Skip to content

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

Python

fix: address PR review feedback (items 1-6)

Teo Gonzalez Collazo574f5bd4b00e
diff --git a/README.md b/README.md
index 8e2559fa0..72f8559d7 100644
--- a/README.md
+++ b/README.md
@@ -480,6 +480,7 @@ The catalog auto-updates whenever `registry.json` changes β€” new community CLIs
| **πŸ§ͺ Testing & Mocking** | Control HTTP mock servers, manage test stubs, record and replay API traffic for integration testing | **[WireMock](https://wiremock.org)** |
| **πŸ”¬ Graphics & GPU Debugging** | Analyze GPU frame captures, inspect pipeline state, export shaders, and diff rendering state | RenderDoc |
| **🎬 Video & Subtitles** | Transcribe speech, translate subtitles, burn styled captions into video β€” full captioning pipeline | VideoCaptioner |
+| **πŸ” AI-Native Search** | Neural and deep web search with structured content retrieval through embedding-based APIs | [Exa](https://exa.ai) |
| **✨ AI Content Generation** | Generate professional deliverables (slides, docs, diagrams, websites, research reports) through AI-powered cloud APIs | [AnyGen](https://www.anygen.io), Gamma, Beautiful.ai, Tome |
---
@@ -834,12 +835,19 @@ Each application received complete, production-ready CLI interfaces β€” not demo
<td align="center">βœ… 88</td>
</tr>
<tr>
+<td align="center"><strong>πŸ” <a href="exa/agent-harness/">Exa</a></strong></td>
+<td>AI-Native Web Search</td>
+<td><code>cli-anything-exa</code></td>
+<td>exa-py SDK</td>
+<td align="center">βœ… 40</td>
+</tr>
+<tr>
<td align="center" colspan="4"><strong>Total</strong></td>
-<td align="center"><strong>βœ… 2,005</strong></td>
+<td align="center"><strong>βœ… 2,045</strong></td>
</tr>
</table>
-> **100% pass rate** across all 2,005 tests β€” 1,453 unit tests + 533 end-to-end tests + 19 Node.js tests.
+> **100% pass rate** across all 2,045 tests β€” 1,493 unit tests + 533 end-to-end tests + 19 Node.js tests.
---
@@ -948,8 +956,9 @@ cli-anything/
β”œβ”€β”€ πŸ¦™ ollama/agent-harness/ # Ollama CLI (98 tests)
β”œβ”€β”€ 🎨 sketch/agent-harness/ # Sketch CLI (19 tests, Node.js)
β”œβ”€β”€ πŸ”¬ renderdoc/agent-harness/ # RenderDoc CLI (59 tests)
-└── 🎬 videocaptioner/agent-harness/ # VideoCaptioner CLI (26 tests)
-└── ☁️ cloudcompare/agent-harness/ # CloudCompare CLI (88 tests)
+β”œβ”€β”€ 🎬 videocaptioner/agent-harness/ # VideoCaptioner CLI (26 tests)
+β”œβ”€β”€ ☁️ cloudcompare/agent-harness/ # CloudCompare CLI (88 tests)
+└── πŸ” exa/agent-harness/ # Exa CLI (40 tests)
```
Each `agent-harness/` contains an installable Python package under `cli_anything.<software>/` with Click CLI, core modules, utils (including `repl_skin.py` and backend wrapper), and comprehensive tests.
diff --git a/exa/agent-harness/cli_anything/exa/core/search.py b/exa/agent-harness/cli_anything/exa/core/search.py
index 2c79beaf0..ada757e63 100644
--- a/exa/agent-harness/cli_anything/exa/core/search.py
+++ b/exa/agent-harness/cli_anything/exa/core/search.py
@@ -68,6 +68,8 @@ def get_contents(
"""Fetch full page contents for one or more URLs."""
client = get_client()
+ # NOTE: exa-py's get_contents() accepts content keys (text, highlights, ...)
+ # as top-level kwargs, unlike search() which wraps them in a `contents=` param.
kwargs = build_contents_param(content_mode, freshness) or {}
response = client.get_contents(urls, **kwargs)
diff --git a/exa/agent-harness/cli_anything/exa/exa_cli.py b/exa/agent-harness/cli_anything/exa/exa_cli.py
index c17f9c3b8..553c944b5 100644
--- a/exa/agent-harness/cli_anything/exa/exa_cli.py
+++ b/exa/agent-harness/cli_anything/exa/exa_cli.py
@@ -173,7 +173,7 @@ _CATEGORY_CHOICES = click.Choice(
@cli.command("search")
@click.argument("query")
@click.option("--type", "search_type", default="auto", show_default=True,
- type=_SEARCH_TYPES, help="Search mode.")
+ type=_SEARCH_TYPES, help="Search mode. 'auto' uses neural search (embedding-based).")
@click.option("--num-results", "-n", default=10, show_default=True,
type=click.IntRange(1, 100), help="Number of results (1–100).")
@click.option("--category", type=_CATEGORY_CHOICES, default=None,
diff --git a/exa/agent-harness/cli_anything/exa/utils/exa_backend.py b/exa/agent-harness/cli_anything/exa/utils/exa_backend.py
index ebf14da34..d55f2ddea 100644
--- a/exa/agent-harness/cli_anything/exa/utils/exa_backend.py
+++ b/exa/agent-harness/cli_anything/exa/utils/exa_backend.py
@@ -40,11 +40,14 @@ def check_connectivity() -> dict[str, Any]:
"""Verify the API key is valid by running a minimal search.
Returns a dict with keys: ok (bool), message (str).
+
+ Note: This performs a real search call (1 result) which consumes a small
+ amount of API credit. There is no free health-check endpoint in the Exa API.
"""
try:
client = get_client()
client.search("test", num_results=1)
- return {"ok": True, "message": "API key valid β€” Exa reachable"}
+ return {"ok": True, "message": "API key valid β€” Exa reachable (note: uses 1 search credit)"}
except RuntimeError as exc:
return {"ok": False, "message": str(exc)}
except Exception as exc: # noqa: BLE001
@@ -65,7 +68,7 @@ def build_contents_param(
A contents dict suitable for passing to exa.search() / exa.get_contents(),
or None if content_mode is "none".
"""
- if content_mode == "none": # noqa: SIM114
+ if content_mode == "none":
return None
contents: dict[str, Any] = {}