`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>
The base MCPTransport.send_notification falls back to self.send() which
writes a request AND reads a response. For stdio MCP servers this hangs
forever because notifications (per JSON-RPC 2.0 spec) have no response.
This affected every stdio MCP server attached to OpenJarvis: after
MCPClient.initialize() sent its `initialize` request and received the
server capabilities, it sent the spec-required `notifications/initialized`
notification, which then blocked indefinitely on proc.stdout.readline().
StreamableHTTPTransport already overrides send_notification correctly
(transport.py:213). This adds the symmetric fix for StdioTransport so
stdio MCP servers can complete the handshake and be discovered.
Reproduced with the CyberStrikeAI cmd/mcp-stdio server (78 tools): without
the fix, `_discover_external_mcp` hangs forever in `MCPClient.initialize`.
With the fix, all 78 tools are discovered cleanly.
Follow-up on @tomaioo's signature-verification panic fix in PR #235.
1. Clippy on Rust 1.95+ flags `len() % 2 != 0` with the
`manual_is_multiple_of` lint, which was failing the `rust` CI job
on PR #235 and blocking merge. Switch to `is_multiple_of(2)`.
2. Add an explicit `is_ascii()` guard before slicing. With only the
length check, a non-ASCII input (e.g. `"é"` — 2 bytes but 1 char)
would survive the length check before `from_str_radix` caught it.
The explicit guard makes the rejection intent clear and avoids
relying on the post-slice error path.
3. Extract the hex-parsing into a private `parse_public_key_hex`
helper. PyO3-bound `#[pymethods]` are awkward to unit-test from
Rust (need a Python interpreter via `prepare_freethreaded_python`);
a plain function is testable with no GIL boilerplate.
4. Add 5 unit tests covering the security boundary:
- empty input -> Some(empty vec)
- valid hex decodes to the right bytes
- odd-length rejected without panic (the original bug)
- non-hex chars rejected (previously silently filtered)
- multi-byte UTF-8 rejected without panic
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`verify_signature` slices `public_key_hex[i..i + 2]` without validating that the input length is even. An odd-length or otherwise malformed string can trigger an out-of-bounds panic, which may crash the process (or at minimum terminate the request path), creating a denial-of-service vector if this method is reachable from untrusted input.
Signed-off-by: tomaioo <203048277+tomaioo@users.noreply.github.com>
Tauri's build script enforces strict SemVer
(`MAJOR.MINOR.PATCH[-pre][+build]`) on `tauri.conf.json > version`, but
the autotag scheme introduced in #358 emits PEP 440 dev releases like
`1.0.2.dev661` — PEP 440 separates dev with `.`, SemVer requires `-`.
First post-#358 desktop run failed with:
tauri.conf.json > version must be a semver string
PyPI requires PEP 440; Tauri requires SemVer. They genuinely don't
agree on `.devN`. Translate just for the Tauri bundle:
1.0.2.dev661 -> 1.0.2-dev.661 (valid SemVer prerelease)
1.0.2 -> 1.0.2 (passthrough)
1.0.0-rc.1 -> 1.0.0-rc.1 (passthrough)
Tag, git history, PyPI wheel, and the updater's `latest.json` all keep
the PEP 440 form. Only the embedded bundle version uses SemVer, and
the comparison the updater does is bundle-vs-latest.json (both SemVer
now) so the upgrade path stays consistent.
Failing run for reference: 26118619500
Co-authored-by: krypticmouse <herumbshandilya123@gmail.com>
The frontend bundling step in pypi-publish.yml assumed Vite produced
`frontend/dist/`, but vite.config.ts is configured with
`outDir: '../src/openjarvis/server/static'` and `emptyOutDir: true` —
Vite writes straight to the package's static dir and clears stale
assets itself. The `rm -rf dist; cp -r dist/.` ceremony was dead code
that would have deleted the build output had the assertion not
short-circuited it first.
First post-#358 autotag run failed at this step with
`frontend/dist/index.html missing or empty after build` (build was
fine; the assertion checked the wrong path).
Fix: drop the rm/cp dance and assert the actual output location.
Co-authored-by: krypticmouse <herumbshandilya123@gmail.com>
- calculator: add `ln` alias for `math.log`, replace `^` with `**` before
AST parsing so caret-as-power works, convert SyntaxError → ValueError for
consistent error handling, and return `math.inf` on division by zero
(matching the documented meval behaviour) instead of raising an exception
- file_read / file_write: replace the hardcoded `str(path).startswith(str(d) + "/")
guard with `Path.is_relative_to()` so allowed-directory checks work on
Windows (and any OS whose separator is not `/`)
- git_tool: catch `NotADirectoryError` raised by `subprocess.run` on Windows
when `cwd` points to a non-existent path, returning a proper error result
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-authored-by: Robby Manihani <manihani@stanford.edu>
* 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>
