improve the robustness of markdown parsing and the reliability of test outcomes in the tree summarization module. |
||
|
Steven EnamakelandGitHub
|
0609493e1a | Add RAM-tiered local AI presets (#425) | ||
|
Steven EnamakelandGitHub
|
cd2a4a9a87 |
feat(screen-intelligence): OCR-only mode without vision model (#424)
* feat(settings): add 'Use Vision Model' option to Screen Intelligence Panel - Introduced a new checkbox in the Screen Intelligence Panel to toggle the use of a vision model for richer context extraction from screenshots. - Updated state management to handle the new option and integrated it into the configuration and processing logic. - Adjusted related tests and configurations to support the new feature, ensuring compatibility across the application. * feat(cli): add --no-vision-model option for screen intelligence - Introduced a new command-line option `--no-vision-model` to allow users to skip the vision model and use OCR and text LLM only. - Updated the CLI options parsing to handle the new flag and modified the bootstrap logic to respect this setting. - Enhanced usage documentation to reflect the new option and its alias `--ocr-only` for clarity. * fix(screen-intelligence): read use_vision_model from engine runtime config The processing worker was reading use_vision_model from the persisted config file (Config::load_or_init), so the CLI --no-vision-model flag had no effect. Now reads from the engine's in-memory runtime config which the CLI correctly overrides via apply_config(). Also moves image compression before OCR pass. * fix: add use_vision_model to test fixtures and fix rustfmt Add the new use_vision_model field to all AccessibilityConfig test fixtures so TypeScript compilation passes. Also includes rustfmt auto-fix for screen_intelligence_cli.rs. |
||
|
|
94f7531d69 |
Make QuickJS runtime fully synchronous to fix async deadlock (#422)
* feat(sync): implement background sync handling in event loop - Introduced a mechanism to track background sync status with a new `sync_in_flight` flag. - Updated the event loop to check for sync completion and persist state to memory upon completion. - Modified the `handle_sync` function to fire the `onSync` handler in the JS runtime asynchronously, allowing for immediate return while the sync process runs in the background. - Enhanced logging to provide feedback on sync status and completion. * fix(net): disable connection pooling in HTTP client to prevent hanging on POST requests through staging proxy * Enhance promise handling in JS call processing - Added logging to track promise resolution progress and timeout events. - Implemented a polling mechanism to drive the QuickJS job queue until promises resolve or timeout occurs. - Introduced debug information logging for stalled promises to aid in troubleshooting. - Improved feedback during polling to indicate ongoing operations. This update aims to improve the reliability and debuggability of asynchronous JavaScript calls within the application. * Refactor JS fetch implementation for synchronous behavior - Updated the `fetch` function in the QuickJS library to operate synchronously from the JavaScript perspective, blocking the thread until the HTTP request completes. - Enhanced error handling and logging for HTTP requests, including timeouts and response details. - Removed the previous asynchronous implementation to streamline the fetch operation. - Cleaned up the code by removing unused comments and improving readability. This change aims to improve the consistency and reliability of network operations within the application. * Fix Rust formatting in ops_net.rs Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Steven Enamakel
|
ca4eb39e9b | fix(oauth): enhance logging to include Notion-Version in fetch requests |