Two fixes: (1) /v1/chat/completions now builds its injected system prompt via SystemPromptBuilder, so SOUL.md/MEMORY.md/USER.md persona files apply to the OpenAI-compatible endpoint exactly as they do on the managed-agent path; injection still only happens when the client omits a system message. (2) FTS5 query tokens are now split on any non-alphanumeric character, so apostrophes (user's) and quotes can no longer reach the MATCH string unescaped; all-punctuation queries return empty instead of erroring.
The Rust workspace fails to build on stable 1.86/1.87 with cryptic E0658
errors deep in dependencies: rig-core uses let-chains and
openjarvis-skills uses `is_multiple_of`, both stabilized in 1.88 (#252).
Add a rust-toolchain.toml pinning channel 1.88 (rustup then auto-selects
a working toolchain instead of erroring mid-build) and declare
rust-version = "1.88" in [workspace.package] to self-document it.
Because the toolchain pin makes CI's `cargo clippy -D warnings` run under
1.88 — whose clippy enables `uninlined_format_args` — also apply the
mechanical `format!("{}", x)` -> `format!("{x}")` rewrites across the
workspace (via `clippy --fix`; string output is identical, no logic
change). Verified clippy + fmt + `cargo test --workspace` clean on BOTH
1.88 and current stable.
Verified locally: cargo +1.86 and +1.87 fail (E0658), +1.88 builds and
tests cleanly. Supporting true 1.86 is infeasible without downgrading
rig-core below the versions exposing the token-usage symbols we use —
deferred.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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>
- Add porter stemming to FTS5 tokenizer (tokenize='porter unicode61')
so plurals like 'medications' match 'Medication'
- Strip punctuation from FTS5 queries so question marks don't break MATCH
- Expand tilde (~) in db_path before opening SQLite connection
- Remove 'id' from FTS5 columns (UUIDs shouldn't be full-text indexed)
- Add memory context injection to server chat_completions route
(routes.py had no memory integration - UI chat was never grounded)
- Fix agent name-to-ID resolution in agent_cmd.py (foreign key error)
- Align Python SQLiteMemory schema with Rust backend
- Engine discovery (#73): get_engine() now falls back to any healthy
engine when the explicitly-requested key fails, instead of returning
None. Fixes LM Studio (and other non-default engines) not being found
when deploying agents.
- FTS5 case sensitivity & scoring (#67): Add explicit unicode61 tokenizer
to the FTS5 virtual table for case-insensitive search. Replace ambiguous
`rank` column with explicit `bm25()` call with column weights (id=0,
content=1, source=0.5) to produce correct positive scores. Includes
auto-migration for existing databases.
- Interactive engine selection (#72): `jarvis init` now detects running
engines and presents an interactive picker. Also accepts `--engine`
flag to skip the prompt. Engine choice flows through to config
generation.
- Windows desktop support (#68): Add RAM detection via wmic, Windows
binary paths (LOCALAPPDATA, ProgramFiles, cargo), port cleanup via
netstat+taskkill, and USERPROFILE fallback for HOME env var.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat: add interactive agent confirmation mode and fix tool loading
- Add `interactive` and `confirm_callback` params to ToolUsingAgent and
NativeReActAgent so CLI sessions can prompt user before tool execution
- Fix tool resolution in `ask` and `chat` commands to fall back to
config.tools.enabled when no --tools flag is provided
- Register shell_exec tool in tools/__init__.py auto-discovery
- Add dspy and gepa as optional learning extras (learning-dspy, learning-gepa)
- Fix openjarvis-rust lock version (1.0.0 → 0.1.0)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(cli): support configured tool defaults and confirmations
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
