- test_deep_research_prompt.py (8 tests): date injection, time, day of week,
dynamic generation, response types, tool descriptions, /no_think, Jarvis name
- test_slack_messaging.py (7 tests): connect with/without tokens, error state,
disconnect, handler registration, send without token
- test_connector_health.py (44 tests): all 11 connectors instantiate, have
required methods, report not-connected without creds, have metadata.
Plus KnowledgeStore data presence checks.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add exchange_google_token() and run_oauth_flow() to oauth.py for the
full authorization code exchange. Update gdrive, gcalendar, and
gcontacts connectors to trigger the browser-based OAuth flow when a
client_id:client_secret pair is provided, prefer access_token over raw
token, and require an actual access_token for is_connected(). auth_url()
now returns the Cloud Console credentials page when no client_id is
stored.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- personal_deep_research.toml: add schedule_value="" for template test compat
- test_deep_research_tools_wiring: skip when fastapi not installed in CI
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add deep_research_agent parameter to ChannelBridge.__init__ and update
_handle_chat to try DeepResearchAgent first, falling back to system.ask()
when no research agent is configured.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Resolve tool names from config["tools"] into actual tool instances
using ToolRegistry, inject runtime deps, and pass them to the agent
constructor instead of hardcoded tools=[].
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds `codex/` prefixed model support using the OpenAI Responses API —
the same protocol used by zeroclaw and other Codex-compatible tools.
Live-tested against gpt-5-mini-2025-08-07 with:
- Generate (non-streaming): confirmed working
- System prompt → instructions mapping: confirmed working
- SSE streaming: confirmed working (9 chunks)
- End-to-end via `jarvis ask`: confirmed working
Implementation:
- Default endpoint: api.openai.com/v1/responses (standard API key)
- Override via OPENAI_CODEX_BASE_URL for ChatGPT OAuth tokens
(e.g. chatgpt.com/backend-api/codex)
- Auth via OPENAI_CODEX_API_KEY env var
- Responses API format: input array, instructions field, output_text extraction
- Handles reasoning+message output blocks correctly
- SSE streaming parses response.output_text.delta events
Models: codex/gpt-4o, codex/gpt-4o-mini, codex/o3-mini,
codex/gpt-5-mini, codex/gpt-5-mini-2025-08-07
Usage:
export OPENAI_CODEX_API_KEY="your-api-key-or-oauth-token"
jarvis ask "Hello" --model codex/gpt-5-mini-2025-08-07
Closes#134
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Incorporates the useful new features from PR #135 (by @gridworks) on top
of the existing PrivacyScanner implementation:
- Add DNS configuration check (macOS, via scutil --dns)
- Add --json flag to `jarvis scan` for machine-readable output
- Add --no-scan flag to `jarvis init` to skip the post-init audit
- Expand remote-access process list (ngrok, tailscaled, cloudflared, ZeroTier)
- Upgrade `jarvis scan` output from plain text to Rich table
- Add GET /v1/security/scan API endpoint
- Add tests for all new features (30 tests, all passing)
Closes#133
Co-Authored-By: gridworks <5502067+gridworks@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Auto-detects local sources (Apple Notes, iMessage, Obsidian), ingests
them into ~/.openjarvis/knowledge.db via IngestionPipeline + SyncEngine,
and launches an interactive Deep Research chat session with Qwen3.5 via
Ollama.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implements SyncScheduler that runs a daemon background thread to call
SyncEngine.sync() on all registered connectors at a configurable interval.
Provides run_once() as a synchronous helper for testing. Disconnected
connectors are skipped each cycle; errors are logged without stopping the
loop. 4 tests covering run_once, disconnected skip, start/stop, and
per-connector chunk counts.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implements WhatsAppConnector that reads exported .txt chat files from a
directory, parses the standard WhatsApp export line format with regex,
and yields one Document per chat file with participants, timestamps, and
since filtering. Registers under "whatsapp" in ConnectorRegistry with
MCP tools for whatsapp_search_messages and whatsapp_get_chat. 10 tests
covering parsing, multi-file, since filtering, is_connected, and registry.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Remove the ARG002 noqa suppression and translate the `since` datetime
parameter into a Gmail `after:<epoch>` query string passed to
`_gmail_api_list_messages`, so incremental syncs only fetch messages
newer than the requested cutoff.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add optional `attachment_store` parameter to IngestionPipeline. When
provided, attachments are stored as blobs in AttachmentStore and their
text (plain/markdown/csv via decode, PDF via pdfplumber) is chunked and
indexed in the KnowledgeStore with attachment provenance metadata.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add disk-persistent storage for ColBERT token-level embeddings so the
reranker can reuse pre-computed embeddings across queries instead of
re-encoding every document on every search.
- EmbeddingStore: individual .pt files per chunk with SQLite index for
O(1) lookup, graceful degradation when torch is not installed
- ColBERTReranker: checks EmbeddingStore for cached embeddings before
falling back to docFromText(), stores newly computed embeddings
- KnowledgeStore: ensures chunk_id is always present in retrieval
metadata (both at store time and as a backfill in retrieve)
- 18 tests covering round-trip persistence, deletion, torch-absent
degradation, and reranker cache-hit/miss behavior
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
_apply_toml_section only normalized TOML arrays to comma-separated strings
for real dataclass fields, but backward-compat property setters like
reward_weights also expect string input. When a user's config.toml had
an array value for a property-backed attribute, the raw list was passed
to the setter which called .split(",") on it, causing:
'list' object has no attribute 'split'
This also hardens serve.py against the same issue when reading
config.agent.tools.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds a new POST /{connector_id}/sync endpoint alongside the existing GET
sync-status endpoint. The new endpoint validates the connector is registered
and connected, then runs SyncEngine.sync() and returns chunks_indexed.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Implements AttachmentStore that writes blobs to {base_dir}/{sha[:2]}/{sha}
with a SQLite metadata index tracking filename, MIME type, size, and the
accumulated list of source_doc_ids for each content-identical blob.
Includes 7 unit tests covering SHA-256 return, file path layout,
idempotent dedup, multi-source tracking, metadata retrieval, content
round-trip, and missing-blob None return.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Merge main into fix/ssrf-check, keeping both the auto-recover
logic for error-state agents and the async streaming support
for the send_message endpoint.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Parse the last_sync checkpoint timestamp into a datetime and pass it as
the `since` argument to connector.sync(), enabling subsequent syncs to
fetch only new items rather than a full re-fetch.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The model catalog listed non-existent Qwen3.5 sizes (3B, 8B, 14B) and
pointed to MLX community repos that don't exist, causing `jarvis init`
to recommend models that cannot be downloaded on Apple Silicon.
Replace with the actual Qwen3.5 model family sizes (0.8B, 2B, 9B, 27B)
and verified mlx-community repo URLs from HuggingFace.
Fixes#129
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Implements create_connectors_router() with GET /connectors, GET
/connectors/{id}, POST /connectors/{id}/connect, POST
/connectors/{id}/disconnect, and GET /connectors/{id}/sync endpoints.
Includes 6 passing tests covering list, detail, 404, connect, disconnect,
and sync status.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(evals): PinchBench harness fixes — scores from 26% to 84%
Multiple infrastructure bugs prevented PinchBench from producing
accurate scores. This commit fixes the eval harness so model scores
match the official leaderboard (Qwen3.5-397B: 26% → 84%, GPT-5.4:
5% → 58%).
Key fixes:
- EvalRunner: wrap generation in PinchBenchTaskEnv context so workspace
files persist through grading (was deleting before scorer ran)
- EvalRunner: detect task_env datasets and force sequential processing
(CWD changes aren't thread-safe)
- EvalRunner: fix episode_mode auto-detection to check for real
iter_episodes() override instead of hasattr() (always True)
- Scorer: use "params" field in transcripts to match PinchBench grade()
functions (was "arguments")
- Scorer: add None guard in _trace_to_transcript for tool_calls
- Scorer: capture final assistant text response in transcript so
text-only tasks (like sanity check) can be graded
- Scorer: add _tool_results_to_transcript() helper for EvalRunner path
- native_openhands: add native function-calling support (tools=
parameter) with text-based fallback, matching monitor_operative
- Tools: add Python fallbacks for file_read, file_write, shell_exec,
calculator, think, http_request when openjarvis_rust unavailable
- Security: add Python fallback for is_sensitive_file()
- Config: add "pinchbench" to KNOWN_BENCHMARKS
- Add PinchBench eval configs for Qwen3.5-397B and GPT-5.4
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(evals): fix hybrid grading crash when grading_weights is None
The 4 tasks with grading_type=hybrid (task_10, task_13, task_16_market,
task_22) crashed because grading_weights was explicitly None in task
metadata. dict.get("key", default) returns None (not the default) when
the key exists with value None. Use `or` to coalesce None to defaults.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(evals): handle MagicMock datasets in runner type checks
The iter_episodes and create_task_env type identity checks fail with
AttributeError when the dataset is a MagicMock (used in tracker tests).
Wrap in try/except to default to False for non-DatasetProvider objects.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adds tests/agents/test_channel_agent_integration.py covering the full
stack from KnowledgeStore + IngestionPipeline through TwoStageRetriever,
KnowledgeSearchTool, and DeepResearchAgent into ChannelAgent/FakeChannel:
- test_quick_query_inline_response: asserts inline reply with meeting info
and no openjarvis:// escalation link
- test_deep_query_escalation_link: asserts openjarvis:// link is present
when engine issues a tool call and returns a long report
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
