Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 22 additions & 23 deletions Cargo.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

3 changes: 2 additions & 1 deletion crates/openhuman-cli/Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -345,6 +345,7 @@ tinytools-agent = { path = "../../vendor/tinyagents/vendor/tinytools/crates/tiny
# The Jev ranker `tool-search-bench` measures; gated with the crate's `jev`
# feature so the bin builds without a Jev client.
tinytools-jev = { path = "../../vendor/tinyagents/vendor/tinytools/crates/tinytools-jev", optional = true }
tinyjevclient = { git = "https://github.com/tinyhumansai/tinyjevclient", rev = "84b3983c7e1e14f7515658ceafabb6c4e7967c94", optional = true }
tokio = { version = "1", features = ["full"] }
toml = "1.0"
tracing = "0.1"
Expand Down Expand Up @@ -393,7 +394,7 @@ wiremock = "0.6"
default = ["openhuman-core/default", "openhuman-tinyhumans/default", "jev"]
# The Jev-backed `tool_search` ranker; `openhuman-tinyhumans`'s own gate, plus
# the client `tool-search-bench` measures it with.
jev = ["openhuman-tinyhumans/jev", "dep:tinytools-jev"]
jev = ["openhuman-tinyhumans/jev", "dep:tinytools-jev", "dep:tinyjevclient"]
http-server = ["openhuman-core/http-server", "openhuman-tinyhumans/http-server"]
inference = ["openhuman-core/inference", "openhuman-tinyhumans/inference"]
documents = ["openhuman-core/documents", "openhuman-tinyhumans/documents"]
Expand Down
1 change: 1 addition & 0 deletions crates/openhuman-cli/src/bin/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ the arguments to `openhuman_core::run_core_from_args`.
| `openhuman-fleet` | `fleet.rs` | `http-server`, `bin-tools` | Process-per-user supervisor + reverse proxy |
| `rss-bench` | `rss_bench.rs` | `rss-bench` | Steady-state RSS benchmark for an embedded agent roster |
| `tool-dialect-bench` | `tool_dialect_bench.rs` | none | Manual A/B of the text tool-call dialects against a local Ollama model |
| `tool-search-bench` | `tool_search_bench.rs` | none (`jev`, in `default`, for the Jev rankers) | `tool_search` ranker comparison (bm25 / overlap / embedding / jev) over the real orchestrator registry plus the recorded Composio catalogues, against `tests/fixtures/tool_search/intents.jsonl` |
| `library-profile` | `library_profile/main.rs` (+ `harness.rs`, `mock.rs`, `scenarios/`) | `rss-bench` (add `rss-bench-dhat` for heap profiles) | Hermetic library-embedding profiling scenarios |

`http-server` is in `default`; `bin-tools`, `rss-bench` and `rss-bench-dhat`
Expand Down
Loading
Loading