mirror of
https://github.com/tinyhumansai/openhuman.git
synced 2026-07-28 13:32:23 +00:00
fc4b97abc2d64f220209814b8b44726ecc002f4d
60
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Mega MindandGitHub
|
d2f045769f | test(notifications): add Phase 4 RPC and dismiss reducer coverage (#878) | ||
|
|
95504d4b09 |
test: add 196 tests across MCP, services, utils, autocomplete (#855)
Co-authored-by: Jwalin Shah <jshah1331@gmail.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai> |
||
|
Steven EnamakelandGitHub
|
7bd8f9d4c1 | ci: parallelize rust tests, dedupe typecheck/clippy/sentry across workflows (#895) | ||
|
VectorJetandGitHub
|
a96d9da3a4 | chore: migrate from yarn to pnpm (#886) | ||
|
Steven EnamakelandGitHub
|
3862b1bb1c | fix(tests): run webview_apis mock bridge on a dedicated runtime (#893) | ||
|
Mega MindandGitHub
|
11c67a70b9 | feat(notifications): add dismiss/stats RPC, DomainEvents, and triage bus integration (#875) | ||
|
Mega MindandGitHub
|
208c276a3e | feat(notifications): bridge CEF providers into core ingest pipeline with dedup (#874) | ||
|
|
b329e45cdb |
feat(skills): uninstall for user-scope SKILL.md skills (#781) (#833)
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com> |
||
|
Steven EnamakelandGitHub
|
500ddc2a8a | feat(webview_apis): WebSocket bridge for live-webview APIs, Gmail first (#869) | ||
|
|
629b4ccb07 |
test(memory_tree): unit tests for retrieval RPC handlers (#710) (#839)
- Add JSON-RPC handlers for source, global, and topic-based memory retrieval. - Integrate Ollama embeddings for semantic reranking of chunks and summaries. - Implement 15 unit tests for RPC handlers covering parameter parsing and PII redaction. - Redact PII from logs by removing raw source, entity, and node identifiers. - Fix BFS traversal for drill-down and deduplicate results in topic queries. - Add configuration for embedding endpoints, models, and strictness modes. Co-authored-by: sanil-23 <sanil@vezures.xyz> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai> |
||
|
|
5e660f2fe8 |
feat(core): memory namespaces, recall citations, provider_surfaces RPC (#803)
Co-authored-by: Jwalin Shah <jshah1331@gmail.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai> |
||
|
|
3bb714bf96 |
feat(webview): native OS notifications from embedded webview apps (#714) (#727)
* feat(webview_accounts): native OS notifications from embedded webviews (#714) Forward CEF notification intercept payloads to tauri-plugin-notification, prefixing the title with the provider label so the source of each toast is obvious at a glance. Honour `silent` (skip toast, still record route), `icon` (passed through to the native builder), and `tag` (used as the dedup key, with a monotonic timestamp fallback for untagged payloads). Record a NotificationRoute keyed by `{provider}:{account_id}:{tag_or_uuid}` so a future click hook (UNUserNotificationCenter / notify-rust on_response) can route the OS click back to the source account. Entries are cleared on webview_account_close / _purge to bound map growth. Expose webview_notification_permission_state / _request commands mapping tauri::plugin::PermissionState onto the web API triple. Non-cef stubs return "default" so the frontend can call the same invoke names on both runtimes. Wire notification:allow-* capabilities so the plugin can be invoked from the webview. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(accounts): wire notification permission + click bridge (#714) Round-trip the OS notification permission once per session on first account open via the new invoke pair. Attach a dormant notification:click listener that dispatches setActiveAccount and brings the main window to front when a platform click hook starts emitting the event — contract matches the Rust NotificationRoute shape so the emit side is a one-liner. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: sync Cargo.lock to 0.52.26 after version bump Lockfile picked up the pending 0.52.26 version bump from Cargo.toml while building the notification feature. No dependency graph change. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat(notifications): add notification bypass for embedded webview apps (#679) - Add NotificationBypassPrefs (global DND, per-account mute, bypass-when-focused) to WebviewAccountsState with thread-safe AtomicBool window focus tracking - Evaluate all three bypass conditions inside forward_native_notification before showing OS toast; each suppression path logs at debug with [notify-bypass] prefix - Add four new Tauri commands: webview_notification_set_dnd, webview_notification_mute_account, webview_notification_get_bypass_prefs, webview_set_focused_account - Wire window focus tracking in setup hook via on_window_event Focused handler - Frontend: add setAccountMuted, setGlobalDnd, getBypassPrefs, setFocusedAccount helpers in webviewAccountService; sync focused account on open + click - Add NotificationsPanel settings page with Global DND toggle - Register NotificationsPanel at /settings/notifications Closes #679 * feat(notifications): integrate notifications feature into app - Added Notifications page and routing to AppRoutes. - Introduced NotificationRoutingPanel in Settings for managing notification settings. - Updated SettingsHome to include navigation for notification routing. - Integrated notifications reducer into the store for state management. - Enhanced Rust backend to support notification handling from embedded webviews. This commit lays the groundwork for a comprehensive notification system within the application. * refactor(notifications): clean up code formatting and structure - Simplified JSX structure in NotificationCard for better readability. - Consolidated fetchNotifications call in NotificationCenter for cleaner syntax. - Improved formatting in NotificationRoutingPanel and notificationsSlice for consistency. - Enhanced Rust code readability by streamlining function signatures and logic. These changes enhance code maintainability and readability across the notifications feature. * refactor(webview_accounts): simplify webview_notification_set_dnd function signature - Removed unnecessary line breaks in the webview_notification_set_dnd function for improved readability. * feat(notifications): implement provider-level notification settings management - Added `getNotificationSettings` and `setNotificationSettings` functions to manage notification settings for providers. - Enhanced `NotificationRoutingPanel` to display and update settings for Gmail, Slack, Discord, and WhatsApp. - Introduced new RPC endpoints for retrieving and updating notification settings. - Updated database schema to store notification settings persistently. This commit establishes a robust system for managing notification preferences, improving user control over notifications. * refactor(notifications): improve code formatting and readability - Enhanced formatting in NotificationRoutingPanel for better clarity. - Streamlined function signatures in notificationService and Rust backend. - Improved readability of assertions in tests by adjusting line breaks. These changes contribute to a more maintainable and comprehensible codebase for the notifications feature. * chore(vendor): bump tauri-cef to fix Slack notification permission banner Updates the tauri-cef submodule to 55db2d6 which adds a navigator.permissions.query shim in the CEF render process. Slack checks this API (not just Notification.permission) to decide whether to show its "needs your permission" banner — the shim returns "granted" for notifications queries so the banner no longer appears. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * chore(vendor): bump tauri-cef for cargo fmt fixes Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * chore(vendor): bump tauri-cef — native V8 permissions.query shim Switches from context.eval() to a proper PermissionsQueryV8Handler so the navigator.permissions.query fix actually runs in on_context_created. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(notifications): patch navigator.permissions.query in ua_spoof.js The V8 set_value_bykey approach in cef-helper's on_context_created does not stick on CEF platform objects (Chromium's V8 binding layer silently ignores property writes on native wrappers like Permissions). The init script path via frame.execute_java_script runs in the fully-initialised JS context where navigator.permissions IS writable, matching how ua_spoof.js already overrides navigator.userAgent successfully. Slack checks navigator.permissions.query({ name: 'notifications' }) before showing its "needs permission" banner — patching it here to return "granted" removes the banner. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(notifications): use Object.defineProperty to shim navigator.permissions Two-layer fix for the Slack "needs permission to enable notifications" banner: 1. cef-helper (submodule update to 99a2686): context.eval() in on_context_created installs Object.defineProperty(navigator, 'permissions', ...) before any page JS runs. 2. ua_spoof.js: same Object.defineProperty pattern as belt-and-suspenders for frames that reload or trigger permission checks after on_load_end. Simple property assignment on Blink platform objects is silently ignored; Object.defineProperty on the navigator wrapper itself (the same mechanism already used for navigator.userAgent) works correctly. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(notifications): address CodeRabbit review issues on PR #727 - Move raw_title out of log::info! (PII risk) — log title_chars at info, raw_title at debug only - Fix permissionChecked set before async invoke in ensureNotificationPermission so transient failures allow retry on next account open * fix(cef): enable webview-data-url feature for CEF placeholder URL The CEF backend uses a data: URL as the initial webview location so CDP can attach before the real provider URL loads. Tauri's add_child rejects data: URLs unless the webview-data-url feature is enabled. * fix(notifications): address remaining CodeRabbit issues on PR #727 - cdp/emulation: bump Chrome UA 124→136 to pass Slack browser check - cdp/session: inject Page.addScriptToEvaluateOnNewDocument to stub Notification.permission as "granted" and silence provider banners - notifications/mod.rs + core/all.rs: wire notifications domain into the controller registry (fixes unknown-method in json_rpc_e2e tests) - notifications/schemas: add skipped bool output to ingest schema - notifications/store: add tracing::warn on datetime parse failure - notificationService: union return type for ingestNotification - webviewAccountService: narrow union before accessing result.id - NotificationCenter: drive loading/error from fetch effect; track allProviders separately so filter pills don't collapse on selection - NotificationRoutingPanel: rollback optimistic update on save failure - useSettingsNavigation: add notifications/notification-routing routes - scripts/install.sh: remove silent dry-run exit 0 on asset failure - scripts/setup-dev-codesign.sh: remove unconditional -legacy flag - docs/SUMMARY.md: remove worktree path, fix macOS capitalisation, remove self-referential deletion note * chore: apply prettier + cargo fmt + fix useEffect dep warning Auto-apply formatting changes flagged by the pre-push hook: - prettier reformatted NotificationCenter.tsx and notificationService.ts - cargo fmt reformatted all.rs, openhuman/mod.rs, notifications/schemas.rs - NotificationRoutingPanel: move providers array to module scope so useEffect dependency array is satisfied without exhaustive-deps warning * feat(notifications): enhance notification management and permissions - Added new commands for managing notification preferences, including setting global Do Not Disturb (DND), muting specific accounts, and retrieving current bypass preferences. - Implemented a notification permission state handler to ensure consistent behavior across different environments. - Updated the JavaScript shim for notification permissions to handle both Notification and PushManager states, ensuring compatibility with various providers. - Refactored the WebviewAccountsState to include a new structure for managing notification bypass preferences, improving the overall notification handling logic. * update agents * fix(notifications): complete schema + navigation metadata for ingest/settings routes - app/src/components/settings/hooks/useSettingsNavigation.ts: resolve the new `/settings/notifications` and `/settings/notification-routing` URLs to their SettingsRoute values and feed them into breadcrumbs so the new panels don't silently fall through to `'home'`. Addresses CodeRabbit on useSettingsNavigation.ts:34. - src/openhuman/notifications/schemas.rs: add the optional `reason` output on `notification.ingest` (populated alongside `skipped=true` by the runtime) and the normalized `settings` output on `notification.settings_set` so schema-driven clients see the full response shape. Addresses CodeRabbit on schemas.rs:103 and schemas.rs:217. - src/core/all.rs: add a `notification` namespace_description so CLI help covers the new controllers, plus a test assertion. Addresses CodeRabbit on src/core/all.rs:149. * fix(notifications): trace DB entry, surface empty update matches, warn on bad scored_at - Add `tracing::trace!` checkpoints around the `with_connection` DB open and schema migration so notification-delivery issues are reconstructible from logs. - `update_triage` and `mark_read` now inspect `Connection::execute`'s affected-row count: log a `warn!` when the update matched zero rows (row deleted between ingest and scoring / client passed a stale id), `debug!` on the normal path. - `scored_at` parsing no longer silently drops malformed values — log a `warn!` with the raw value and parse error before treating the row as unscored, matching the existing behavior for `received_at`. Addresses CodeRabbit on store.rs (lines 72, 172, 294). * fix(webview): respect silent notifications, multi-host CDP fallback, shim idempotency - webview_accounts/mod.rs: honor the Web Notification `silent` flag. Previously we only logged it and still called `builder.show()`, so pages that marked a notification silent still produced an OS toast. Mirror event still fires so the in-app center updates; only the OS toast is suppressed. Also picks up a prior cargo-fmt rewrap. - cdp/target.rs: `browser_ws_url()` now continues the host loop when `resp.json()` fails instead of early-returning via `?`. A malformed response from the first host (CDP_HOST) no longer prevents the `localhost` fallback from being tried. - webview_accounts/ua_spoof.js: guard the Notification wrapper behind `window.__OH_NOTIF_SHIM` so repeated evaluations of the script (Page.addScriptToEvaluateOnNewDocument + frame-level re-injections) don't stack wrappers onto the same page globals or re-proxy `Function.prototype.toString`. Addresses CodeRabbit on webview_accounts/mod.rs:377, cdp/target.rs:33, and ua_spoof.js:176. * update agents * update --------- Co-authored-by: oxoxDev <nikhil@tinyhumans.ai> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai> |
||
|
|
5fff5568d3 |
feat(memory): Phase 2 memory tree - preprocessing, scoring, admission gate (#708) (#733)
* feat(memory): phase 1 memory tree - multi-source ingestion & canonical chunks (#707) Adds an isolated memory tree layer under src/openhuman/memory/tree/ implementing Phase 1 of the new memory architecture (umbrella #711). Zero edits to existing memory/*.rs files - the new layer coexists with the legacy TinyHumans-backed client. - Source adapters: chat / email / document -> canonical Markdown - Token-bounded chunker with deterministic SHA-256 chunk IDs - SQLite persistence at <workspace>/memory_tree/chunks.db with full provenance metadata (source_kind, source_id, owner, timestamps, tags, time_range) and back-pointer to raw source - Unified JSON-RPC ingest (dispatches on source_kind + JSON payload): openhuman.memory_tree_ingest, _list_chunks, _get_chunk - DataSource enum covering the 8 providers from m.excalidraw step 1 (Discord/Telegram/Whatsapp/Gmail/OtherEmail/Notion/MeetingNotes/DriveDocs) - ~40 unit tests (chunk ID stability, UTF-8-safe splitting, canonicalisation idempotence, store round-trip, filter behavior) Additive only: new tables in a new DB file, new JSON-RPC namespace, no existing behavior changes. Feeds #708 (scoring), #709 (summary trees), #710 (query tools). Closes #707. Parent: #711. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(memory): phase 2 memory tree - preprocessing, scoring, admission gate (#708) Adds the scoring / admission layer between Phase 1's chunker and store. Stacked on feat/707-memory-ingestion (PR #732) - depends on Phase 1's chunk substrate. - Pluggable EntityExtractor trait + CompositeExtractor chain - RegexEntityExtractor: mechanical entities (emails, URLs, @handles, #hashtags) - Always on, deterministic, zero deps, UTF-8-safe char spans - Five weighted signals: token count, unique-word ratio, metadata weight, source weight (per-DataSource), interaction (reply/sent/mention/dm tags), entity density - Exact-match entity canonicalisation (email lowercased, @ and # stripped) - Admission gate drops chunks below configurable threshold (default 0.3) - Score rationale persists for EVERY chunk (kept or dropped) for debugging - Entities indexed for KEPT chunks only - Two new SQLite tables added to the memory_tree DB: - mem_tree_score: per-chunk score rationale with all signal values - mem_tree_entity_index: inverted index entity_id -> node_id - Idempotent ALTER TABLE migration adds embedding BLOB column to mem_tree_chunks (used in Phase 3 retrieval, wired but not populated here) - Ingest pipeline converted to async to accommodate the extractor trait; blocking SQLite work isolated on spawn_blocking; JSON-RPC surface unchanged (same memory_tree_ingest / list / get methods) - Phase 2 deliberately ships without GLiNER/semantic NER - per-chunk semantic entities land later behind a cargo feature flag; the composite extractor interface keeps that drop-in trivial Additive only: new tables, new columns, new module. Existing Phase 1 behavior unchanged except that low-signal chunks are now dropped before reaching mem_tree_chunks. Raise score_drop_threshold to 0 to disable the gate and restore Phase-1-identical behavior. Closes #708. Parent: #711. Depends on: #707 (#732). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * Fix memory tree scoring persistence issues * Fix memory tree scoring robustness issues from PR review - ingest: fail fast if scorer returns fewer/more results than chunks (silent zip truncation would drop chunks or their score rationale) - score::persist_score{,_tx}: clear stale entity-index rows before re-indexing a re-scored chunk, since INSERT OR REPLACE never deletes rows whose entity_id is no longer in the new extraction - score::store::lookup_entity: clamp limit to i64::MAX before casting to prevent a large usize wrapping into a negative LIMIT Adds clear_entity_index_drops_stale_rows regression test. --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai> |
||
|
|
0ce1253fe1 |
feat(memory): Phase 1 memory tree - multi-source ingestion & canonical chunks (#707) (#732)
* feat(memory): phase 1 memory tree - multi-source ingestion & canonical chunks (#707) Adds an isolated memory tree layer under src/openhuman/memory/tree/ implementing Phase 1 of the new memory architecture (umbrella #711). Zero edits to existing memory/*.rs files - the new layer coexists with the legacy TinyHumans-backed client. - Source adapters: chat / email / document -> canonical Markdown - Token-bounded chunker with deterministic SHA-256 chunk IDs - SQLite persistence at <workspace>/memory_tree/chunks.db with full provenance metadata (source_kind, source_id, owner, timestamps, tags, time_range) and back-pointer to raw source - Unified JSON-RPC ingest (dispatches on source_kind + JSON payload): openhuman.memory_tree_ingest, _list_chunks, _get_chunk - DataSource enum covering the 8 providers from m.excalidraw step 1 (Discord/Telegram/Whatsapp/Gmail/OtherEmail/Notion/MeetingNotes/DriveDocs) - ~40 unit tests (chunk ID stability, UTF-8-safe splitting, canonicalisation idempotence, store round-trip, filter behavior) Additive only: new tables in a new DB file, new JSON-RPC namespace, no existing behavior changes. Feeds #708 (scoring), #709 (summary trees), #710 (query tools). Closes #707. Parent: #711. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(memory): enhance memory tree functionality and tests - Added support for "memory_tree" namespace description in `namespace_description`. - Implemented clamping for zero token budget in `chunk_markdown` to prevent empty leading chunks. - Introduced detailed logging for document ingestion, including title length. - Updated output schemas in `schemas.rs` for improved clarity. - Enhanced chunk listing with clamping limits and ordering by sequence in `list_chunks`. - Normalized source references in canonicalization functions to drop blank values. - Added comprehensive tests for new features and edge cases in chunking and canonicalization. These changes improve the robustness and usability of the memory tree layer, aligning with ongoing development efforts for Phase 1 of the memory architecture. * fix(memory): address follow-up CodeRabbit comments --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> Co-authored-by: Steven Enamakel <enamakel@tinyhumans.ai> |
||
|
Steven EnamakelandGitHub
|
e5f571cec7 |
feat(tokenjuice): Rust port of terminal-output compaction engine (#644)
* feat(tokenjuice): implement core functionality for terminal-output compaction engine - Introduced the `tokenjuice` module, which includes the classification and reduction of tool outputs based on JSON-configured rules. - Added new dependencies for Unicode handling: `unicode-segmentation` and `unicode-width`. - Implemented the `classify` module to match tool execution inputs against predefined rules, enhancing the ability to process and summarize terminal outputs. - Created a comprehensive set of types and utilities for managing tool execution inputs and classification results. - Established a built-in rule set for common tools, improving the initial setup and usability of the `tokenjuice` engine. - Enhanced testing framework with integration tests to ensure the accuracy of output compaction and classification. These changes lay the groundwork for a robust terminal-output management system, facilitating better interaction with various tools and improving overall user experience. * feat(tokenjuice): implement tokenjuice module for terminal output compaction - Introduced the `tokenjuice` module, which includes functionality for classifying and reducing terminal output based on JSON-configured rules. - Added new dependencies: `unicode-segmentation` and `unicode-width` to support text processing. - Created a new `classify.rs` file for rule classification logic, including matching helpers and scoring functions. - Implemented a `reduce.rs` file to handle the main reduction pipeline and text normalization. - Established a structured approach for loading and compiling rules from multiple sources, including built-in and user-defined rules. - Added integration tests to ensure the correctness of the output reduction process. These changes enhance the application's ability to manage and compact verbose tool outputs, improving overall efficiency and user experience. * test(tokenjuice): enhance test coverage for classification and reduction logic - Added a series of unit tests to `classify.rs` to validate the behavior of tool name filters and argument matching, ensuring correct classification of tool executions. - Introduced tests for edge cases in `reduce.rs`, including command tokenization and normalization of execution inputs, to improve robustness against various input formats. - Expanded tests in `builtin.rs` to cover duplicate ID reporting and compile issues, enhancing error handling and reporting mechanisms. - Implemented additional tests in `compiler.rs` to verify regex handling in rule definitions, ensuring invalid patterns are correctly ignored. These enhancements improve the overall test coverage and reliability of the tokenjuice module, facilitating better maintenance and future development. * test(tokenjuice): add edge-case tests for gh table and reduction pipeline * style(tokenjuice): apply cargo fmt * feat(tokenjuice): wire into agent tool loop output compaction Add `tokenjuice::compact_tool_output` helper and call it in the agent tool loop after credential scrubbing (and on error paths with exit=1), before any optional payload_summarizer. Derives argv/command heuristically from JSON tool arguments (command / args / argv / cmd shapes) so shell-wrapping tools still match upstream family rules (git/*, package/*, tests/*, etc.). Pass-through safe: outputs under 512 bytes or where compaction saves <5% are returned untouched. * fix(tokenjuice): address coderabbit review comments - classify: derive command from argv join when input.command is unset, so commandIncludes* rules still match argv-only callers - rules/loader: log read_dir / file_type / read_to_string failures at debug level so permission or filesystem issues are observable rather than silently skipped - text/ansi: add trace log at strip_ansi entry/exit with lengths (no text content) per the project debug-logging rules - tests: remove orphan src/openhuman/tokenjuice/tests/integration.rs which was never wired into any module declaration; the real fixture- parity runner lives at tests/tokenjuice_integration.rs and asserts hard when the fixtures directory is missing Vendored-rule issues (docker-ps / kubectl-describe / git/branch / grep casing / counter-pattern overbreadth / etc.) come from upstream and are left as-is; this module is a straight port of the upstream rule set and should not fork from it in v1. |
||
|
Steven EnamakelandGitHub
|
fff24a6c6f |
fix(prompts): v2 prompt pipeline, integrations_agent, and subagent session plumbing (#642)
* refactor(transcript): update session transcript paths and enhance directory structure
- Changed the source of truth path for session transcripts from `sessions/{DDMMYYYY}/{agent}_{index}.jsonl` to `session_raw/{DDMMYYYY}/{agent}_{index}.jsonl` to better reflect the organization of files.
- Updated the logic for creating and resolving transcript paths to accommodate the new directory structure, ensuring compatibility with legacy `.md` files.
- Improved documentation to clarify the changes in file organization and their implications for transcript management.
This refactor enhances the clarity and maintainability of session transcript handling by establishing a more logical file structure.
* refactor(prompts): update tool handling in prompt builders
- Replaced `Vec<String>` with `Vec<ToolSummary<'_>>` for available tools in multiple agent prompt builders, enhancing type safety and clarity.
- Introduced `render_tool_catalog` and `render_connected_integrations` functions to dynamically generate sections in prompts based on available tools and connected integrations.
- Updated the `build` function in various agent prompts to utilize the new rendering functions, ensuring that prompts accurately reflect the current context and available resources.
These changes improve the maintainability and functionality of the prompt generation process across different agents.
* refactor(prompts): streamline prompt builders for agent templates
- Updated the prompt builders for various agents to utilize the sibling `prompt.md` template directly, enhancing clarity and maintainability.
- Replaced `Vec<ToolSummary<'_>>` with `Vec<ToolSummary>` and `Vec<ConnectedIntegration>` for improved type safety in test cases.
- Adjusted the `build` function to ensure consistent formatting and handling of tool catalogs across different agents.
These changes simplify the prompt generation process and prepare the codebase for future enhancements.
* refactor(harness): unify tool filtering and prompt loading for debug consistency
- Exposed `filter_tool_indices` and `load_prompt_source` as `pub(crate)` to ensure that both the live runner and debug dump share the same filtering and loading logic, eliminating discrepancies.
- Enhanced documentation for both functions to clarify their purpose and usage, improving maintainability and understanding of the codebase.
These changes streamline the tool management process and enhance the reliability of debug outputs, ensuring consistency across different contexts.
* refactor(prompts): enhance prompt builders for agent templates
- Updated the prompt builders for various agents to return fully-assembled system prompts, incorporating section helpers from `crate::openhuman::context::prompt`.
- Replaced `Vec<ToolSummary<'_>>` with `Vec<ToolSummary>` and `Vec<ConnectedIntegration>` for improved type safety in test cases.
- Adjusted the `build` function to ensure consistent formatting and handling of user files, tools, and workspace sections across different agents.
These changes streamline the prompt generation process, improve maintainability, and prepare the codebase for future enhancements.
* refactor(prompts): enhance prompt context handling for dynamic sources
- Updated the prompt builders to support fully-assembled prompts from dynamic sources, allowing for more flexible prompt generation.
- Introduced `PromptTool` and `PromptContext` structures to replace `ToolSummary`, improving type safety and clarity in prompt construction.
- Refactored the handling of prompt sources in both the subagent runner and session builder to streamline the integration of dynamic prompts and legacy sources.
These changes improve the maintainability and functionality of the prompt generation process, ensuring accurate representation of available tools and context in agent interactions.
* refactor(prompts): improve prompt context and tool handling
- Enhanced the `PromptContext` structure to include additional fields for better context management, such as `skills`, `dispatcher_instructions`, and `tool_call_format`.
- Replaced `ToolSummary` with `PromptTool` for improved type safety and clarity in prompt generation.
- Updated the handling of dynamic prompt sources in both the subagent runner and debug dump, ensuring consistent integration and rendering of prompts.
- Introduced a mechanism to handle empty visible tool names, enhancing the robustness of prompt generation.
These changes streamline the prompt construction process and improve the overall maintainability of the codebase.
* refactor(prompts): reorganize prompt handling and introduce SystemPromptBuilder
- Moved prompt-related types and builders from `openhuman::context::prompt` to `openhuman::agent::prompts` for better modularity.
- Introduced `SystemPromptBuilder` to streamline the construction of system prompts, allowing for flexible section management.
- Updated module exports to maintain compatibility while enhancing the organization of prompt-related code.
These changes improve the clarity and maintainability of the prompt generation process, aligning it more closely with the agents that utilize these prompts.
* refactor(prompts): unify agent prompt handling and update CLI references
- Removed the "main" alias for the orchestrator in the prompt dumping process, treating it as just another registered agent.
- Updated the `debug-agent-prompts.sh` script to reflect this change, ensuring all agents are included uniformly.
- Revised documentation and error messages in `agent_cli.rs` to replace references to "main" with "orchestrator" for clarity.
- Enhanced the debug dump functionality to maintain consistency across agent prompts, improving overall maintainability and usability.
These changes streamline the prompt handling process and clarify the usage of agent identifiers in the CLI, aligning with the new architecture.
* refactor(prompts): remove CACHE_BOUNDARY references from agent prompts
- Eliminated the CACHE_BOUNDARY marker from various agent prompt files, streamlining the prompt generation process.
- Updated the build functions in multiple agents to ensure consistent handling of workspace rendering without the cache boundary.
- Refactored related prompt handling logic to enhance clarity and maintainability, aligning with the new architecture.
These changes simplify the prompt structure and improve the overall efficiency of prompt generation across agents.
* refactor(prompts): remove cache boundary references from tests and prompts
- Eliminated all instances of cache boundary references from the subagent runner and related tests, simplifying the prompt handling logic.
- Updated test assertions to reflect the removal of cache boundary checks, ensuring consistency across the testing framework.
- Refactored the session manager to streamline the system prompt assembly process without relying on cache boundaries.
These changes enhance the clarity and maintainability of the prompt generation process, aligning with the recent architectural updates.
* refactor(harness): clean up unused imports and streamline code
- Removed unnecessary imports from multiple files, including `RandomState`, `Hasher`, and `SerializeMap`, to enhance code clarity and maintainability.
- Simplified the structure of several modules by eliminating redundant use statements, ensuring a cleaner and more efficient codebase.
These changes contribute to a more organized and readable code structure, aligning with ongoing refactoring efforts.
* refactor(prompts): enhance agent prompt structures and integration handling
- Updated the `orchestrator`, `skills_agent`, and `welcome` prompts to streamline the rendering of connected integrations and delegation guides.
- Introduced dedicated functions for rendering integration information, ensuring clarity in the agent's voice and responsibilities.
- Removed redundant sections from the shared prompt builder, allowing each agent to manage its own prompt content more effectively.
- Improved test coverage for prompt generation, ensuring accurate representation of connected integrations and skills.
These changes enhance the maintainability and clarity of the prompt generation process, aligning with the recent architectural updates.
* refactor(session): update integration handling and clean up prompt parameters
- Revised documentation for `connected_integrations` in the `Agent` struct to clarify its role in the agent's prompt rendering.
- Updated the parameter name in `render_subagent_system_prompt_with_format` to `_connected_integrations` to indicate it is unused, enhancing code clarity.
- Cleaned up import statements in the context module for better organization and maintainability.
These changes improve the clarity of integration handling and streamline the code structure, aligning with ongoing refactoring efforts.
* refactor(agent_cli): simplify command options and improve documentation
- Removed the `--skill` option from the `dump-prompt` command, streamlining the command usage and focusing on essential parameters.
- Updated documentation to clarify the usage of the `dump-prompt` command and its parameters, enhancing user understanding.
- Cleaned up the `DumpFlags` structure by removing unused fields, contributing to a more maintainable codebase.
These changes improve the clarity and usability of the agent CLI, aligning with ongoing refactoring efforts.
* refactor(cli): streamline dotenv loading and clean up prompt rendering
- Introduced `load_dotenv_for_cli` to load environment variables for all CLI entrypoints, ensuring consistent configuration across commands.
- Updated documentation to clarify the purpose of the dotenv loading mechanism.
- Removed unnecessary blank lines in prompt rendering functions across multiple agents, enhancing code readability.
These changes improve the maintainability and clarity of the CLI and prompt handling, aligning with ongoing refactoring efforts.
* refactor(debug-agent-prompts): enhance environment loading and streamline workspace resolution
- Updated the script to load environment variables from a `.env` file, ensuring consistent configuration for prompt generation.
- Simplified workspace resolution by delegating to the binary's internal logic, improving reliability and reducing code duplication.
- Revised documentation to clarify the usage of command options and the impact of environment variables on prompt rendering.
These changes improve the maintainability and clarity of the debug agent prompts script, aligning with ongoing refactoring efforts.
* refactor(agent): remove category filter and simplify agent definitions
- Eliminated the `category_filter` from various agent definitions and related tests, streamlining the agent configuration.
- Updated the `run_list` function in `agent_cli.rs` to reflect the removal of category filtering, enhancing output clarity.
- Revised documentation and comments to remove references to the now-removed category filter, improving overall code maintainability.
These changes contribute to a cleaner and more efficient agent architecture, aligning with ongoing refactoring efforts.
* feat(agents): introduce integrations_agent and tools_agent for enhanced service handling
- Added the `integrations_agent` to manage service integrations via Composio, including a new TOML configuration and prompt structure.
- Introduced the `tools_agent` for general ad-hoc tasks using built-in OpenHuman tools, with its own configuration and prompt.
- Updated the loader to include both agents in the built-in agent list, increasing the total number of agents from 13 to 14.
- Revised orchestrator and welcome prompts to delegate integration tasks to the new `integrations_agent`, ensuring clarity in agent responsibilities.
- Enhanced tests to verify the registration and functionality of the new agents, improving overall test coverage.
These changes expand the capabilities of the agent architecture, allowing for more specialized handling of integrations and tool usage.
* refactor(agents): update references from skills_agent to integrations_agent
- Changed all instances of `skills_agent` to `integrations_agent` across various files, including prompts, CLI commands, and tool registrations.
- Updated documentation and comments to reflect the new agent name, ensuring clarity in agent responsibilities and usage.
- Revised debug scripts to align with the new prompt structure for the integrations agent.
These changes enhance consistency in the codebase and improve the clarity of agent interactions.
* refactor(agents): rename skills_agent to integrations_agent throughout the codebase
- Updated all instances of `skills_agent` to `integrations_agent` in various files, including tests, documentation, and comments.
- Ensured consistency in agent references to improve clarity in agent responsibilities and interactions.
- Revised related code structures to align with the new naming convention, enhancing overall maintainability.
These changes support the transition to the new agent architecture and improve code readability.
* refactor(prompts): implement dynamic prompt rendering for enhanced context handling
- Introduced `DynamicPromptSection` to allow prompts to be built dynamically using a function pointer, enabling real-time access to the `PromptContext`.
- Updated `SystemPromptBuilder` to support dynamic prompts, ensuring that late-arriving state like `connected_integrations` is accurately reflected in the rendered output.
- Revised the prompt handling logic in the agent builder to streamline the integration of dynamic prompts, improving overall flexibility and responsiveness.
These changes enhance the prompt generation process, aligning with the ongoing improvements in agent architecture and context management.
* refactor(prompts): refine delegation guide to display only connected integrations
- Updated the `render_delegation_guide` function to list only the toolkits that are actively connected, omitting unauthorized toolkits to prevent hallucinations during delegation.
- Revised related tests to ensure the prompt correctly reflects the current state of integrations, including scenarios where no integrations are connected.
- Introduced a new utility function to filter out welcome-only tools from non-welcome agents, enhancing the clarity and safety of tool visibility.
These changes improve the accuracy and focus of the delegation guide, aligning with the ongoing enhancements in agent prompt handling.
* refactor(planner): update tool usage and prompt guidelines for read-only operations
- Modified the `agent.toml` configuration to clarify that the planner operates in a read-only mode, specifying that it does not mutate the workspace or memory.
- Revised the prompt guidelines to reflect the read-only nature of the planner, emphasizing the need for explicit nodes for any required writes to be handled by downstream agents.
These changes enhance the clarity of the planner's operational constraints and improve the overall structure of the planning process.
* refactor(config): remove web search enable flag and update related configurations
- Eliminated the `OPENHUMAN_WEB_SEARCH_ENABLED` environment variable and associated logic, as web search is now always enabled by default.
- Updated the configuration schema to reflect the removal of the enable flag from `WebSearchConfig`.
- Adjusted tool registration to ensure web search is always available, simplifying the configuration process.
These changes streamline the web search functionality, ensuring it is consistently available across all sessions.
* refactor(config): update http_request flag to always enabled
- Changed the `http_request` configuration to always be enabled, removing the dependency on the `config.http_request.enabled` flag.
- This adjustment simplifies the configuration process and ensures consistent behavior across the application.
These changes contribute to a more streamlined configuration and enhance the overall reliability of the onboarding process.
* refactor(debug-agent-prompts): transition to dump-all command for agent prompts
- Replaced the previous method of listing agent IDs and dumping prompts with a new `dump-all` command that consolidates the functionality into a single call.
- Updated the script to handle output directory and workspace options more efficiently, leveraging Rust's `dump_all_agent_prompts` for processing.
- Enhanced the handling of the `integrations_agent` to generate separate dumps for each connected toolkit, improving the clarity and organization of output files.
- Revised related logging and summary generation to reflect the new structure, ensuring a more streamlined user experience.
These changes modernize the prompt dumping process, aligning it with the latest architectural improvements and enhancing usability.
* feat(composio): implement dynamic fetching of toolkit actions for integrations
- Added a new `fetch_toolkit_actions` function to retrieve the current action catalogue for a specified Composio toolkit, enhancing the responsiveness of the integrations agent.
- Updated the `subagent_runner` to utilize the fresh action list at spawn time, ensuring that the toolkit's actions reflect the latest backend state.
- Modified the `render_integrations_agent` function to refresh the action catalogue during prompt generation, improving the accuracy of the displayed tools.
These changes enhance the integration experience by providing up-to-date action information, aligning with the ongoing improvements in agent functionality.
* refactor(integrations-agent): update tool visibility and configuration handling
- Modified the `agent.toml` to replace `wildcard` with `named` tools, enhancing control over tool visibility for the integrations agent.
- Updated the `subagent_runner` to ensure that tool visibility aligns with the new TOML configuration, preventing unnecessary stripping of tools.
- Revised the `render_integrations_agent` function to respect the updated tool scope, improving the accuracy of the tool list generated for subagents.
These changes streamline the tool management process, ensuring that only explicitly defined tools are available during agent execution.
* feat(composio): add composio_list_connections tool for dynamic integration detection
- Introduced the `composio_list_connections` tool in the orchestrator's configuration, allowing the agent to detect newly-authorized Composio integrations mid-session.
- Enhanced the `ComposioListConnectionsTool` to filter and return only currently-connected integrations with ACTIVE or CONNECTED status, improving the accuracy of integration management.
- Updated the tool's description to clarify its functionality and usage context.
These changes enhance the agent's ability to manage integrations dynamically, aligning with ongoing improvements in the integration experience.
* fix(prompt): update delegation guide to reference Skills page
- Modified the `render_delegation_guide` function to change the reference from **Settings → Integrations** to the **Skills** page for connecting integrations. This update clarifies the user instructions for integration management.
* feat(session): introduce session key management for sub-agents
- Added `session_key` and `session_parent_prefix` fields to `ParentExecutionContext` to facilitate hierarchical transcript naming for sub-agents.
- Updated `persist_subagent_transcript` to generate transcript filenames based on the parent's session key, ensuring a flat file structure that reflects the parent-child relationship.
- Enhanced `AgentBuilder` and `Agent` to support the new session key management, allowing for better organization of session transcripts.
- Adjusted related functions to ensure proper handling of session keys during agent execution and transcript persistence.
These changes improve the clarity and organization of session transcripts, aligning with the ongoing enhancements in agent functionality.
* refactor(tests): update integrations agent tests for tool scope and transcript handling
- Renamed the `integrations_agent_is_wildcard` test to `integrations_agent_tool_scope_honours_toml` to better reflect its purpose of validating tool scope based on TOML configuration.
- Enhanced the test to assert that the `integrations_agent` correctly recognizes named tools instead of a wildcard.
- Removed the `integrations_agent_has_extra_tools_for_export` test as it is no longer relevant to the current tool management strategy.
- Improved the `latest_in_dir` function to clarify the handling of transcript naming schemes, ensuring proper differentiation between legacy and keyed formats.
These changes streamline the testing process and improve the accuracy of tool scope validation, aligning with recent updates in agent functionality.
* refactor(subagent_runner): improve transcript persistence and streamline inner loop
- Removed the `persist_subagent_transcript` function, transitioning transcript persistence to occur per-iteration within the `run_inner_loop`, enhancing reliability by ensuring transcripts are written immediately after each provider response.
- Updated the handling of session keys to maintain consistent naming for transcripts, reflecting the parent-child relationship in the file structure.
- Simplified the code by eliminating redundant post-loop transcript writes, aligning with recent changes in agent functionality and improving overall clarity in transcript management.
* refactor(agent_cli, subagent_runner, session): improve code readability and formatting
- Enhanced formatting in `agent_cli.rs` for better readability by adjusting the structure of string formatting.
- Streamlined conditional checks in `subagent_runner.rs` to improve clarity and maintainability.
- Simplified the handling of agent IDs in `builder.rs` to reduce line length and improve code flow.
- Updated test cases in `tests.rs` for better alignment and readability of expected values.
- Improved formatting in `debug_dump.rs` to enhance the clarity of toolkit action fetching and logging.
These changes collectively enhance the overall readability and maintainability of the codebase, aligning with ongoing refactoring efforts.
* fix(tests): add missing session_key fields to ParentExecutionContext stub
* fix: address PR review feedback
* fix(prompts-v2): round 2 PR review — dispatcher instructions, workspace-file preservation, cached-tool fallback, transcript persistence
- subagent_runner: populate PromptContext.dispatcher_instructions for Dynamic prompts (was empty string, dropping the ## Tool Use Protocol block in render_tools for PFormat/Json/Native sub-agents)
- subagent_runner: add post-tool persist_transcript after tool results are appended so a mid-round crash doesn't lose tool outputs
- prompts::sync_workspace_file: preserve user-edited workspace files — only overwrite when the file doesn't exist OR its current hash matches the stored builtin hash
- context::debug_dump: mirror runner's cached-tool fallback — keep cached action catalogue on empty/error from fetch_toolkit_actions instead of blanking it
- core::agent_cli: add entry/exit debug logs around dump_all / dump_prompt calls and a trace log around each prompt file write; update module banner to note --toolkit is required when --agent is integrations_agent
|
||
|
|
d545c193b9 |
feat(agent): fuzzy-filter skills_agent toolkit actions by task prompt (#579)
* feat(agent): fuzzy-filter skills_agent toolkit actions by task prompt Narrow large Composio toolkits (e.g. github ~500 actions) down to the handful relevant to a given delegation prompt before registering them as native tools on a spawned skills_agent. Falls back to the full catalogue when the filter yields fewer than MIN_CONFIDENT_HITS hits to avoid starving the sub-agent on under-specified prompts. Filter is only invoked when both `definition.id == "skills_agent"` and a `toolkit=` argument is present, so orchestrator and other sub-agents are unaffected. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test(composio): mock toolkits route in ops integration test --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
|
ea088d9f15 |
feat(prompt): unified delegation guide + dynamic per-toolkit tool registration (#447) (#570)
* feat(prompt): unified delegation guide + dynamic per-toolkit tool registration (#447) Cuts main agent prompt token cost ~98% on accounts with connected integrations and replaces the generic Composio dispatcher with native per-action tool calling inside skills_agent. ## Why Issue #447: prompt payloads were ballooning because main/orchestrator re-shipped a full prose enumeration of every connected toolkit's actions on every turn (~13.7k tokens for one gmail integration alone), and skills_agent had no way to scope tools to a single toolkit so it inherited a flat dispatcher (composio_execute) that the LLM couldn't reliably call without first round-tripping composio_list_tools. ## What ### main / orchestrator prompt - Replace `ConnectedIntegrationsSection`'s per-action prose dump with a unified Delegation Guide: one bullet per integration (toolkit + one-line description + spawn snippet). Tokens added per integration: ~30. Savings vs old per-action listing: ~5k+ tokens per connected toolkit. - Drop every "Composio" reference from delegating-agent prose so the surface stays provider-neutral. ### skills_agent - Add a `toolkit` argument to `spawn_subagent` with three pre-flight validation modes resolved against the parent's connected integrations list before any LLM call: * missing toolkit -> ToolResult::error (model retries) * unknown toolkit -> ToolResult::error (model retries) * in allowlist, not connected -> ToolResult::success (model surfaces "authorize in Settings -> Integrations" to user; not flagged as a tool failure in the agent loop or web channel) - New `ComposioActionTool` (`src/openhuman/composio/action_tool.rs`) implements the `Tool` trait per Composio action. The sub-agent runner constructs ~N of these at spawn time from the cached integration overview and injects them via a new `extra_tools` parameter through `run_typed_mode` -> `run_inner_loop`. - `filter_tool_indices` drops every skill-category parent tool when `is_skills_agent_with_toolkit` is true so the only skill-category entries the sub-agent sees are the freshly-built per-action tools. This eliminates apify_*, composio_list_*, composio_authorize, and composio_execute from the toolkit-scoped surface. - Sub-agent renderer takes the parent's actual `tool_call_format` instead of hardcoding PFormat. Native dispatchers no longer carry a prose `## Tools` section at all (schemas already travel through the request body's `tools` field) — eliminates a ~30k-token duplication that was blowing past the model's context window. ### integration overview fetch - `fetch_connected_integrations_uncached` now merges Composio's toolkit allowlist with the user's active connections and returns one `ConnectedIntegration` per allowlisted toolkit with a `connected: bool` flag. Unconnected entries carry no schemas, just the toolkit name + description, so the orchestrator can mention them without trying to invoke them. - `ConnectedIntegrationTool` preserves the action's full JSON parameter schema so `ComposioActionTool` can advertise it through native function-calling. ### plumbing - `ParentExecutionContext` carries a `ComposioClient` and the parent's resolved `tool_call_format`, populated alongside `connected_integrations` in `Session::fetch_connected_integrations`. Triage and test paths pass `None` / `PFormat` defaults. - `dispatch_subagent` (the `SkillDelegationTool` path) plumbs its pre-bound skill_id through `toolkit_override` instead of the broken `skill_filter_override` (which used `{skill}__` prefix matching that never matched Composio's `TOOLKIT_*` naming). - `web::run_chat_task` failures now log the underlying error at WARN so debugging an in-flight failure no longer requires turning on TRACE for socket events. - `scripts/stage-core-sidecar.mjs` queries `cargo metadata` for the real target directory instead of assuming `<repo>/target` so the staging step works under workspace-level `target-dir` overrides (the vezures-workspace shared `.cargo-target` setup). ## Verified end-to-end Two RPC tests against a freshly-rebuilt sidecar (gmail connected, notion / slack / etc. allowlisted but not connected): | Test | Behavior | Tokens | Iterations | |---|---|---|---| | Connected (gmail, "fetch 5 unread emails") | spawn_subagent -> 62 dynamic gmail tools registered -> 1 GMAIL_FETCH_EMAILS call with smart args -> markdown table response | 42,911 input | 1 | | Not-connected (notion, "create a page") | main answers directly without spawning, tells user to authorize in Settings -> Integrations | 3,319 input | 1 | Both flows complete cleanly. The connected path proves dynamic per-action tool registration is working with full schema validation; the unconnected path proves the unified delegation guide + ToolResult::success return for not-connected toolkits keeps the model on a graceful path without polluting the chat with error styling. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test(prompt): update test callers + assertions for new renderer signature Follow-up to #447. The main patch changed three signatures that test callers hadn't been updated for, and flipped one assertion that was validating the now-removed prose schema duplication. - `SubagentRunOptions` test constructors in subagent_runner.rs (2 sites) now pass `toolkit_override: None`. - `ConnectedIntegration` test constructor in orchestrator_tools.rs now passes `connected: true` (the default for test integrations — they're treated as authorized so delegation logic still runs). - 12 `render_subagent_system_prompt` test callers in prompt.rs now pass `&[]` for the new `extra_tools` slice and `ToolCallFormat::PFormat` for the new `tool_call_format` argument. - `render_subagent_system_prompt_honors_identity_safety_and_skills_flags` used to assert `rendered.contains("Parameters:")` on the Json dispatcher branch — that was valid in the old world where the prose `## Tools` section dumped full JSON schemas for Json/Native formats. The main patch deliberately removes that dump (it was the ~30k-token duplication of the native `tools` field), so the test now asserts the opposite: no `## Tools` header and no `Parameters:` line are emitted for Native/Json dispatchers. The schemas still travel through the provider request's `tools` field. Also picks up `rustfmt` rewraps in action_tool.rs and ops.rs from a background linter run — pure whitespace, no semantic change. Verified green against the full `cargo test --lib` suite for every test touched by this PR: - openhuman::context::prompt::tests (26 passed) - openhuman::agent::harness::subagent_runner::tests (19 passed) - openhuman::composio::ops::tests (2 passed) - openhuman::tools::impl::agent::tests (0 scoped) The 7 remaining failures in `cargo test --lib` are pre-existing Windows-path/filesystem flakes in subsystems this PR doesn't touch (self_healing polyfill path separator, cron scheduler shell spawning, local_ai::paths absolute-path detection, security::policy sandbox path handling, composio::trigger_history jsonl archive, and a real pre-existing `Option::unwrap()` panic in browser::screenshot). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test(harness): add composio_client + tool_call_format to integration test stub Follow-up to #447. The `tests/agent_harness_public.rs` integration test constructs a `ParentExecutionContext` in `stub_parent_context` that was missing the two fields added in the main patch (`composio_client` and `tool_call_format`). `cargo test --lib` doesn't compile integration tests, which is why this slipped past local verification — it only surfaced on Linux CI. - `composio_client: None` — the stub parent has no composio client because these tests don't exercise the integration-overview path. - `tool_call_format: ToolCallFormat::PFormat` — default legacy format; none of the tests in this file exercise the sub-agent renderer's format branching, so PFormat is the safe pick. Verified locally that `cargo test --no-run` compiles all integration test targets including `agent_harness_public`. (The `agent_memory_loader_public` link error in the local run is a pre-existing Windows `libucrt`/`fgets` C-runtime issue unrelated to this PR — won't reproduce on Linux CI.) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(prompt,composio): address CodeRabbit review on #570 (#447) Four fixes from the CodeRabbit review of PR #570, ranked by impact: ## `context/prompt.rs` — Json dispatcher needs prose tool catalog The initial patch gated the prose `## Tools` section behind `matches!(tool_call_format, ToolCallFormat::PFormat)`, which conflated Json with Native. Only `ToolCallFormat::Native` uses the provider's native function-calling channel where schemas travel via the request body's `tools` field. `ToolCallFormat::Json` is a prompt-driven format (the model wraps JSON tool calls in `<tool_call>` tags) and relies on the prose catalog the same way PFormat does — without it the model sees protocol instructions but no visible tool names or schemas. Inverted the guard to `!matches!(tool_call_format, Native)` so PFormat and Json both render the `## Tools` section with their respective per-entry shapes (compact `Call as:` signature for PFormat, inline `Parameters:` JSON schema for Json). Updated the `render_subagent_system_prompt_honors_identity_safety_and_skills_flags` test: the Json assertion now expects `Parameters:` to be present again (reverting commit 2's flip), and a new Native-branch assertion guards against the ~54k-token schema duplication the original PR fixed. ## `composio/ops.rs` — don't cache degraded snapshots All three backend calls in `fetch_connected_integrations_uncached` (`list_toolkits`, `list_connections`, `list_tools`) previously returned `Some(Vec::new())` or fell through to an empty inner vec on transient errors. The outer `fetch_connected_integrations` caches whatever the uncached path returns, so a single transient 5xx would silently hide every integration, mark connected toolkits as disconnected, or register dynamic Composio tools with zero callable actions — until the cache is invalidated or the process restarts. Changed all three branches to return `None`, which signals the caller to NOT cache the result and retry on the next call. ## `composio/ops.rs` — prefix match needs a delimiter `starts_with(&slug.to_uppercase())` false-matches when two toolkit slugs share a text prefix (e.g. `git` vs `github`). The current allowlist doesn't trigger this, but adding a new toolkit could silently leak actions between integrations. Anchored the prefix with an underscore so `GMAIL_SEND_EMAIL` matches `gmail_`, not just `gmail`. ## `scripts/stage-core-sidecar.mjs` — resolve CARGO_TARGET_DIR vs repo root `resolve(process.env.CARGO_TARGET_DIR)` uses the process's current working directory, but the `cargo build` spawn below runs with `cwd: root`. For an absolute env var this is identical, but a relative `CARGO_TARGET_DIR` and a cwd outside the repo would make the two paths disagree and the binary lookup would miss. Defensive fix: `resolve(root, process.env.CARGO_TARGET_DIR)` so both paths anchor to the same base. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
|
1836c7691f |
Feat: smart routing (#569)
* chore: update OpenHuman version to 0.52.9 and add intelligent routing functionality - Bumped OpenHuman version from 0.52.7 to 0.52.9 in Cargo.lock files. - Introduced a new routing module that implements intelligent model routing based on task complexity and local model health. - Added a health checker for the local Ollama model server to improve routing decisions. - Enhanced the provider to classify tasks and determine the appropriate backend (local or remote) for processing requests. - Updated related files to support the new routing logic and ensure seamless integration with existing functionalities. * refactor(routing): streamline provider and enhance routing logic - Removed the `build_tool_instructions` function from the public API, simplifying the routing module. - Updated the `IntelligentRoutingProvider` to utilize a more efficient model resolution process, improving routing decisions based on task complexity and local model health. - Introduced a new `quality` module to assess response quality, enabling better fallback decisions when local responses are deemed low quality. - Enhanced the `RoutingHints` struct to provide more granular control over routing behavior, including privacy requirements and cost sensitivity. - Added tests to validate the new routing logic and quality assessment, ensuring robust functionality across various scenarios. * feat(tests): add live end-to-end routing tests for real backend integration - Introduced a new test file `live_routing_e2e.rs` containing end-to-end tests for routing against a live backend. - Tests require a valid backend URL, user session JWT, and real network interactions, hence marked as `#[ignore]`. - Implemented functionality to set up environment variables, write configuration files, and perform JSON-RPC calls to validate routing behavior. - Added assertions to ensure correct handling of various routing cases, enhancing test coverage for the routing module. * refactor(format): ran format command * feat(routing): add IntelligentRoutingProvider and enhance LocalHealthChecker - Introduced a new `factory.rs` file containing the `new_provider` function to construct an `IntelligentRoutingProvider` that integrates local AI capabilities with remote backend providers. - Enhanced the `LocalHealthChecker` in `health.rs` by adding a `reqwest::Client` for improved health probing, including better logging for cache hits and misses, and streamlined cache updates. - Updated health check logic to utilize the new client, ensuring more reliable health status checks for local AI services. * refactor(routing): move new_provider function to factory module - Moved the `new_provider` function from `mod.rs` to a new `factory.rs` module to improve code organization and maintainability. - Updated public exports to include the new location of `new_provider`, ensuring continued accessibility for constructing `IntelligentRoutingProvider` instances. - Removed the old implementation from `mod.rs`, streamlining the routing module's structure. * refactor(routing): simplify local task routing logic - Removed redundant conditions for routing medium tasks locally, streamlining the decision-making process in the `decide` function. - Updated comments to reflect the simplified logic, enhancing code clarity and maintainability. * docs(tests): clarify comments in json_rpc_e2e.rs regarding hint overrides logic. * refactor(tests): enhance live routing end-to-end tests with timeout handling - Introduced a timeout mechanism for reading SSE events to prevent indefinite blocking. - Updated environment variable management in tests to ensure safe access and cleanup. - Improved comments for clarity regarding the safety of environment variable mutations during tests. * refactor(tests): update SSE event reading in live routing tests. * refactor(routing): enhance medium task routing logic and update comments - Updated the routing logic for medium tasks to utilize hints for local bias, ensuring more accurate routing decisions. - Revised comments throughout the code to clarify the behavior of task categories and routing preferences. - Adjusted test cases to reflect the new routing logic, ensuring they accurately validate the expected behavior for medium tasks. * refactor(tests): implement timeout handling for dictation event reception - Added a timeout mechanism to the dictation event test to prevent indefinite blocking while waiting for the "pressed" event. - Enhanced the test logic to consume events until the expected event type is received, improving reliability and clarity in the test flow. --------- Co-authored-by: Steven Enamakel <31011319+senamakel@users.noreply.github.com> |
||
|
|
7685e877ee |
feat(agent): welcome->orchestrator routing + per-agent tool scoping (#525, #526) (#544)
* feat(agent): add subagents + delegate_name fields to AgentDefinition (#525, #526) Introduces the schema change needed to make agent definitions the single source of truth for both direct tools and delegation targets: - `subagents: Vec<SubagentEntry>` — declarative list of agents this agent can spawn, expanding at build time into synthesised delegate_* tools on the LLM's function-calling surface. Supports two TOML shapes via `#[serde(untagged)]`: * Bare string (`"researcher"`) → `SubagentEntry::AgentId` * Inline table (`{ skills = "*" }`) → `SubagentEntry::Skills(SkillsWildcard)` The `Skills` variant expands dynamically to one delegate_{toolkit} tool per connected Composio toolkit at runtime. - `delegate_name: Option<String>` — optional override for the tool name this agent is exposed as when another agent lists it in `subagents`. Defaults to `delegate_{id}` when absent, lets the researcher agent be exposed as `research`, code_executor as `run_code`, etc. Schema only — no runtime behavior change yet. Follow-up commits wire the field into `collect_orchestrator_tools`, the dispatch path, and the debug dump. TOML placement note: `subagents = [...]` must appear before the `[tools]` table header in agent TOMLs. Once a table section opens, every subsequent top-level key is consumed by that table, so placing `subagents` after `[tools]` parses it as `tools.subagents` and fails deserializing ToolScope. The test doc-comment records this constraint. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(agent): drive orchestrator delegation tools from TOML subagents (#525, #526) Completes the half-built migration from a hardcoded ARCHETYPE_TOOLS table + orphan skill_delegation.rs to a TOML-driven delegation surface where each agent declares its subagents and the tool list is synthesised from the registry at agent-build time. Rewrites `collect_orchestrator_tools` to take the orchestrator's AgentDefinition, the global AgentDefinitionRegistry, and the slice of connected Composio integrations, then iterates the definition's `subagents` field: * `SubagentEntry::AgentId` → one ArchetypeDelegationTool. The tool's `name()` comes from the target agent's `delegate_name` override (or `delegate_{id}` fallback) and its `description()` is the target's `when_to_use`. Editing an agent's TOML when_to_use now immediately updates the tool schema the orchestrator LLM sees — zero drift, no hardcoded description strings to keep in sync. * `SubagentEntry::Skills { skills = "*" }` → one SkillDelegationTool per connected Composio toolkit. Each routes to the generic skills_agent with `skill_filter` pre-populated. Empty integrations list (CLI path, or user not yet connected) produces zero tools rather than phantom `delegate_*` entries for unconnected toolkits. Also in this commit: - Wire the orphan `skill_delegation.rs` into `impl/agent/mod.rs` via `mod skill_delegation;` + `pub use SkillDelegationTool;`. The file has existed since earlier work but was never declared in the module tree, so it compiled as dead code. - Delete the legacy `MAIN_AGENT_TOOL_ALLOWLIST` constant and the `main_agent_tools` filter in `tools/ops.rs`. They were documented as "no longer the primary source of truth" since the from_config builder switched to `collect_orchestrator_tools`, and grep confirms no external callers remain. Clean deletion. - Delete the hardcoded `ARCHETYPE_TOOLS` const in `tools/impl/agent/mod.rs`. The 4-entry table has been replaced by the orchestrator TOML's `subagents` list (which covers those 4 plus archivist plus the skills wildcard), and the re-export in `tools/mod.rs` is removed accordingly. - Update `agents/orchestrator/agent.toml`: add the `subagents` field listing researcher / planner / code_executor / critic / archivist / { skills = "*" }. Keep `spawn_subagent` in `[tools] named` as an advanced fallback so power users can still spawn custom workspace- override agent ids that aren't in the declarative subagents list. - Add `delegate_name = "..."` to the 5 archetype TOMLs so the orchestrator LLM sees natural tool names (`research`, `plan`, `run_code`, `review_code`, `archive_session`) rather than the `delegate_<agent_id>` fallback. - Update `agent/harness/session/builder.rs` (line ~461) to call the new `collect_orchestrator_tools` signature. Looks up the orchestrator definition from the global registry; passes an empty integrations slice because the builder is synchronous and cannot await Composio's async fetch. The channel-dispatch path will populate integrations in a later commit — the CLI/REPL path ships without per-toolkit delegation tools, which is acceptable regression since CLI users still reach Composio via `composio_execute` and the retained `spawn_subagent` fallback. Tests: * 5 new unit tests in `orchestrator_tools.rs` cover the baseline AgentId + Skills wildcard expansion, empty-integrations edge case, unknown-id graceful skip, non-delegating agent with empty subagents, and the slug sanitiser for tool-name-safe Composio toolkit names. * Runs clean alongside all existing agent-module tests (323 pass; one pre-existing Windows-path failure in `self_healing::tests:: tool_maker_prompt_includes_command` is unrelated to this PR and fails identically on the upstream baseline). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(agent): plumb per-agent tool scoping through bus + tool loop (#525, #526) Adds the parameter plumbing for agent-aware tool filtering without changing any runtime behaviour. Every existing call site continues to pass `None` / empty extras, so the LLM still sees the full unfiltered registry — the actual routing logic that populates these fields lands in commit 4b (dispatch.rs onboarding-flag → target_agent_id). Why two parameters and not one filter: Tools in this codebase are `Box<dyn Tool>` — owned trait objects with no Clone impl, stored in a shared `Arc<Vec<Box<dyn Tool>>>`. We can't cheaply build a per-turn filtered subset of the global registry, and we can't mutate the Arc to remove entries. Two new parameters work around this without touching the global registry's lifetime model: * `visible_tool_names: Option<&HashSet<String>>` — whitelist filter applied at the iteration site inside `run_tool_call_loop`. When `Some(set)`, only tools whose `name()` is in the set contribute to the function-calling schema and are eligible for execution; every other tool in the combined registry is hidden from the model and rejected if the model emits a call for it. `None` preserves the legacy "everything visible" behaviour. * `extra_tools: &[Box<dyn Tool>]` — per-turn synthesised tools spliced alongside `tools_registry`. The dispatch path will use this to surface delegation tools (`research`, `delegate_gmail`, …) that are built fresh each turn from the active agent's `subagents` field and the current Composio integration list — tools that don't exist in the global startup-time registry because they depend on per-user runtime state. Empty slice for agents that don't delegate. Inside the loop, `tool_specs` is built from `tools_registry.iter().chain(extra_tools.iter()).filter(is_visible)`, and the tool-execution lookup uses the same chain + filter so the function-calling schema and the execution surface stay in sync. Files touched in this commit: src/openhuman/agent/harness/tool_loop.rs - Add `visible_tool_names` and `extra_tools` parameters to `run_tool_call_loop`. Build `tool_specs` from chained iteration with the visibility filter applied. Replace the `find_tool` call at the execution site with an inline chain+filter lookup so hallucinated calls to filtered-out tools surface as "unknown tool" errors. Drop the now-unused `find_tool` import. - Update the legacy `agent_turn` wrapper to pass `None, &[]`, preserving its existing unfiltered behaviour. - Update all 9 in-file test sites to pass `None, &[]`. src/openhuman/agent/harness/tests.rs - Update all 3 `run_tool_call_loop` test sites to pass `None, &[]`. src/openhuman/agent/bus.rs - Add `target_agent_id: Option<String>`, `visible_tool_names: Option<HashSet<String>>`, and `extra_tools: Vec<Box<dyn Tool>>` fields to `AgentTurnRequest`, with rustdoc explaining each. - Destructure the new fields in the `agent.run_turn` handler; thread `visible_tool_names.as_ref()` and `&extra_tools` through to `run_tool_call_loop`. Augment the dispatch trace with target_agent / extra_tool_count / visible_tool_count / filter_active so production logs show whether scoping is active. - Update the in-test `test_request()` helper to populate the new fields with safe defaults. src/openhuman/agent/triage/evaluator.rs - Update the triage `AgentTurnRequest` initializer to set `target_agent_id = Some("trigger_triage")` (for tracing) with `visible_tool_names: None` + `extra_tools: Vec::new()` because the classifier intentionally runs against an empty registry and emits a structured JSON decision rather than calling tools. src/openhuman/channels/runtime/dispatch.rs - Update the channel-message `AgentTurnRequest` initializer to set the three new fields to safe defaults (`None` / `None` / empty vec). Commit 4b will replace these with the real onboarding-flag based routing. src/openhuman/tools/impl/agent/mod.rs - Bug fix: `dispatch_subagent` previously took `_skill_filter: Option<&str>` but discarded the value, hardcoding `SubagentRunOptions::skill_filter_override = None`. That meant `SkillDelegationTool::execute()` synthesising `dispatch_subagent("skills_agent", ..., Some("gmail"))` never actually narrowed `skills_agent`'s tool list — so even with the orchestrator's view scoped, the spawned `skills_agent` subagent would still see the full Composio catalog. Drop the underscore, propagate `skill_filter` into `skill_filter_override`, and add a tracing log line to make this path observable. This is the downstream half of the #526 leak that commit 3's orchestrator- side scoping alone wouldn't have caught. Tests: 8/8 `tool_loop` tests pass, 3/3 harness `tests.rs` cases pass, 323/324 agent module tests pass overall (the one failure is the same pre-existing Windows-path bug in `self_healing::tool_maker_prompt_ includes_command` that fails identically on the upstream baseline). No existing test expectations were changed. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(dispatch): route channel messages to welcome/orchestrator by onboarding flag (#525) Wires the per-agent tool scoping plumbing from commit 4a into the channel-message dispatch path. Each incoming channel message now picks the active agent — `welcome` pre-onboarding, `orchestrator` post — based on `Config::onboarding_completed`, loads the matching definition from the global `AgentDefinitionRegistry`, synthesises any `delegate_*` tools the agent declares in its `subagents` field, and passes everything through to `agent.run_turn` on the bus. This is the half of #525 that makes the welcome agent actually run for new users — the welcome definition has existed since upstream PR #522 but had no caller; nothing in dispatch consulted the onboarding flag, so every channel message ran through the same generic tool loop with the full registry exposed. Changes: src/openhuman/channels/runtime/dispatch.rs - New `AgentScoping` struct carrying the three new `AgentTurnRequest` fields (`target_agent_id`, `visible_tool_names`, `extra_tools`) plus an `unscoped()` constructor for safe-fallback paths. - New async `resolve_target_agent(channel)` helper: * fresh `Config::load_or_init().await` per turn (no cache — the loader reads from disk every call, verified at `config/schema/load.rs:409`, so the welcome→orchestrator handoff is observed on the next message after `complete_onboarding(complete)` flips the flag, with no need for an explicit handoff event); * picks `"welcome"` or `"orchestrator"` based on the flag and emits a structured `[dispatch::routing] selected target agent` info trace recording the choice + the flag value, satisfying the #525 acceptance criterion `"agent-selection logs clearly record why each agent was selected at onboarding boundaries"`; * looks up the definition in `AgentDefinitionRegistry::global()`, gracefully falling back to `AgentScoping::unscoped()` (= legacy behaviour, no filter, no extras) if the registry isn't initialised or the definition isn't found, so a routing miss never fails the user message; * for agents with a non-empty `subagents` field, awaits `composio::fetch_connected_integrations(&config)` and runs `orchestrator_tools::collect_orchestrator_tools` to materialise per-turn delegation tools (`research`, `plan`, `delegate_gmail`, …). Agents with empty `subagents` get an empty extras vec. - New `build_visible_tool_set(definition, &extra_tools)` helper that returns `Some(union)` for `ToolScope::Named` agents (their named list ∪ the names of the synthesised delegation tools) and `None` for `ToolScope::Wildcard` agents to preserve the unfiltered semantics — so agents like `skills_agent` and `morning_briefing` that already work via `wildcard + category_filter` keep their existing behaviour without this layer interfering. - `process_channel_message` calls `resolve_target_agent` once per turn, drops the placeholder defaults from commit 4a, and feeds the real `target_agent_id`/`visible_tool_names`/`extra_tools` into `AgentTurnRequest`. - New imports: `AgentDefinition`, `AgentDefinitionRegistry`, `ToolScope`, `Config`, `fetch_connected_integrations`, `orchestrator_tools`, `Tool`, `HashSet`. End-to-end behaviour after this commit: 1. New user, `onboarding_completed=false`: dispatch picks `welcome`, loads its 2-tool TOML scope, builds `visible_tool_names = {complete_onboarding, memory_recall}`, no extras, hands off to the bus. Bus handler applies the filter → welcome's LLM sees exactly 2 tools. 2. Welcome agent guides the user through setup, eventually calls `complete_onboarding(action="complete")` → flag persists to disk via `config.save()`. 3. Next user message: dispatch reads the flag fresh, picks `orchestrator`, fetches connected Composio integrations, expands `subagents = ["researcher", "planner", "code_executor", "critic", "archivist", { skills = "*" }]` into delegate_research / delegate_plan / delegate_run_code / delegate_review_code / delegate_archive_session + one delegate_<toolkit> per connected integration. visible_tool_names is the union with the 4 direct tools from orchestrator's `[tools] named` list. LLM sees the scoped delegation surface, not the full 1000+ Composio catalog. #526's runtime leak is now fixed end-to-end: the orchestrator's LLM prompt only contains the tools its TOML allows, and the SkillDelegationTool path narrows skills_agent to a single toolkit via the `skill_filter` propagation fix from commit 4a. No agent at any layer sees more than its definition declares. Tests: 599/599 channel module tests pass — including `runtime_dispatch::dispatch_routes_through_agent_run_turn_bus_handler` and the telegram integration variant, which exercise the full bus roundtrip with the new fields populated. No existing assertions were modified. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(debug_dump): apply orchestrator definition filter to main dump (#526) Replaces the explicit `empty_filter: HashSet::new()` in `render_main_agent_dump` with a real visibility whitelist derived from the orchestrator's `AgentDefinition`. The "main" dump path now mirrors the runtime dispatch path from commits 4a/4b — same definition, same delegation tool synthesis, same filter — so `openhuman agent dump-prompt main` shows what the LLM actually sees in production instead of the unfiltered global registry. Before this commit, `dump-prompt main` always rendered every tool in the registry regardless of which agent was supposed to run, which is exactly the symptom #526 reports: "agent prompt tool scopes leak full GitHub tool catalog". The runtime fix in commit 4b stops the leak in production but the dump path was the user's primary observability tool for inspecting prompts, so leaving it unscoped would mask future regressions and confuse debug sessions. Changes in `src/openhuman/context/debug_dump.rs`: * `dump_agent_prompt` now loads `AgentDefinitionRegistry` once at the top (previously only loaded inside the sub-agent branch). When the request is for "main" or "orchestrator_main", it looks up the "orchestrator" definition from the registry and passes it into `render_main_agent_dump` along with the registry itself. Missing orchestrator entry → structured error listing known agents instead of silently rendering an unfiltered prompt. * `render_main_agent_dump` signature gains `registry: &AgentDefinitionRegistry` and `orchestrator_def: &AgentDefinition`. Inside, it: - calls `collect_orchestrator_tools(orchestrator_def, registry, connected_integrations)` to synthesise the same per-turn delegation tools (`research`, `plan`, `delegate_<toolkit>`, …) that dispatch generates; - extends `prompt_tools` with the synthesised extras so they contribute to the rendered tool catalogue; - builds `visible_filter: HashSet<String>` from `orchestrator_def.tools` (the `[tools] named` list) ∪ the names of the synthesised extras, falling back to an empty HashSet when the orchestrator definition uses `ToolScope::Wildcard` (which the prompt builder treats as "no filter, every tool visible") so dump consumers that supply a wildcard orchestrator (custom workspace overrides, tests) retain the legacy unscoped behaviour; - replaces `visible_tool_names: &empty_filter` in the `PromptContext` with `&visible_filter`; - filters the returned `tool_names` and `skill_tool_count` by the same predicate so the `DumpedPrompt` summary fields match what the prompt text actually contains. Tests: * Replaces the previous `render_main_agent_dump_includes_tool_ instructions_and_skill_count` test with two more focused cases: 1. `render_main_agent_dump_wildcard_scope_shows_full_tool_set` — regression guard for the legacy wildcard path. Builds a wildcard-scoped orchestrator definition, asserts every tool from `tools_vec` survives, and checks the standard system- prompt skeleton (Tools section, Tool Use Protocol, cache boundary) still renders. 2. `render_main_agent_dump_named_scope_filters_to_whitelist` — the #526 regression guard. Builds an orchestrator with `ToolScope::Named(["query_memory", "ask_user_clarification"])` and a `tools_vec` containing `shell`, `query_memory`, and `GMAIL_SEND_EMAIL`. Asserts the dump's `tool_names` is exactly `["query_memory"]` — `shell` and `GMAIL_SEND_EMAIL` are in the global registry but NOT in the whitelist, so they MUST be excluded. If a future change reintroduces the unfiltered behaviour this test fails immediately. * Adds two test helpers: `wildcard_orchestrator_def()` builds a minimal orchestrator definition with all `omit_*` flags set and `ToolScope::Wildcard`, and `registry_with_orchestrator(orch)` wraps it in an `AgentDefinitionRegistry` so the tests can call `render_main_agent_dump` without going through the full TOML loader. 11/11 debug_dump tests pass. The two new guards plus the 9 existing sub-agent / filter / composio-stub tests all run clean. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test(dispatch): unit tests for build_visible_tool_set + cargo fmt cleanup (#525, #526) Adds focused unit tests for the per-agent scoping helper landed in commit 4b and runs `cargo fmt` across the files touched by this PR. Why scoping unit tests, not full integration tests: `resolve_target_agent` is async and reads `Config::load_or_init().await` which does a real disk read every call (no cache, verified at `config/schema/load.rs:409`). Mocking that requires either spinning up a full workspace under a temp dir with a config.toml containing the right `onboarding_completed` value, or adding a test-only injection point on the public Config API. Both are tractable but invasive enough to belong in their own follow-up PR. The end-to-end dispatch path is already covered by the existing channel integration tests (`dispatch_routes_through_agent_run_turn_bus_handler` etc.) which exercise the full bus roundtrip with the new fields populated, and which still pass after the new resolver landed (it gracefully falls back to `AgentScoping::unscoped()` when no orchestrator definition is registered in the test environment). Pure-function unit tests for `build_visible_tool_set` cover the branching logic that does the actual scoping work: how the named whitelist + extras union is built, how Wildcard scope is preserved, how duplicates are de-duplicated, etc. That's the part most likely to drift in future changes, so it's the part most worth fencing with focused tests. Tests added (all in `src/openhuman/channels/runtime/dispatch.rs` under the new `scoping_tests` module): * `wildcard_scope_yields_none_filter` — `ToolScope::Wildcard` must produce `None` regardless of whether extras are present, so skills_agent / morning_briefing keep their full skill-category catalogue. * `named_scope_without_extras_returns_named_only` — the welcome agent's path: 2 named tools, no delegation, exactly 2 entries in the visibility whitelist. * `named_scope_with_extras_returns_union` — the orchestrator's path: 3 direct named tools + 3 synthesised extras (research, delegate_gmail, delegate_github) → 6 entries. * `empty_named_with_extras_returns_extras_only` — guards a future "delegation-only" agent layout where the agent has no direct tools of its own, just spawns subagents. * `empty_named_with_no_extras_returns_empty_set` — guards the distinction between `None` (no filter, all visible) and `Some(empty)` (filter active, nothing matches). Important because the prompt loop's `is_visible` check treats them differently. * `duplicate_names_across_named_and_extras_are_deduplicated` — the HashSet handles collisions automatically, but the test pins that behaviour so a future migration to `Vec<String>` (which would silently double-count) gets caught. * `agent_scoping_unscoped_has_no_filter_or_extras` — pins the safe-fallback constructor's contract. Used when the registry is uninitialised or the target agent is missing — every field must default to "no scoping" so the channel turn falls back to legacy unfiltered behaviour rather than crashing. Plus `cargo fmt` run across the 6 files modified by this PR. No behavioural changes. Final test status across all commits 2-6 in this PR: * agent::harness::definition: 10/10 ✅ (4 new for Subagents schema) * agent::harness::tool_loop: 8/8 ✅ * agent::harness::tests: 3/3 ✅ * tools::orchestrator_tools: 5/5 ✅ (5 new) * channels::*: 599/599 ✅ (incl. dispatch integration) * channels::runtime::dispatch::scoping_tests: 7/7 ✅ (7 new) * context::debug_dump: 11/11 ✅ (1 replaced + 1 new) * Total agent module: 323/324 (one pre-existing Windows path failure in `self_healing::tool_maker_prompt_includes_command` confirmed identical against upstream/main baseline) Pre-existing Windows-environment test failures NOT caused by this PR and out of scope (all confirmed identical on upstream baseline; CI on Linux is unaffected): * self_healing::tool_maker_prompt_includes_command (PathBuf separator) * cron::scheduler::run_job_command_success / _failure (Unix shell) * composio::trigger_history::archives_triggers_in_daily_jsonl... (path) * local_ai::paths::target_paths_preserve_absolute_overrides (path) * security::policy::checklist_root_path_blocked (POSIX absolute) * security::policy::checklist_workspace_only_blocks_all_absolute (POSIX) * tools::implementations::browser::screenshot::screenshot_command_ contains_output_path (browser binary lookup) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(welcome): upgrade bare-install nudge with concrete integration pitches (#525) Follow-up to #522 that addresses a rough UX edge in the welcome agent prompt: users who arrive with only an API key configured (no channels, no Composio integrations, no web search / browser / local AI) were getting a "gentle suggestion" to connect something without any concrete picture of what they'd actually unlock. The welcome agent would finish onboarding, hand off to orchestrator, and leave the user staring at a functional-but-empty assistant with no roadmap for how to make it useful. This commit rewrites the prompt to handle sparse setups explicitly. No Rust changes — this is prompt.md only, picked up at build time via the existing `include_str!` loader in `agents/mod.rs`. Changes to `src/openhuman/agent/agents/welcome/prompt.md`: * Step 2's "point out what's missing" sub-point is rewritten from a single "gently suggest" line into a four-case decision tree keyed off `check_status` state: - No API key → critical, block completion. - Integrations yes, channels no → note the Tauri-only reach limitation, suggest a messaging platform. - Channels yes, integrations no → degraded assistant, nudge toward Composio. - Nothing beyond the API key → the "bare install" case, gets the new Step 2.5 treatment. * New **Step 2.5: Handling a bare install** section added after Step 2. Spells out what the user DOES have (sandboxed reasoning + coding assistant with memory), what they're MISSING (any external action), and how to structure the message: state the current capability honestly, pitch 2-3 specific integrations with concrete example prompts, point to Settings → Integrations / Channels, and leave room for the user to opt into the coding-only experience if that's what they actually want. For bare-install users the word budget stretches to 250-400 words (up from 200-350) so the concrete pitches and example prompts actually fit without cramming. * New **Integration capability reference** section giving the LLM a menu it can draw from when pitching integrations. Each entry is a one-line "connect X → I can Y" with a concrete example prompt the user could send next: - Gmail: "Summarise the most important emails that came in overnight and flag anything that needs a reply today." - Google Calendar: "What's on my calendar tomorrow, and do I have a 30-minute gap before 2pm?" - GitHub: "List open issues on my main project tagged 'bug' and summarise which ones look newest or most urgent." - Notion: "Pull up my 'Ideas' Notion database and show me the three newest entries." - Slack / Discord / Linear / Jira / etc. with similar shapes. Plus a sub-section for messaging platforms (Telegram / Discord / Slack / iMessage / WhatsApp / Signal / web-fallback) that clarifies which each is best for, and a sub-section for the other capabilities (web search, browser automation, HTTP requests, local AI) that explains what breaks without them. The LLM is told NOT to list everything — just pick 2-3 most likely to matter, defaulting to Gmail + GitHub + one of {Calendar, Notion} as the top-3 pitch when no profile context is available. * Tone guidelines updated to document the stretched word budget for bare installs (200-350 for configured users, 250-400 for bare installs). * "What NOT to do" list updated: - Explicitly allows product-tour-style listing ONLY in the bare-install case (Step 2.5), forbids it elsewhere. - Clarifies that describing what WOULD unlock with integration X is fine and encouraged; claiming a capability the user doesn't have is still forbidden. - Adds a new "Don't gloss over a bare install" entry that pins the rule: API-key-only users get concrete pitches and example prompts, not vague suggestions. Scope note: this commit does NOT change the completion logic. `complete_onboarding(complete)` still accepts API-key-only as the minimum bar — that's a separate design question for the maintainer about whether zero-integration users should be gatekept. This change improves what the welcome agent SAYS to those users, not whether they're allowed to proceed. Tests: all 14 `agent::agents::tests` pass (including `welcome_has_onboarding_and_memory_tools` which validates the welcome agent's declarative shape is unchanged). The prompt.md edit is pure content — no schema changes, no tool additions. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(web-channel): route Tauri in-app chat to welcome/orchestrator + Windows fsync fix (#525) Closes the web-channel-side half of the #525 welcome agent routing. Also bundles a small pre-existing Windows compatibility fix for `app_state::ops::sync_parent_dir` that was blocking end-to-end testing of this branch on Windows. ## Web channel routing (primary change) Commit 4b ( |
||
|
Steven EnamakelandGitHub
|
3a20599f45 |
feat: dynamic connected integrations in agent system prompts (#520)
* feat(agent): add support for connected integrations in system prompts - Introduced a new `fetch_connected_integrations` method to retrieve and populate active Composio integrations for the agent. - Updated the `Agent` struct to include a `connected_integrations` field, allowing the system prompt to display available external services. - Enhanced the `build_system_prompt` method to incorporate connected integrations, improving the context provided to users during interactions. - Added a `ConnectedIntegrationsSection` to the prompt rendering, ensuring visibility of active integrations in the system prompt output. - Overall, these changes enhance the agent's ability to leverage connected services, improving user experience and interaction capabilities. * feat(debug_dump): integrate connected integrations into agent prompt dumps - Added a new `fetch_connected_integrations_for_dump` function to retrieve active integrations for the agent during prompt dumps. - Updated the `render_main_agent_dump` function to include connected integrations, enhancing the context provided in the debug output. - Improved the overall structure and clarity of the debug dump process, ensuring that connected integrations are accurately represented in the agent's prompt context. * refactor(agent): streamline integration fetching for system prompts - Refactored the `fetch_connected_integrations` method in the `Agent` struct to delegate integration fetching to a new centralized function in the `composio` module, enhancing code clarity and maintainability. - Updated the `fetch_connected_integrations_for_dump` function to utilize the new centralized fetching logic, ensuring consistent integration retrieval across different contexts. - Improved the overall structure of integration handling, allowing for better error management and logging during the fetching process. * feat(agent): add connected integrations support to parent execution context - Introduced a new field `connected_integrations` in the `ParentExecutionContext` struct to store active Composio integrations. - Updated relevant functions to utilize the new `connected_integrations` field, ensuring that system prompts and agent dumps reflect the current integrations. - Enhanced the integration cache management by implementing cache invalidation logic when connections are created or deleted, improving the accuracy of integration data across sessions. - Overall, these changes enhance the agent's ability to leverage connected services, providing users with better context during interactions. * feat(agent): initialize connected integrations in subagent context - Added a `connected_integrations` field to the `ParentExecutionContext` and `Agent` struct, allowing for the storage and retrieval of active Composio integrations. - Updated the `dispatch_target_agent` function to populate the `connected_integrations` field when creating a new sub-agent context. - Enhanced the `fetch_connected_integrations` method to return an `Option<Vec<ConnectedIntegration>>`, improving error handling and caching logic. - These changes improve the agent's ability to manage and utilize connected integrations, enhancing user interactions and context awareness. * refactor(agent): improve caching logic in fetch_connected_integrations - Updated the `fetch_connected_integrations` function to handle caching more effectively by using a match statement. - The function now caches results only when the backend is reachable, preventing unnecessary caching when the client is unavailable. - This change enhances error handling and ensures that subsequent calls with different configurations can retry without stale data. * style: apply cargo fmt formatting * feat(agent): enhance connected integrations handling and caching - Updated the `dispatch_target_agent` function to initialize connected integrations for sub-agents, ensuring they have access to the latest integrations. - Improved the caching mechanism for connected integrations by using a `HashMap` keyed by configuration identity, allowing for user-specific caching and better isolation of integration data. - Refactored the `invalidate_connected_integrations_cache` function to clear the entire cache instead of setting it to `None`, enhancing cache management. - Added a new method `load_from_default_paths` in the `Config` struct to reliably load user configurations without being affected by environment variable overrides, improving the debug dump process. - Enhanced the rendering of connected integrations in system prompts to provide clearer instructions based on available tools, improving user interaction clarity. * feat(agent): add method to set connected integrations - Introduced a new `set_connected_integrations` method in the `Agent` struct to allow for replacing the agent's connected integrations from external sources, enhancing flexibility in integration management. - Updated the caching mechanism for connected integrations to utilize `LazyLock`, improving initialization efficiency and thread safety. * style: apply cargo fmt |
||
|
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
|
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
|
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
|
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 |
||
|
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 |
||
|
|
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 |
||
|
Steven EnamakelandGitHub
|
0609493e1a | Add RAM-tiered local AI presets (#425) | ||
|
|
200db04fc7 |
feat: scope user data to per-user directories (#370)
* feat(config): add user ID retrieval and workspace scoping for authenticated users - Implemented `read_authenticated_user_id` to extract the user's ID from `auth-profiles.json`, avoiding a dependency cycle with the credentials module. - Introduced `maybe_scope_workspace_to_user` to create user-specific workspace directories based on the authenticated user ID, ensuring isolated workspace data. - Updated the configuration loading process to call `maybe_scope_workspace_to_user`, enhancing user data management. - Added unit tests for the new functionality, ensuring correct behavior in various scenarios. This change improves user experience by providing personalized workspace management based on authentication status. * feat(config): enhance user management with active user state handling - Added functions to manage the active user state, including `read_active_user_id`, `write_active_user_id`, and `clear_active_user`, allowing for user-specific configuration and workspace isolation. - Introduced `default_root_openhuman_dir` to standardize the retrieval of the root directory for user data. - Updated configuration loading to support user-scoped directories, improving the overall user experience by ensuring personalized settings and workspace management. This change enhances the OpenHuman platform by enabling better user data management and isolation. * feat(credentials): enhance user directory management during session storage - Added logic to create and activate user-scoped directories based on the resolved user ID when storing session data, ensuring credentials are saved in the correct location. - Implemented error handling for directory creation and active user ID writing, with appropriate logging for failures. - Updated the configuration loading process to reflect the newly activated user directory, improving user-specific settings management. - Enhanced the `get_data_dir` function to return user-scoped directories if an active user is set, streamlining data access. This change improves user experience by ensuring that session data is correctly organized and accessible based on user context. * refactor(tests): update user ID handling and improve test coverage - Renamed and refactored tests to better reflect functionality, focusing on active user ID management. - Removed the `write_auth_profiles` helper function and replaced it with direct calls to `write_active_user_id` for clarity. - Enhanced tests to cover scenarios for reading and clearing active user IDs, ensuring accurate behavior in user-specific configurations. - Added a new test for building user directory paths, improving overall test coverage for user management features. This change streamlines the testing process and enhances the clarity of user ID handling in the configuration schema. * refactor(paths): streamline model and binary path resolution - Introduced a new `shared_root_dir` function to centralize the logic for determining the shared root openhuman directory, improving code clarity and reducing duplication. - Updated `workspace_ollama_dir` and `workspace_local_models_dir` functions to utilize the new shared root directory, ensuring consistent path resolution for user-specific and shared resources. - Enhanced the `model_artifact_path` function to leverage the new directory structure, improving the organization of model artifacts. This refactor enhances maintainability and clarity in the path management for local AI resources. * style: apply cargo fmt formatting Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * refactor(paths): streamline directory management for model artifacts - Updated the `model_artifact_path` function to utilize a new `shared_root_dir` function, which centralizes the logic for determining the root openhuman directory. - Enhanced the `config_root_dir` function to improve clarity and maintainability. - Adjusted the `workspace_ollama_dir` and `workspace_local_models_dir` functions to leverage the new shared directory logic, ensuring consistent path resolution across the application. These changes improve the organization of directory management and enhance the overall clarity of the codebase. --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
|
faa881c5f1 |
Feat/343 screen intelligence e2e tests (#359)
* test(screen_intelligence): add E2E pipeline proof tests for #343 Add layered test coverage proving the full capture → vision → memory pipeline: screenshot save/cleanup disk paths, VisionSummary serde roundtrip, JSON-RPC shape tests for status and vision_recent endpoints. - tests/screen_intelligence_vision_e2e.rs: save_screenshot_to_disk creates a PNG and keep_screenshots=false cleanup removes it; VisionSummary struct serializes/persists/is queryable end-to-end; platform support table + macOS checklist added to module doc - tests/json_rpc_e2e.rs: screen_intelligence_status shape test (platform_supported, session.active, permissions.screen_recording); vision_recent returns empty summaries without an active session - src/openhuman/screen_intelligence/tests.rs: save_screenshot_to_disk unit tests for the write path and the no-image-ref error path Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(screen_intelligence): enhance vision summary persistence and error handling - Added new fields to track vision persistence count, last persisted key, and last persist error in SessionRuntime and SessionStatus. - Implemented error handling for vision summary persistence, ensuring errors are logged and state is updated accordingly. - Introduced a new method to analyze a frame and persist the summary, improving the vision processing pipeline. - Updated tests to validate the new functionality and ensure proper behavior with mocked vision outputs. This commit improves the robustness of the screen intelligence pipeline by enhancing the tracking and handling of vision summary persistence. --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com> |
||
|
YellowSnnowmannandGitHub
|
1acc916244 |
feat: extract and load user working memory from skill sync payloads (#357)
* feat: implement user working memory extraction from skill sync payloads - Added functionality to enable the extraction of user working memory from successful skill syncs, allowing for persistent storage of user preferences, goals, constraints, and entities. - Introduced a new configuration option in to toggle working memory extraction. - Created comprehensive documentation on the working memory extraction process, detailing its implementation and privacy considerations. - Updated memory loading logic to include working memory entries in the context provided to agents, enhancing personalization capabilities. - Enhanced logging for memory extraction processes to improve observability and debugging. This feature enhances the user experience by allowing skills to maintain context across interactions, improving the overall effectiveness of the OpenHuman platform. * docs: update architecture documentation to include user working memory integration * refactor: centralize working memory constants and enhance extraction logic - Moved `WORKING_MEMORY_KEY_PREFIX` and `WORKING_MEMORY_LIMIT` constants to `memory_context.rs` for better organization and accessibility. - Updated `MemoryLoader` to utilize these constants, improving code clarity. - Enhanced working memory extraction logic in `MemoryWriteJob` to conditionally persist user working-memory documents based on the job type. - Improved logging for memory extraction processes to provide clearer insights during execution. - Adjusted tests to ensure consistent behavior with the new working memory extraction logic. * chore: update OpenHuman version to 0.51.8 and refactor JSON-RPC test for clarity - Bumped the OpenHuman version in Cargo.lock from 0.51.6 to 0.51.8. - Refactored the JSON-RPC end-to-end test to improve readability by encapsulating the result assertion logic within a block, enhancing clarity in the flow of data handling. |
||
|
|
b8ae9674b3 |
fix(memory): graph query returns namespace data and add sync e2e tests (#344) (#363)
* fix(memory): graph query returns namespace data and add sync e2e tests (#344) The knowledge graph UI showed empty because graph_query(None) only queried the graph_global table, while ingestion writes to graph_namespace. Now graph_query(None) queries both tables via graph_query_all(), merging results. Changes: - Added graph_query_all() in unified graph store to query across all namespaces - MemoryClient::graph_query(None) now uses graph_query_all() instead of graph_query_global() - MemoryWorkspace passes selectedNamespace to the RPC call - Added diagnostic logging in ingestion pipeline (RelEx model availability, extraction counts) - Added debug logging in tauriCommands for unexpected response shapes - Added 2 integration tests proving document sync populates the graph (ignored by default for CI, run with --ignored) Closes #344 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: remove trailing comma for Prettier compliance Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
YellowSnnowmannandGitHub
|
0c14aea96a |
Improve autocomplete observability and runtime controls in settings + JSON-RPC (#308)
* Enhance AutocompletePanel logging and functionality - Introduced MAX_LOG_ENTRIES constant to limit log entries to 200. - Updated log formatting to include timestamps with milliseconds for better precision. - Added UI logging for various actions (e.g., saving settings, starting/stopping autocomplete) to improve traceability. - Enhanced error handling in refreshStatus, acceptSuggestion, and other functions to log specific failure messages. - Added unit tests for AutocompletePanel to ensure functionality and logging behavior. This update improves the overall user experience by providing clearer logs and better error handling in the Autocomplete feature. * Refactor accessibility and autocomplete components for improved error handling and logging - Updated to log role changes as debug information instead of returning an error, allowing for more flexible handling of role fluctuations. - Increased the timeout for autocomplete refresh operations from 15 seconds to 120 seconds to accommodate longer processing times, enhancing reliability. - Improved error handling in the autocomplete engine to preserve previous suggestions and provide clearer error messages when operations are aborted. These changes enhance the user experience by providing better logging and more robust handling of focus and autocomplete functionalities. * Enhance AutocompletePanel functionality and improve error handling - Refactored loadHistory to return an empty array when Tauri is not available, improving error handling. - Introduced waitForAcceptedHistoryEntry to ensure the history is loaded before accepting suggestions, enhancing user experience. - Updated the accept suggestion logic to use the new waitForAcceptedHistoryEntry function, ensuring the correct suggestion is applied. - Modified tests to reflect changes in the accept suggestion API, ensuring accurate functionality. These changes improve the reliability and responsiveness of the autocomplete feature. |
||
|
|
b589a29e77 |
Extract socket controller into dedicated domain module (#340)
* refactor: remove global_engine usage in tests and instantiate AccessibilityEngine directly - Updated the test suite to eliminate the use of global_engine, replacing it with a direct instantiation of AccessibilityEngine. - This change enhances test isolation and clarity by ensuring that each test operates with its own instance of the engine, improving reliability and maintainability. * feat: add socket module for skill communication - Introduced a new `socket` module to facilitate communication between skills, enhancing the modularity and organization of the codebase. - Updated imports in `qjs_engine.rs` to reference the new `SocketManager` from the `socket` module, streamlining socket management for skill interactions. - Removed the deprecated `socket_manager` module from the skills module, improving clarity and reducing redundancy in the code structure. * feat: integrate socket controllers and schemas into core functionality - Added socket-related registered controllers and schemas to the core build functions, enhancing the communication capabilities within the OpenHuman framework. - Updated the `build_registered_controllers` and `build_declared_controller_schemas` functions to include socket components, ensuring comprehensive integration of the new socket module. * feat: enhance QuickJS skill runtime with socket manager integration - Updated the `bootstrap_skill_runtime` function to initialize and register the `SocketManager` globally, allowing RPC handlers to access socket functionalities. - Improved documentation to reflect the addition of socket management capabilities alongside the QuickJS skill runtime. - Cleaned up imports in `event_handlers.rs` to streamline the codebase. * refactor: remove socket manager integration from skill runtime - Removed the `SocketManager` integration from the `bootstrap_skill_runtime` function, simplifying the socket management process. - Eliminated the `socket_manager` field and related methods from the `RuntimeEngine` struct, streamlining the codebase. - Cleaned up unused MCP handlers and socket-related imports in the event handlers, enhancing code clarity and maintainability. * refactor: remove sync_tools calls from skill status handling - Eliminated unnecessary calls to `sync_tools()` in the `RuntimeEngine` during skill status changes, simplifying the skill lifecycle management. - This change enhances performance by reducing redundant synchronization operations during skill execution and shutdown processes. * feat: enhance socket event handling with improved logging - Added logging for incoming socket events to improve observability, including event name and data size. - Implemented detailed debug logging for event payloads, ensuring clarity on the data being processed. - Updated event handling logic to streamline routing for webhook requests and inbound channel messages, enhancing the overall responsiveness of the system. - Introduced logging for unhandled events to aid in debugging and monitoring. * feat: enhance socket management and auto-connect functionality - Updated the `bootstrap_skill_runtime` function to clone the `SocketManager` instance for global registration, ensuring proper socket management. - Introduced background tasks for auto-starting skills and auto-connecting to the backend using stored session tokens, improving startup efficiency and user experience. - Added detailed logging for session token checks and connection attempts, enhancing observability and debugging capabilities during socket operations. * feat: enhance skill selection and tool management in tests - Introduced a new `manifests_in_dir` function to retrieve skill manifests from a specified directory, improving skill discovery. - Added `select_skill_id` function to prioritize skill selection based on environment variables and preferred candidates, enhancing flexibility in test configurations. - Updated the test suite to utilize the new skill selection logic, ensuring more robust and configurable test scenarios. - Improved handling of tool selection with enhanced logging and fallback mechanisms for better debugging and usability. * format code:wq * feat: add Rust checks and formatting commands to package.json - Introduced new scripts for Rust checks and formatting in both the main and app package.json files. - Updated pre-push hook to include Rust compile checks, enhancing pre-push validation. - Modified existing format commands to integrate Rust formatting, ensuring consistency across codebases. * fix: improve formatting of the "Keep Screenshots" label description - Adjusted the formatting of the description text for better readability by breaking it into multiple lines within the `ScreenIntelligencePanel` component. * fix: install rustls crypto provider before WebSocket TLS connect The socket auto-connect was panicking with "Could not automatically determine the process-level CryptoProvider" because tokio-tungstenite uses rustls for wss:// but no crypto provider was installed. Install the ring provider before each connect attempt. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: use dynamically selected skill in sync memory tests The tests hardcoded 'example-skill' which no longer exists in the skills directory. Now dynamically picks the first available skill (preferring server-ping) so tests work regardless of which skills are present. 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 EnamakelandGitHub
|
e925e8a319 |
Fix local reset flow and Accessibility permission handling (#324)
* refactor: clean up imports and improve code structure in skills_cli and registry_ops - Removed unused imports in `skills_cli.rs` and `registry_ops.rs` to enhance code clarity. - Streamlined import statements for better organization and readability. - Minor adjustments in `engine.rs` to maintain consistency in import usage. * fix: update UI text and styles for MemoryWorkspace and SkillSetupWizard components - Changed the title in MemoryWorkspace to "Memory (EverMind)" for clarity. - Updated text colors in SkillSetupWizard for better visibility and consistency. - Enhanced button styles and loading indicators for improved user experience. * feat: implement reset functionality for OpenHuman data and enhance app data clearing process - Added a new utility function `resetOpenHumanDataAndRestartCore` to reset local OpenHuman data and restart the core process. - Updated `clearAllAppData` in `SettingsHome` to utilize the new reset function, improving the app's data clearing process. - Enhanced error handling during the data reset and session clearing operations to ensure robustness. - Introduced tests for the new reset functionality to validate its behavior and integration. * refactor: remove screen recording permission from AccessibilityPanel - Eliminated the screen recording permission check and associated UI elements from the AccessibilityPanel component. - Updated tests to ensure the screen recording option is no longer present in the rendered output, improving clarity and focus on relevant permissions. * chore: update package.json files to integrate Husky for Git hooks - Added Husky as a dev dependency in both package.json files to manage Git hooks. - Included "prepare" and "postinstall" scripts in the main package.json to ensure Husky is set up correctly. - Cleaned up the app's package.json by removing the "prepare" script, as it is now handled in the main package.json. - Enhanced logging in tauriCommands.ts for better debugging during the reset process. * fix: update variable name for clarity in ops.rs test assertions - Changed the variable name from `data` to `value` in the test assertions to enhance clarity and better reflect its purpose. - Ensured that the assertions remain functional and maintain the integrity of the test logic. * feat: enhance skill selection logic in skills_debug_e2e.rs - Introduced a new function `select_skill_id` to improve skill selection based on environment variables and preferred skills. - Updated the skill ID retrieval process to prioritize user-defined skills while maintaining a fallback to the default skill. - Enhanced documentation to clarify the usage of environment variables for skill testing. * format |
||
|
Steven EnamakelandGitHub
|
ef708bdd20 |
refactor(core): move app state ownership into the Rust core (#320)
* refactor(core): integrate CoreStateProvider and streamline state management - Replaced UserProvider with CoreStateProvider in App component to centralize state management. - Updated various components to utilize the new CoreStateProvider for accessing session tokens and user data. - Refactored hooks and components to eliminate direct Redux store dependencies, enhancing modularity and maintainability. - Introduced a new core state management structure to improve the handling of user authentication and onboarding states. This refactor aims to simplify state access across the application and improve overall code clarity. * fix: restore polyfills import and clean up component imports - Reintroduced the import of polyfills in main.tsx to ensure compatibility. - Adjusted import statements in PrivacyPanel and SocketProvider for consistency. - Simplified conditional expressions in TeamInvitesPanel and TeamMembersPanel for better readability. - Refactored CoreStateProvider and store.ts to streamline state initialization. - Enhanced formatting in various files for improved code clarity and maintainability. * refactor(tests): streamline onboarding and protected route tests - Updated OnboardingOverlay tests to utilize mock state management and simplify assertions. - Refactored ProtectedRoute tests to improve readability and ensure consistent use of mock state. - Enhanced teamApi tests to replace direct API calls with core RPC method calls, improving test isolation and clarity. - Adjusted socketSelectors tests to utilize a centralized core state snapshot for better state management during tests. * refactor(onboarding): simplify onboarding state management and improve loading logic - Removed unnecessary local state for onboarding completion in OnboardingOverlay, directly utilizing snapshot data. - Enhanced loading logic to prevent unnecessary renders and improve user experience during onboarding. - Updated PrivacyPanel to handle analytics consent persistence with error handling. - Refactored TeamManagementPanel and TeamPanel to improve team data fetching logic and loading states. - Streamlined CoreStateProvider to manage session token synchronization and state updates more effectively. * chore(deps): update tempfile dependency and refactor app state management - Added `tempfile` dependency to Cargo.toml for improved temporary file handling. - Refactored app state loading and saving functions to enhance error handling and ensure data integrity. - Introduced quarantine mechanism for corrupted app state files to prevent application crashes. - Updated URL parsing logic to ensure proper formatting of API URLs. - Adjusted type definitions in schemas for better clarity and consistency. * refactor(tests): simplify mock state usage in onboarding and protected route tests - Consolidated mock state management in OnboardingOverlay and ProtectedRoute tests for improved readability. - Streamlined assertions by reducing unnecessary lines in test setups. - Enhanced consistency in mock return values across tests to ensure clarity and maintainability. * refactor(tests): enhance PublicRoute tests with mock state and routing - Updated PublicRoute tests to utilize MemoryRouter for improved routing simulation. - Simplified mock state management by integrating `useCoreState` for user authentication scenarios. - Streamlined test assertions and removed redundant preloaded state configurations for clarity and maintainability. * refactor(tests): streamline mock state usage in PublicRoute and Mnemonic tests - Simplified mock state management in PublicRoute and Mnemonic tests for improved readability. - Consolidated mock return values to reduce redundancy and enhance clarity in test setups. - Improved consistency in the usage of `useCoreState` across test files. * Refactor billing components for improved readability - Cleaned up import statements in BillingPanel.tsx for better organization. - Enhanced formatting of billing plan descriptions in billingHelpers.ts for consistency. - Improved readability of conditional checks in BillingPanel component. * Refactor API endpoint handling for clarity and consistency - Updated references from `/settings` to `/auth/me` in various modules to standardize user authentication flows. - Renamed `parse_settings_response_json` to `parse_api_response_json` for improved clarity in response handling. - Adjusted user ID extraction functions to reflect the new endpoint structure, enhancing maintainability across the codebase. - Updated test cases to align with the new endpoint naming conventions, ensuring consistency in API interactions. |
||
|
|
8381283c52 |
Fix/update api (#319)
* feat(webhooks): refactor webhook URL handling and enhance API endpoints - Introduced a new utility function `buildWebhookIngressUrl` to standardize the construction of webhook URLs across components. - Updated `WebhooksDebugPanel` and `TunnelList` components to utilize the new URL builder for improved consistency and maintainability. - Refactored API endpoints in `tunnelsApi` to reflect changes in webhook routing, ensuring all references to tunnel management are aligned with the new structure. - Adjusted user API calls to replace `/telegram/me` with `/auth/me` for better clarity and consistency in authentication flows. - Enhanced socket service to normalize channel connection update payloads, improving error handling and data integrity. These changes streamline webhook management and enhance the overall developer experience when working with webhooks. * feat(messaging): enhance Telegram and Discord channel linking functionality - Added support for managed DM linking with Telegram and OAuth flow for Discord. - Introduced `createChannelLinkToken` API to generate short-lived link tokens for messaging channels. - Updated `MessagingPanel` to handle managed linking flows, including building launch URLs and user instructions. - Enhanced configuration to include a Telegram bot username for fallback linking. - Updated tests to mock new configuration values for consistent testing. These changes improve the user experience for linking messaging channels and streamline the authentication process. * feat(api): introduce core command client and refactor API calls - Added a new `coreCommandClient` to facilitate RPC calls to core services. - Refactored existing API endpoints in `authApi`, `billingApi`, `creditsApi`, `tunnelsApi`, and `userApi` to utilize the new command client for improved consistency and maintainability. - Updated the billing API to include new endpoints for fetching balance, transactions, and managing auto-recharge settings. - Enhanced the user API to streamline user data retrieval. - Improved error handling and logging across the refactored API calls. These changes enhance the overall architecture of the API services, making them more modular and easier to maintain. * refactor(api): streamline API calls and enhance error handling - Refactored `creditsApi` and `tunnelsApi` to ensure consistent use of the new core command client. - Updated API methods to improve error handling and response parsing. - Introduced a new `authed_json` method in `BackendOAuthClient` for standardized authenticated requests. - Cleaned up unused imports and optimized code structure across various modules. These changes enhance the maintainability and reliability of the API services. * refactor(api): streamline API calls and improve code readability - Reorganized API calls in `authApi`, `billingApi`, `creditsApi`, and `tunnelsApi` to enhance consistency and maintainability. - Updated function formatting for better readability, ensuring parameters are clearly defined. - Cleaned up import statements and removed unnecessary line breaks to improve code clarity. These changes contribute to a more maintainable codebase and enhance the overall developer experience. * refactor(MessagingPanel): clean up imports and remove unused constants - Reorganized import statements for clarity and consistency. - Removed unused constants related to channel definitions and status styles to streamline the component. - Simplified the `updateField` function call in the rendering logic for better readability. These changes enhance the maintainability of the MessagingPanel component. * fix: restore helper functions removed during merge cleanup buildManagedChannelLaunchUrl and buildManagedChannelInstruction were stripped by the linter after merge resolution, breaking the build. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(messaging): enhance MessagingPanel with pending instruction handling - Introduced a new state for pending instructions to improve user feedback during channel connection processes. - Updated error handling to ensure users receive clear instructions, including URLs for manual access if automatic opening fails. - Refactored connection status updates to streamline the dispatch process and improve code readability. - Enhanced the rendering logic to display pending instructions in the UI, providing better context for users during authentication flows. * fix(api): encode channel and ID parameters in webhook and OAuth URLs - Updated the URL construction in the BackendOAuthClient to encode the channel parameter, ensuring proper formatting for requests. - Modified the get_tunnel, update_tunnel, and delete_tunnel functions to encode the ID parameter in webhook URLs, enhancing security and compatibility with special characters. * fix(auth): validate channel input for link token creation - Added validation to ensure the channel is not empty and is one of the supported types (telegram, discord). - Converted the channel string to lowercase for consistent matching. - Updated the call to create_channel_link_token to use a reference to the channel variable. * chore(todos): update TODO list with completed tasks and new feature requests - Marked several tasks as completed, including integration of the custom memory engine and skills registry into the core. - Added new items to the TODO list, including improvements for voiceover functionalities, screen intelligence, and Gmail skill enhancements. - Included tasks for debugging skills from the UI and improving prompts to reduce hallucinations. * refactor(webhooks): improve formatting of get_tunnel function for readability - Reformatted the get_tunnel function to enhance code clarity by adjusting the indentation and line breaks in the call to get_authed_value. - This change improves the maintainability of the code and aligns with the overall code style. * test(userApi): enhance userApi tests with improved mocking and error handling - Added a mock function for core command calls to streamline test setup. - Introduced a helper function to generate mock user data for consistent test cases. - Updated tests to use the mock function for simulating API responses, improving clarity and maintainability. - Enhanced error handling in tests to cover various API error scenarios, ensuring robustness in userApi.getMe functionality. * refactor(billingApi): update tests to use core command mocking and improve error handling - Replaced apiClient mocks with core command mocks for better alignment with the new API structure. - Updated test cases to reflect changes in API call expectations, enhancing clarity and maintainability. - Improved error handling in tests to ensure proper propagation of errors from core command calls. * refactor(billingApi): simplify test cases by consolidating mock function calls - Streamlined mock function calls in billingApi tests for improved readability and consistency. - Removed unnecessary line breaks in mock responses, enhancing clarity in test definitions. - Ensured that error handling and API call expectations are clearly represented in the tests. * refactor(api): rename settings endpoint to current_user for clarity - Updated the endpoint handling authenticated profile fetches to improve clarity in the codebase. - Adjusted the routing to reflect the new function name, enhancing maintainability and understanding of the API's purpose. --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
Mega MindandGitHub
|
04146bf0bf |
Fix/191 skills reliability upstream (#282)
* feat(skills): core RPC data stats, tool timeout env, ping state merge (#191) - Add openhuman.skills_data_stats and SkillDataDirectoryStats (disk usage). - Centralize tool execution timeout via OPENHUMAN_TOOL_TIMEOUT_SECS (tool_timeout). - Apply timeout to skill event loop, agent tool loop, harness default, delegate. - Ping scheduler: merge connection_error into published_state via registry. - JSON-RPC e2e: assert skills_data_stats. Closes #214 Closes #218 Part of #213 (backend) Made-with: Cursor * feat(app): skills sync stats UI, reconnect resync, FE timeouts, chat errors (#191) - useSkillDataDirectoryStats + Skills.tsx merge disk stats with skill state. - resyncRunningSkillsAfterReconnect on socket connect; disconnectSkill OAuth cleanup in finally. - withTimeout for callTool/triggerSync; VITE_TOOL_TIMEOUT_SECS in app .env.example. - Structured ChatSendError in Conversations (data-chat-send-error-code). Closes #213 Closes #215 Closes #216 Closes #217 Closes #219 Made-with: Cursor * test(e2e): onboarding helpers and skills smoke specs (#191) - shared-flows: 5-step onboarding, completeOnboardingIfVisible. - auth-access-control + voice-mode use shared helpers. - skills-registry: named skill assertion; new skill-oauth, multi-round, reconnect, lifecycle specs. Closes #220 Closes #221 Closes #222 Closes #223 Closes #224 Part of #189 (E2E helpers) Made-with: Cursor * style: rustfmt + Prettier for CI (PR #282) Fix Type Check workflow: prettier --check and cargo fmt --check. Made-with: Cursor * fix: PR #282 review — tool timeout config, tool_timeout module, CI diagnostics - Centralize VITE_TOOL_TIMEOUT_SECS in config.ts (TOOL_TIMEOUT_SECS) - Move tool_timeout to folder module; merge_published_state broadcasts SKILL_STATE_CHANGED - Resync guard after socket reconnect; qjs_engine logs data dir stat errors - E2E: registry/lifecycle/multi-round failure diagnostics; onboarding label constant - chatSendError arrow export; rustfmt/import grouping in event_loop Made-with: Cursor * test(e2e): add Gmail skill end-to-end tests - Introduced a comprehensive end-to-end test suite for the Gmail skill, covering the full lifecycle from discovery to OAuth completion and email management. - Implemented two modes: a lifecycle-only mode that validates the skill's event loop without real credentials, and a live mode that interacts with the Gmail API using actual credentials. - Added detailed environment variable requirements and usage instructions for both testing modes. Closes #XXX (replace with relevant issue number if applicable) |
||
|
sanil-23andGitHub
|
945a5c4a02 |
feat: subconscious loop — local-model background awareness via heartbeat (#268)
* feat: subconscious loop — local-model background awareness via heartbeat Add a subconscious inference layer to the heartbeat engine. On each tick, the engine reads HEARTBEAT.md tasks, builds a delta-based situation report (memory docs, graph relations, skills health, environment), and evaluates them with the local Ollama model. Architecture: - HeartbeatEngine (scheduler) delegates to SubconsciousEngine (brain) - HeartbeatConfig extended with inference_enabled, context_budget_tokens - No separate SubconsciousConfig — all config lives under [heartbeat] - Default HEARTBEAT.md ships with 3 active tasks (email, deadlines, skills) Subconscious module (src/openhuman/subconscious/): - engine.rs: tick logic, local model inference, escalation to cloud model - situation_report.rs: delta assembler (memory, graph, skills, env, tasks) - prompt.rs: task-driven system prompt for local model - decision_log.rs: dedup tracking with 24h TTL and acknowledgment - types.rs: Decision (noop/act/escalate), TickOutput, RecommendedAction - schemas.rs: RPC controllers (subconscious_status, subconscious_trigger) - integration_test.rs: two-tick lifecycle test with fixtures Decision flow: - noop: no changes, skip — no LLM call wasted - act: local model recommends actions → stored in memory KV - escalate: calls cloud model to resolve → concrete actions stored Verified with real Ollama inference (gemma3:4b): - Tick 1: ingested gmail+notion → "act: deadline needs attention" (high) - Tick 2: ingested state changes → "act: deadline moved" (high) - Skills health section populated from live skill registry Closes #145 * feat: add subconscious_actions RPC endpoint New endpoint openhuman.subconscious_actions returns stored action entries from the subconscious KV namespace, sorted by most recent first, with configurable limit (default 20). Response format: { "entries": [ { "tick_at": 1775117975.58, "actions": [...] } ], "count": 1 } The upcoming subconscious page will call this to display notifications and recommended actions to the user. * fix: budget underflow and UTF-8 panic in situation report truncation - Use saturating_add for newline byte to prevent underflow when section exactly fills the remaining budget - Truncate at valid UTF-8 char boundary using char_indices instead of raw byte slicing, which panicked on multibyte characters - Add tests for exact-fit and multibyte truncation * fix: address CodeRabbit review — shared engine, dedup, consistent schema Fixes from CodeRabbit review on PR #268: - #8 Two engine instances: Add global.rs singleton shared between HeartbeatEngine::run() and RPC handlers. Both use get_or_init_engine() so decision log, counters, and last_tick_at are always in sync. - #3 Dedup disabled: tick() now extracts actual document IDs from memory via build_situation_report_with_doc_ids() and passes them to decision_log.record(). filter_unsurfaced() actually filters now. - #5 Decision log not loaded on trigger: tick() loads persisted log from KV on first execution (total_ticks == 0), not only from run(). - #4 Inconsistent action schema: handle_escalation() normalizes agent response into RecommendedAction[] via normalize_escalation_response(). Both act and escalate paths store the same schema. - #7 Key collision: store_actions() uses millisecond timestamp + random suffix instead of second-precision truncation. - #10 No-changes unreachable: tick() checks has_new_data (unsurfaced doc IDs) OR has_memory_changes (report text) instead of naive string matching on environment section. * fix: include document content in situation report, not just titles The local model needs actual content to evaluate HEARTBEAT.md tasks meaningfully. Previously it only saw titles like "Deadline reminder" with no way to know if it's urgent. Now recalls content per namespace (up to 500 chars each, max 10 namespaces) via client.recall_namespace(). The model sees actual email text and page content alongside the task checklist. * fix: timestamp parsing, byte-boundary slicing, and truncation overshoot - schemas.rs: split on first ':' after 'actions:' prefix before parsing timestamp, so keys like 'actions:123456:xyz' parse correctly - situation_report.rs: use truncate_at_char_boundary() for error strings instead of raw byte slice which panics on multibyte characters - situation_report.rs: fix append_section and truncate_at_char_boundary to use char END offset (i + len_utf8) in take_while condition, so multibyte chars that start before but end after the budget are excluded |
||
|
YellowSnnowmannandGitHub
|
79fe36b41d | fix: remove the deadlock when re-enabling an already-active session and add unit tests for ScreenIntelligenceDebugPanel and ScreenIntelligencePanel (#275) | ||
|
YellowSnnowmannandGitHub
|
c09983b49b |
feat(about_app): add a runtime capability catalog for app discovery (#267)
* feat(about_app): introduce user-facing capability catalog - Added a new module for the capability catalog, providing a single source of truth for user-facing features in the OpenHuman app. - Implemented functions for listing, looking up, and searching capabilities, enhancing user interaction with the app's features. - Created a structured schema for capabilities, including categories and statuses, to improve organization and accessibility. - Added comprehensive end-to-end tests to validate the functionality of the new capability catalog, ensuring robust performance and reliability. This update significantly enhances the app's ability to expose its features to users, improving overall usability and experience. * feat(about_app): update capability catalog with new features and improved instructions - Revised existing capability instructions for clarity and accuracy, enhancing user guidance on accessing features. - Introduced several new capabilities related to skills and authentication, including connections to Google, Notion, and Web3 wallets, expanding the app's functionality. - Added new settings management capabilities, allowing users to manage desktop services and clear app data, improving user control over the application. These updates significantly enhance the capability catalog, providing users with more options and clearer instructions for utilizing the app's features. |
||
|
|
c134d96056 |
fix(skills): route sync RPC to onSync handler and persist state to memory (#183)
* feat(debug): add script for Notion sync memory verification and enhance memory persistence - Introduced `debug-notion-sync-memory.sh` to facilitate live testing of the Notion skill with memory verification. - The script validates the full flow from skill start to memory persistence, ensuring required environment variables are set. - Updated `handle_skills_sync` to change the RPC method from `skill/tick` to `skill/sync` for better clarity in the sync process. - Implemented `persist_state_to_memory` function to ensure published ops state is saved to memory after sync, cron, and tick events. - Enhanced end-to-end tests to validate memory persistence during skill sync and tick operations, ensuring robust functionality. This update improves the debugging process for the Notion skill and enhances the overall reliability of memory operations. * style: apply cargo fmt formatting Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(memory): implement background memory-write worker for skill state persistence - Introduced a `MemoryWriteJob` struct to encapsulate the details of memory write operations. - Added a bounded background worker using `tokio::spawn` to handle memory writes asynchronously, improving performance and responsiveness. - Updated `persist_state_to_memory` to queue memory write jobs instead of executing them directly, allowing for better flow control and error handling. - Enhanced logging for memory persistence operations to provide clearer insights into success and failure cases. - Modified event handling in `handle_message` to ensure state persistence occurs only after successful operations, reducing the risk of data loss. This update significantly enhances the memory management capabilities of the skill instance, ensuring more reliable state persistence. * feat(skills): enhance skills synchronization and memory persistence - Added detailed debug logging in `handle_skills_sync` to track skill synchronization events, improving observability during skill operations. - Updated `persist_state_to_memory` to include a memory write transaction, ensuring state persistence is handled more robustly and efficiently. - Enhanced event handling in `handle_message` to ensure memory writes are queued correctly, improving the reliability of state persistence during skill operations. These changes improve the overall functionality and reliability of skills synchronization and memory management. * feat(skills): enhance skills synchronization and memory persistence - Added detailed debug logging in `handle_skills_sync` to track skill synchronization events, improving observability during skill operations. - Updated `persist_state_to_memory` to include a `memory_write_tx` parameter, allowing for more efficient state persistence in the event loop. - Enhanced tests for skills synchronization to ensure robust memory handling and state persistence during skill operations. This update improves the reliability and traceability of skills synchronization processes, ensuring better memory management and debugging capabilities. * refactor(tests): update JSON-RPC sync handling in end-to-end tests - Enhanced comments in `json_rpc_skills_runtime_start_tools_call_stop` to clarify the sync process routing through the `skill/sync` RPC. - Updated assertions in `skills_sync_rpc_calls_on_sync_not_on_tick` to ensure proper handling of the new sync flow, verifying that the `skills_sync` method routes correctly to `onSync`. - Improved logging for better observability during skill synchronization tests, ensuring that the expected behavior aligns with the updated RPC structure. These changes improve the clarity and reliability of the end-to-end tests related to skills synchronization. * feat(env): enhance environment configuration for skills development - Updated `.env.example` to include `SKILLS_LOCAL_DIR` for local skills source directory, allowing developers to specify a path for skill discovery and installation. - Improved comments in the environment file to clarify the usage of `SKILLS_REGISTRY_URL` for both remote and local paths, enhancing the development experience. - Refactored `qjs_engine.rs` to prioritize the `SKILLS_LOCAL_DIR` for skill source directory resolution, improving local development workflows. - Added utility functions in `registry_ops.rs` to support local file path handling for skill registries, enhancing flexibility in skill management. These changes streamline the development process for skills by providing clearer configuration options and improving local development capabilities. * feat(tests): enhance skills directory discovery in test files - Updated `try_find_skills_dir` function across multiple test files to include support for the `SKILLS_LOCAL_DIR` environment variable, improving the flexibility of skills directory resolution. - Enhanced comments to clarify the order of directory search priorities, ensuring better understanding for developers. - Improved error handling and logging for cases where the specified directory does not exist, aiding in debugging and test reliability. These changes streamline the skills directory discovery process in tests, enhancing the overall development experience. * feat(tests): enhance skills directory discovery in test files - Updated `try_find_skills_dir` function to include support for the `SKILLS_LOCAL_DIR` environment variable, allowing for more flexible skills directory resolution. - Improved documentation to clarify the priority order for skills directory discovery. - Refactored multiple test files to utilize the updated skills directory discovery logic, enhancing consistency and maintainability across tests. These changes streamline the skills directory discovery process in tests, improving the overall testing framework. * refactor(tests): streamline memory client verification in Notion live tests - Updated the memory client verification process in `notion_live_with_real_data` to utilize `MemoryClient::new_local()` for improved clarity and consistency. - Enhanced comments to clarify the memory store check location and removed redundant error handling for workspace directory creation. - Simplified the error logging to focus on the memory client creation failure, improving readability and maintainability of the test code. These changes enhance the reliability of memory verification in the Notion live tests, ensuring a clearer understanding of the memory client initialization process. --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
|
2545ae374a |
refactor: extract accessibility middleware module (#184)
* feat(autocomplete): add target_role to EngineState for improved context validation - Introduced a new field `target_role` in `EngineState` to store the AXRole of the text element when suggestions are generated. - Updated the `AutocompleteEngine` to validate the focused element against the expected app and role before applying suggestions. - Enhanced the `apply_text_to_focused_field` function to include role validation, ensuring better accuracy in text insertion. - Improved the handling of suggestion context and error states during autocomplete operations. This update enhances the reliability of the autocomplete feature by ensuring that suggestions are applied only when the correct context is maintained. * fix(package): update dev:app script to include core staging step - Modified the `dev:app` script in `package.json` to run `yarn core:stage` before executing `tauri dev`, ensuring that the core sidecar is properly staged during development. - This change enhances the development workflow by automating the staging process, reducing manual steps for developers. This update improves the reliability of the development environment setup. * feat(autocomplete): implement core autocomplete engine and supporting modules - Introduced a new `AutocompleteEngine` struct to manage the state and operations of the autocomplete feature, including starting, stopping, and refreshing suggestions. - Added `EngineState` to track the current status, phase, and context of the autocomplete process. - Implemented helper functions for managing focus and overlay notifications, enhancing user interaction with suggestions. - Created utility functions for terminal context extraction and text sanitization, improving the accuracy of suggestions. - Developed a comprehensive set of types and structures to support autocomplete operations, including suggestion handling and status reporting. This update lays the foundation for a robust autocomplete feature, enhancing user experience through improved context awareness and interaction. * refactor(autocomplete): remove unused functions and improve clipboard handling - Deleted the `normalize_ax_value` and `parse_ax_number` functions as they were not utilized in the codebase, streamlining the autocomplete module. - Enhanced the `clipboard_save` function to improve readability by formatting the string conversion of clipboard output, ensuring better handling of empty or "missing value" cases. This update simplifies the code and improves the overall maintainability of the autocomplete functionality. * refactor(autocomplete): remove unused functions and improve clipboard handling - Deleted the `normalize_ax_value` and `parse_ax_number` functions as they were not utilized in the codebase, streamlining the autocomplete module. - Enhanced the `clipboard_save` function to improve readability by formatting the string conversion of clipboard output, ensuring better handling of empty or "missing value" cases. This update cleans up the code and optimizes the clipboard handling logic for the autocomplete feature. * feat(autocomplete): enhance focus handling and text insertion methods - Implemented a unified Swift helper for querying focused text elements, improving performance and reliability on macOS. - Added fallback mechanisms to use osascript for focus queries when the helper is unavailable, ensuring consistent functionality. - Refactored text insertion logic to prioritize the unified helper, with osascript and AXValue as fallback options, enhancing user experience during text application. - Cleaned up and organized focus-related functions, improving code readability and maintainability. This update significantly enhances the autocomplete feature's ability to interact with focused text elements, providing a more robust and responsive user experience. * feat(accessibility): introduce comprehensive accessibility module for macOS - Added a new `accessibility` module that centralizes focus queries, screen capture, key state detection, and permission management for macOS. - Implemented a unified Swift helper process to enhance performance and reliability in querying focused text elements and managing overlays. - Introduced various functionalities including screen capture, text insertion into focused fields, and permission detection for accessibility features. - Enhanced user experience by providing robust methods for interacting with accessibility APIs, ensuring consistent behavior across different contexts. This update significantly improves the accessibility capabilities of the application, providing a more responsive and user-friendly interface for macOS users. * feat(accessibility): introduce screen capture and focus query modules - Added a new `accessibility` module to centralize platform-specific accessibility functionalities, including screen capture and focus queries. - Implemented `capture.rs` for screen capture using platform-native tools, supporting both windowed and fullscreen modes. - Developed `focus.rs` to handle accessibility focus queries, utilizing a unified Swift helper for improved performance on macOS. - Introduced helper functions for managing overlays and permissions, enhancing user interaction and accessibility features. This update significantly enhances the application's accessibility capabilities, providing robust tools for screen capture and focus management. * refactor(accessibility): remove unused accessibility functions and streamline modules - Deleted unused functions from the accessibility module, including `focused_text_context`, `is_text_role`, `normalize_ax_value`, and `parse_ax_number`, to enhance code clarity and maintainability. - Updated module documentation to reflect the current structure and purpose, ensuring consistency across the accessibility and screen intelligence modules. This update simplifies the codebase and improves the overall organization of accessibility-related functionalities. * feat(image-processing): implement image compression and resizing for vision LLM - Added a new module `image_processing` to handle the compression and resizing of screenshots before sending them to the vision LLM. - Implemented the `compress_screenshot` function, which decodes PNG data-URIs, resizes images to fit within a specified maximum dimension, and re-encodes them as JPEGs. - Updated the `AccessibilityEngine` to utilize the new image processing functionality, ensuring that images sent for analysis are optimized for size and quality. - Introduced new dependencies in `Cargo.toml` for image handling and compression. This update enhances the efficiency of image processing in the application, reducing token usage and improving inference speed. * feat(tests): add end-to-end tests for screen intelligence vision pipeline - Introduced a new test file `screen_intelligence_vision_e2e.rs` to validate the complete flow of the screen intelligence vision pipeline. - Implemented tests that cover generating images, compressing and resizing them, simulating LLM responses, and persisting results to memory. - Utilized temporary directories and environment variable management to ensure test isolation and reliability. - Enhanced the testing framework by including helper functions for image creation and mock responses, improving the overall test coverage and robustness. This update significantly strengthens the testing capabilities of the screen intelligence module, ensuring that the entire pipeline functions correctly under various scenarios. * style: apply cargo fmt and import ordering fixes Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(accessibility): add non-macOS stub for validate_focused_target The function was gated with #[cfg(target_os = "macos")] but exported unconditionally from mod.rs, causing compilation failure on non-macOS. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(accessibility): enhance screen capture and error handling - Updated the screen capture functionality to include a timestamp helper in the documentation. - Improved error handling when reading resized screenshots, ensuring temporary files are removed on failure. - Added logging for raw errors returned by the helper in the focus context, providing better debugging information. - Refactored clipboard handling in the paste functionality to preserve multi-line text, enhancing usability. - Introduced a constant for terminal application names to simplify terminal detection logic. This update improves the robustness and clarity of the accessibility module, enhancing both screen capture and focus handling capabilities. --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
|
cf344facf9 |
feat(voice): dedicated voice assistance module for STT/TTS (#178)
* feat(voice): add dedicated voice assistance module for STT/TTS Extracts speech-to-text (whisper.cpp) and text-to-speech (piper) into a dedicated `src/openhuman/voice/` domain module with its own RPC namespace (`openhuman.voice_*`). Adds proactive availability checking via `voice_status` so the UI can show clear errors when binaries/models are missing instead of failing silently at transcription time. - New module: voice/types.rs, voice/ops.rs, voice/schemas.rs, voice/mod.rs - 4 RPC endpoints: voice_status, voice_transcribe, voice_transcribe_bytes, voice_tts - 21 unit tests + 1 integration test (json_rpc_e2e) - Frontend updated to use voice_* endpoints with status check on mode switch Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: fix cargo fmt in voice/ops.rs Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test(e2e): add voice mode integration spec Tests switching to voice input mode, verifying status check fires, recording button renders, and switching back to text mode restores text input. Also checks reply mode toggle visibility. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: remove unused waitForText import in voice-mode e2e spec Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(voice): in-process whisper engine and LLM post-processing - Add whisper-rs (0.16) for in-process whisper.cpp inference, eliminating cold-start latency from subprocess-per-call (~1-3s) to warm inference (~50ms). Model is loaded once during bootstrap and reused across calls. Falls back to whisper-cli subprocess if in-process loading fails. - Add LLM post-processing layer that passes raw transcription through Ollama to fix grammar, punctuation, and filler words. Accepts optional conversation context to disambiguate names and technical terms. Gracefully degrades to raw whisper output if Ollama is unavailable. - Update voice RPC endpoints with new optional params (context, skip_cleanup) and return both cleaned text and raw_text. - Update frontend to pass conversation history as context for voice transcription cleanup, and update TypeScript interfaces to match. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: apply cargo fmt formatting fixes Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(build): make whisper-rs optional behind `whisper` feature flag The whisper-rs crate requires cmake to compile whisper.cpp from source, which is not available in the CI environment. Move it behind an optional cargo feature so CI builds succeed without cmake. The whisper_engine module now compiles as a no-op stub when the feature is disabled, returning "whisper feature not compiled in" errors. Desktop builds can opt in with `--features whisper`. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: cargo fmt whisper_engine.rs Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(ci): make whisper-rs mandatory and install cmake in CI Revert whisper-rs from optional to mandatory dependency. Add cmake installation to all CI workflows (build, typecheck, test, release) and the CI Docker image so whisper-rs can compile whisper.cpp from source. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: cargo fmt whisper_engine.rs Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: address code review findings across voice module - whisper_engine: validate WAV sample rate (must be 16kHz) and channel count (1 or 2) before feeding audio to whisper - speech: offload load_engine and transcribe_in_process to tokio::task::spawn_blocking to avoid blocking the Tokio runtime - ops: use RAII guard for WHISPER_BIN env var in test to prevent races and ensure restore on panic; log temp file cleanup failures instead of silently ignoring; sanitize paths in debug logs to basenames only - postprocess: add test for disabled cleanup config returning raw text - voice-mode.spec: assert failure when neither voice CTA nor unavailable message appears; make reply mode test runnable in isolation with auth/nav setup Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: apply cargo fmt Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|
YellowSnnowmannandGitHub
|
64eb513071 |
feat(billing, team): add billing and team management RPC functionality (#159)
* feat(billing, team): add billing and team management RPC functionality - Introduced billing module with methods for fetching current plans, purchasing plans, creating portal sessions, and topping up credits. - Added team management module with methods for listing team members, creating invites, listing invites, removing members, and changing member roles. - Updated core registry to include new billing and team controllers and schemas, enhancing the overall functionality of the application. - Implemented comprehensive tests for billing and team RPC methods to ensure reliability and correctness. These additions improve the application's capabilities in managing billing and team functionalities, providing a more robust user experience. * refactor(billing, team): improve code readability and structure * fix(billing, team): enhance error handling and response structure - Improved error handling in to provide clearer error messages when reading response bodies. - Updated validation in to ensure is a finite number greater than zero. - Refined output schemas for billing and team functions to include more descriptive fields, enhancing API clarity. - Introduced a new function to standardize URL path construction, improving code maintainability. - Added tests to verify the correctness of new output structures and API path building. These changes enhance the robustness and usability of the billing and team management functionalities. * feat(billing, team): add gateway normalization and route redaction functionality - Introduced function to standardize payment gateway inputs, ensuring only valid options (stripe, coinbase) are accepted, with defaults and error handling. - Enhanced function to utilize the new gateway normalization logic, improving input validation. - Added function to obscure sensitive identifiers in API route paths, enhancing security in logging. - Implemented unit tests for both and to ensure correctness and reliability of the new features. These changes improve the robustness of billing operations and enhance security in route handling. |
||
|
|
00c7b01280 |
fix(skills): debug infrastructure + disconnect credential cleanup (#154)
* feat(debug): add skills debug script and E2E tests - Introduced a new script `debug-skill.sh` for running end-to-end tests on skills, allowing users to easily test specific skills with customizable parameters. - Added comprehensive integration tests in `skills_debug_e2e.rs` to validate the full lifecycle of skills, including discovery, starting, tool listing, and execution. - Enhanced logging and error handling in the tests to improve observability and debugging capabilities. These additions facilitate better testing and debugging of skills, improving the overall development workflow. * feat(tests): add end-to-end tests for Skills RPC over HTTP JSON-RPC - Introduced a new test file `skills_rpc_e2e.rs` to validate the full stack of skill operations via HTTP JSON-RPC. - Implemented comprehensive tests covering skill discovery, starting, tool listing, and execution, ensuring robust functionality. - Enhanced logging for better observability during test execution, facilitating easier debugging and validation of skill interactions. These tests improve the reliability and maintainability of the skills framework by ensuring all critical operations are thoroughly validated. * refactor(tests): update RPC method names in end-to-end tests for skills - Changed RPC method names in `skills_rpc_e2e.rs` to use the new `openhuman` prefix, reflecting the updated API structure. - Updated corresponding test assertions to ensure consistency with the new method names. - Enhanced logging messages to align with the new method naming conventions, improving clarity during test execution. These changes ensure that the end-to-end tests accurately reflect the current API and improve maintainability. * feat(debug): add live debugging script and corresponding tests for Notion skill - Introduced `debug-notion-live.sh` script to facilitate debugging of the Notion skill with a live backend, including health checks and OAuth proxy testing. - Added `skills_notion_live.rs` test file to validate the Notion skill's functionality using real data and backend interactions. - Enhanced logging and error handling in both the script and tests to improve observability and debugging capabilities. These additions streamline the debugging process and ensure the Notion skill operates correctly with live data. * feat(env): enhance environment configuration for debugging scripts - Updated `.env.example` to include a new `JWT_TOKEN` variable for session management in debugging scripts. - Modified `debug-notion-live.sh` and `debug-skill.sh` scripts to load environment variables from `.env`, improving flexibility and usability. - Enhanced error handling in the scripts to ensure required variables are set, providing clearer feedback during execution. These changes streamline the debugging process for skills by ensuring necessary configurations are easily managed and accessible. * feat(tests): add disconnect flow test for skills - Introduced a new end-to-end test `skill_disconnect_flow` to validate the disconnect process for skills, mirroring the expected frontend behavior. - The test covers the stopping of a skill, handling OAuth credentials, and verifying cleanup after a disconnect. - Enhanced logging throughout the test to improve observability and debugging capabilities. These additions ensure that the disconnect flow is properly validated, improving the reliability of skill interactions. * fix(skills): revoke OAuth credentials on skill disconnect disconnectSkill() was only stopping the skill and resetting setup_complete, leaving oauth_credential.json on disk. On restart the stale credential would be restored, causing confusing auth state. Now sends oauth/revoked RPC before stopping so the event loop deletes the credential file and clears memory. Also adds revokeOAuth() and disableSkill() to the skills RPC API layer. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: apply cargo fmt to skill debug tests Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * refactor(tests): improve skills directory discovery and error handling - Renamed `find_skills_dir` to `try_find_skills_dir`, returning an `Option<PathBuf>` to handle cases where the skills directory is not found. - Introduced a macro `require_skills_dir!` to simplify the usage of skills directory discovery in tests, providing clearer error messages when the directory is unavailable. - Updated multiple test functions to utilize the new macro, enhancing readability and maintainability of the test code. These changes improve the robustness of the skills directory discovery process and streamline the test setup. * refactor(tests): enhance skills directory discovery with improved error handling - Renamed `find_skills_dir` to `try_find_skills_dir`, returning an `Option<PathBuf>` to better handle cases where the skills directory is not found. - Introduced a new macro `require_skills_dir!` to streamline the usage of skills directory discovery in tests, providing clearer error messages when the directory is unavailable. - Updated test functions to utilize the new macro, improving code readability and maintainability. These changes enhance the robustness of the skills directory discovery process and simplify test setup. * fix(tests): skip skill tests gracefully when skills dir unavailable Tests that require the openhuman-skills repo now return early with a SKIPPED message instead of panicking when the directory is not found. Fixes CI failures where the skills repo is not checked out. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(skills): harden disconnect flow, test assertions, and secret redaction - disconnectSkill: read stored credentialId from snapshot and pass it to oauth/revoked for correct memory bucket cleanup; add host-side fallback to delete oauth_credential.json when the runtime is already stopped. - revokeOAuth: make integrationId required (no more "default" fabrication); add removePersistedOAuthCredential helper for host-side cleanup. - skills_debug_e2e: hard-assert oauth_credential.json is deleted after oauth/revoked instead of soft logging. - skills_notion_live: gate behind RUN_LIVE_NOTION=1; require all env vars (BACKEND_URL, JWT_TOKEN, CREDENTIAL_ID, SKILLS_DATA_DIR); redact JWT and credential file contents from logs. - skills_rpc_e2e: check_result renamed to assert_rpc_ok and now panics on JSON-RPC errors so protocol regressions fail fast. - debug-notion-live.sh: capture cargo exit code separately from grep/head to avoid spurious failures under set -euo pipefail. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * style: apply cargo fmt to skills_notion_live.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> |