`SystemPromptBuilder` is fully implemented and tested in
`openjarvis.prompt.builder`, and `BaseAgent.__init__` accepts a
`prompt_builder` kwarg. But no production code path ever instantiates
the builder, so the persona-files feature documented in
`MemoryFilesConfig` (SOUL.md / MEMORY.md / USER.md) had no effect.
Users could write a fully-customized `~/.openjarvis/SOUL.md` and the
file was never read.
This PR wires it up in `_run_agent` (called by `jarvis ask --agent
<name>` and the new fallback from #294):
```python
if "prompt_builder" in inspect.signature(agent_cls.__init__).parameters:
agent_kwargs["prompt_builder"] = SystemPromptBuilder(
agent_template=config.agent.default_system_prompt or "",
memory_files_config=config.memory_files,
system_prompt_config=config.system_prompt,
)
```
The `inspect` guard means agents that override `__init__` without
forwarding `prompt_builder` (e.g. OrchestratorAgent, which has its
own tool-aware system prompt) opt out automatically and keep
working unchanged. SimpleAgent and any future agent that inherits
`BaseAgent.__init__` directly picks up the persona files.
Also fixes a latent bug in `SystemPromptBuilder._load_file`: it
called `path.read_text()` with no encoding, which on Windows falls
back to the system code page (cp950 / cp932 / cp949) and raises
`UnicodeDecodeError` on any non-ASCII persona content. Pin to UTF-8.
## Tests
- Add `test_soul_md_content_reaches_engine_in_simple_agent` — writes
sentinel SOUL.md / MEMORY.md / USER.md to tmp_path, runs the
command, and asserts each sentinel appears in the SYSTEM message
passed to engine.generate.
- Add `test_orchestrator_keeps_its_own_system_prompt` — exercises
the `inspect`-based opt-out so OrchestratorAgent doesn't crash
on the unexpected kwarg.
Run: `pytest tests/cli/test_ask_agent.py tests/cli/test_ask_router.py
tests/cli/test_ask_e2e.py tests/agents/ tests/prompt/`
The 6 remaining failures (test_base_agent, test_loop_guard,
test_manager, test_native_openhands) are pre-existing on
origin/main and unrelated to this change.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Follow-up on @TX-Huang's PR #294. The default-agent fallback now
routes `jarvis ask "..."` (no --agent) through `config.agent.default_agent`,
which dataclass-defaults to `"simple"`. The autouse `_clean_registries`
fixture in tests/conftest.py clears AgentRegistry between tests, so
the fallback then fails with `Unknown agent: simple` and every
CLI-driven test_energy_wiring test exits with code 1.
These tests exercise engine-level instrumentation, not agent dispatch
— ``test_engine_wrapped_with_instrumented``, the energy-monitor
lifecycle tests, and the end-to-end pipeline tests all care that the
engine gets wrapped and telemetry lands in SQLite, regardless of
whether the call goes through an agent. Set ``cfg.agent.default_agent
= ""`` in ``_energy_config`` to keep these tests on the direct-engine
path they were originally designed for. The dedicated
``test_agent_mode_uses_instrumented_engine`` (which explicitly passes
``--agent``) is unaffected.
Same pattern PR #294 already uses in tests/cli/test_ask_router.py
for the two MagicMock-config tests.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`jarvis ask "..."` (no `--agent` flag) routed straight to
`engine.generate()` regardless of `agent.default_agent` in the user's
config. As a result the persona stack — `agent.default_system_prompt`,
SOUL.md, MEMORY.md, USER.md — was silently bypassed for the most
common command.
Behavior now:
- `--agent X` → use agent X (unchanged)
- `--agent ""` (empty) → explicit opt-out, direct-to-engine mode
- (omitted) → fall back to `config.agent.default_agent`,
which dataclass-defaults to `"simple"`,
so persona settings finally take effect
Tests:
- Rename `test_no_agent_uses_direct_mode` to
`test_no_agent_flag_falls_back_to_config_default_agent` and update
its docstring to document the new behavior.
- Add `test_explicit_empty_agent_opts_out_of_agent_mode`.
- Add `test_no_agent_with_blank_config_default_uses_direct_mode` to
cover the case where the user clears `default_agent`.
- Update `_patch_engine` (test_ask_router) and `_patch_ask`
(test_ask_e2e) to re-register `SimpleAgent` after the autouse
`_clean_registries` conftest fixture, since the agent path now
runs in tests that previously short-circuited to direct mode.
- Add explicit `cfg.agent.default_agent = ""` to two
`test_ask_router` tests that mock load_config with a MagicMock
(so `cfg.agent.default_agent` doesn't auto-create as a truthy mock).
Note: `tests/cli/test_ask_context.py` has 2 unrelated pre-existing
failures on origin/main (memory backend returns None on Windows);
those are out of scope for this PR.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
On Windows the default Python stdout encoding follows the system
ANSI code page (cp950 for zh-TW, cp932 for ja, cp949 for ko).
`click.echo()` then raises `UnicodeEncodeError` whenever a CJK
character lands in CLI output — `jarvis ask` returning Chinese
crashes with `'cp950' codec can't encode character '义'`.
Reconfigure `sys.stdout` and `sys.stderr` to UTF-8 with
`errors='replace'` at the `main()` entry point. Scoped to
`win32` so other platforms are untouched. Two unit tests verify
the reconfigure happens on Windows and doesn't on Linux.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`_total_ram_gb()` had branches for Darwin (sysctl) and Linux
(/proc/meminfo) but no Windows path, so `jarvis init` reported
"0.0 GB RAM" on every Windows host. The downstream
`recommend_model()` then fell back to VRAM-only sizing, often
selecting a smaller tier than the system can actually run.
Add a Windows branch that calls `GlobalMemoryStatusEx` via
ctypes — no new dependency. Add a platform-skip-aware test for
each OS branch.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Follow-up on @Dilligaf371's PR #339 fix. Adds a regression test that
spawns a subprocess which consumes stdin without ever writing to
stdout, then issues `send_notification` from a worker thread. If the
override is missing, the thread blocks forever on `proc.stdout.readline()`
and the 2-second join timeout fires.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix: close KnowledgeStore connections in connectors_router endpoints
KnowledgeStore opens a persistent SQLite connection in __init__ but was
never closed at the three instantiation sites in connectors_router.py,
leaking one file descriptor (plus its WAL handle) per call. The worst
offender is _connector_summary(), which is invoked per-connector on
every GET /connectors poll from the frontend — after ~100 polls the
backend hits the default macOS per-process FD limit (256) and asyncio's
accept() starts failing with OSError: [Errno 24] Too many open files.
Add __enter__/__exit__ to KnowledgeStore (close() already existed) and
wrap all three instantiation sites in `with` blocks so the connection
is released deterministically when the scope exits.
- connectors/store.py: add context manager protocol
- server/connectors_router.py: use `with KnowledgeStore() as store:`
in _connector_summary, _ingest, and _run_sync
* test: cover KnowledgeStore context manager + connectors_router close leak
- test_store.py: add two tests for the new __enter__/__exit__ protocol
verifying the connection closes on normal exit and on exceptions.
- test_connectors_router.py: add a regression test that monkeypatches
KnowledgeStore.close to count invocations and asserts every store
opened by GET /v1/connectors is paired with a close.
Also fix a pre-existing bug in the test_connectors_router fixture: the
router is created with prefix="/v1/connectors" internally (line 92 of
connectors_router.py), and the fixture was wrapping it again with
prefix="/v1", producing "/v1/v1/connectors". All 6 existing router
tests were failing with 404 before this fix. 5 of them now pass; the
remaining failure (test_trigger_sync) is an unrelated KeyError on a
missing response field and is out of scope for this PR.
* test: drop connectors_router regression test — skipped in CI anyway
The regression test added in the previous commit relies on FastAPI
being importable, but CI's dev-extra install does not include fastapi
(it lives in the `server` optional group). All tests in
test_connectors_router.py silently skip on CI with "fastapi not
installed", so the regression test would never actually execute there.
Revert test_connectors_router.py to the upstream main version. The
fixture bug I fixed (double prefix) and the connection-leak regression
test both deserve a separate PR scoped to test infrastructure — that
PR should either add fastapi to dev deps, split server tests into
their own CI job, or both.
The KnowledgeStore context manager tests in test_store.py are kept
because they have no fastapi dependency and will run in CI.
* feat(mining): add Pearl model conversion workflow
* test(mining): tolerate missing Docker device request type
* docs(mining): record Gemma and Qwen conversion evidence
* docs(mining): record Qwen local validation evidence
---------
Co-authored-by: krypticmouse <herumbshandilya123@gmail.com>
The desktop app's chat-completions stream relies on a raw browser
fetch from the Tauri webview to the FastAPI backend, so it is
subject to CORS. The default allowlist only contained
`tauri://localhost`, which is the production webview origin on
macOS, Linux, and iOS. On Windows and Android, Tauri 2 serves the
app from `http://tauri.localhost` (or `https://tauri.localhost`
when `windows.useHttpsScheme` is enabled), so the preflight for
`POST /v1/chat/completions` was rejected and the streaming fetch
threw `TypeError: Failed to fetch` before any byte was read.
Symptom users reported: in the Logs tab the request appears to
succeed up to "Request sent", followed immediately by
"Stream error: Failed to fetch" and "Response: 22 chars" -- which
is exactly the length of the synthesized fallback string
`Error: Failed to fetch` written by InputArea.tsx when streamChat
throws.
Add `http://tauri.localhost` and `https://tauri.localhost` to both
default origin lists (`ServerConfig.cors_origins` and the
`create_app` fallback), and add a regression test that drives a
real preflight against `/v1/chat/completions` for each of the
three Tauri origin schemes.
Browser model loading kept working because it is routed through
the Rust `tauriInvoke('fetch_models')` command, which is a
server-to-server HTTP call not subject to browser CORS -- only
streaming chat goes through the webview's fetch.
* feat: add Apple Contacts connector (macOS AddressBook)
Reads directly from ~/Library/Application Support/AddressBook/AddressBook-v22.abcddb
in read-only mode. Extracts names, phone numbers, emails, postal addresses, URLs,
social profiles, and notes for each contact. Requires Full Disk Access like
iMessage and Apple Notes connectors.
- New connector: src/openjarvis/connectors/apple_contacts.py
- Registered in connectors/__init__.py
- Added frontend catalog entry (PIM category) and icon mapping
- MCP tools: contacts_search, contacts_get_contact
* test: add comprehensive tests for Apple Contacts connector
15 tests covering: is_connected (exists/missing), sync yields all real
contacts (skips system rows), extracts all field types (phone, email,
address, URL, social, notes), cleans Apple label markup, org-only
contacts, minimal contacts, since filter, sync_status tracking,
structured metadata, disconnect, mcp_tools, registry, empty DB,
missing DB. Uses fake SQLite database — no real Contacts DB needed.
* fix: scan iCloud/Exchange source databases for all contacts
The main AddressBook database only contains locally-created contacts.
Synced contacts (iCloud, Exchange, etc.) live under
Sources/<UUID>/AddressBook-v22.abcddb. Now scans all source databases
and deduplicates by ZUNIQUEID across sources.
Adds tests for multi-source scanning and cross-source deduplication.
Update all human-readable strings (docstrings, comments, descriptions,
log messages, TOML config descriptions) to correctly say
"DeepResearchBench" instead of "LiveResearchBench" for the
deep_research_bench benchmark. Class names and file paths are
unchanged for backward compatibility.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- openjarvis.__version__ now comes from importlib.metadata.version("openjarvis")
instead of a hardcoded string, so it stays in sync with pyproject.toml on every
release. Tests assert against openjarvis.__version__ rather than a literal.
- Bump actions/checkout@v4 → @v6 and astral-sh/setup-uv@v4 → @v8 across every
workflow ahead of the 2026-06-02 Node.js 20 deprecation on GitHub Actions runners.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Qwen3.5 MoE models provide better quality per GB of memory since only
a fraction of parameters are active per token. Updates the tier table:
≤8 GB → qwen3.5:2b
8-16GB → qwen3.5:4b
16-32GB → qwen3.5:9b
32GB+ → qwen3.5:27b
Closes#132 — jarvis init now recommends a Qwen3 dense model based on
available memory using an explicit tier table:
≤8 GB → qwen3:1.7b (~1.1 GB)
8-16GB → qwen3:4b (~2.5 GB)
16-32GB → qwen3:8b (~5.2 GB)
32GB+ → qwen3:14b (~9.3 GB)
Adds qwen3:0.6b, 1.7b, 4b, 14b, 30b to the model catalog. Falls back
to scanning all compatible models if the tiered pick doesn't support
the selected engine. Shows the user why the model was chosen and how
to download later if declined.
Closes#164 — Qwen and other models with baked-in corporate identities
would claim to be cloud services when running locally. Adds a
configurable default_system_prompt to AgentConfig that is injected as a
fallback when no other system prompt is provided. The default tells the
model it is running locally through OpenJarvis. Users can override or
clear it via config.toml.
Tests were storing digests with local time but get_today() filters
by UTC date, causing failures when local date != UTC date.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(evals): add tool_choice=auto + fix traces thread safety
Two fixes for eval accuracy and stability:
1. TauBench agent: add tool_choice="auto" to match tau2's native
LLMAgent behavior. Without this, Qwen and GPT-5.4 score 10-14pp
below leaderboard because the models don't receive explicit
tool-calling guidance.
2. SystemBuilder: apply self._traces flag to config.traces.enabled.
Previously builder.traces(False) was a no-op — traces stayed
enabled, creating SQLite connections in the main thread that
crashed when accessed from ThreadPoolExecutor worker threads
in GAIA evals ("SQLite objects created in a thread can only be
used in that same thread").
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: enrich inference events with model response content and add Trace.messages
Add content, tool_calls, and finish_reason fields to INFERENCE_END events
published by InstrumentedEngine. For non-instrumented engines, BaseAgent._generate()
now publishes INFERENCE_START/END events with the same rich data. Add _message_to_dict
helper and messages field to Trace dataclass for full conversation capture.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: enhance TraceCollector with rich content, tool details, and messages
Capture model response content, tool_calls, and finish_reason in GENERATE
steps; store tool arguments and result text in TOOL_CALL steps; extract
conversation messages from AgentResult.metadata into Trace.messages; and
implement the last_trace property. Also adds a messages column to the
TraceStore schema so messages survive the SQLite round-trip.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: agents store conversation messages in AgentResult.metadata
Both NativeReActAgent and MonitorOperativeAgent now serialize their
internal messages list via _message_to_dict and include it in the
returned AgentResult.metadata under the "messages" key. This enables
TraceCollector to capture full conversation traces.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: wire TraceCollector into system._run_agent and JarvisAgentBackend
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: persist rich trace data in eval trace JSONL files
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add TerminalBench config for Qwen 3.5-122B
* fix: add SQLite migration for traces.messages column on existing databases
* fix: check trace_store instead of shared config for trace enablement
* feat(evals): add ToolCall-15, LiveCodeBench, LiveResearchBench + telemetry
Three new benchmark integrations and full telemetry wiring for the
NeurIPS 2026 IPW/IPJ experiments.
## New Benchmarks
### ToolCall-15
15-scenario tool calling accuracy benchmark across 5 categories.
All scenarios defined inline with deterministic scoring (0/1/2 per
scenario). Fast to run (~5min/model) — ideal for optimization loops.
### LiveCodeBench
Competitive programming from LeetCode/AtCoder/CodeForces via
HuggingFace dataset. Sandboxed code execution with per-test
timeouts. Single-turn generation via jarvis-direct backend.
### LiveResearchBench
100 expert-curated deep research tasks. LLM-as-judge scoring
across 4 dimensions (comprehensiveness, insight, instruction
following, readability). Uses web_search tool for live research.
## Telemetry Wiring
- FLOPs estimation: 2 * active_params * total_tokens (MoE-aware)
- Energy/power capture flows from InstrumentedEngine through
backends to EvalResult and RunSummary
- New telemetry_summary section in output JSON with IPW/IPJ
- JarvisDirectBackend now propagates gpu_metrics flag
- TauBench forwards telemetry flags to SystemBuilder
## Experiment Plan
Added docs/experiments/neurips-2026-plan.md tracking the full
experiment matrix: 9 models x 7 benchmarks across NVIDIA, AMD,
and Apple hardware stacks.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Jon Saad-Falcon <jonsaadfalcon@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
