agentx-python 0.6.9__tar.gz → 0.6.11__tar.gz

{agentx_python-0.6.9 → agentx_python-0.6.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentx-python
-Version: 0.6.9
+Version: 0.6.11
 Summary: Official Python SDK for AgentX (https://www.agentx.so/)
 Home-page: https://github.com/AgentX-ai/AgentX-python
 Author: Robin Wang and AgentX Team
@@ -21,19 +21,33 @@ Provides-Extra: crewai
 Requires-Dist: crewai>=0.80.0; extra == "crewai"
 Provides-Extra: openai-agents
 Requires-Dist: openai-agents>=0.0.3; extra == "openai-agents"
+Provides-Extra: openai
+Requires-Dist: openai>=1.0.0; extra == "openai"
 Provides-Extra: anthropic
 Requires-Dist: anthropic>=0.25.0; extra == "anthropic"
 Provides-Extra: google-adk
 Requires-Dist: google-adk>=1.0.0; extra == "google-adk"
 Provides-Extra: google-genai
 Requires-Dist: google-genai>=1.0.0; extra == "google-genai"
+Provides-Extra: litellm
+Requires-Dist: litellm>=1.0.0; extra == "litellm"
+Provides-Extra: llamaindex
+Requires-Dist: llama-index-core>=0.10.0; extra == "llamaindex"
+Provides-Extra: autogen
+Requires-Dist: autogen-agentchat>=0.4.0; extra == "autogen"
+Requires-Dist: autogen-core>=0.4.0; extra == "autogen"
 Provides-Extra: all
 Requires-Dist: langchain-core>=0.1.0; extra == "all"
 Requires-Dist: crewai>=0.80.0; extra == "all"
 Requires-Dist: openai-agents>=0.0.3; extra == "all"
+Requires-Dist: openai>=1.0.0; extra == "all"
 Requires-Dist: anthropic>=0.25.0; extra == "all"
 Requires-Dist: google-adk>=1.0.0; extra == "all"
 Requires-Dist: google-genai>=1.0.0; extra == "all"
+Requires-Dist: litellm>=1.0.0; extra == "all"
+Requires-Dist: llama-index-core>=0.10.0; extra == "all"
+Requires-Dist: autogen-agentchat>=0.4.0; extra == "all"
+Requires-Dist: autogen-core>=0.4.0; extra == "all"
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -72,6 +86,7 @@ Also see [SDK Developer Docs](https://developers.agentx.so), [API Reference Docs
 - [Production tracing](#production-tracing) — record live agent runs from any framework
 - [Monitor](#monitor) — automatic production monitoring, patterns and signals
 - [Custom agent evaluations](#custom-agent-evaluations) — LLM-as-a-judge, cosine / Jaccard similarity
+- [Self-host](#self-host) — run Trace/Evaluate/Monitor on your own machine instead of the hosted dashboard
 - [Links](#links)
 
 ---
@@ -234,9 +249,13 @@ Each integration auto-captures LLM calls, tool calls, and token usage — instal
 | LangChain             | `pip install "agentx-python[langchain]"`     | `AgentXCallbackHandler`  |
 | CrewAI                | `pip install "agentx-python[crewai]"`        | `AgentXCrewObserver`     |
 | OpenAI Agents SDK     | `pip install "agentx-python[openai-agents]"` | `AgentXTracingProcessor` |
+| OpenAI (raw client)   | `pip install "agentx-python[openai]"`        | `patch_openai_client`    |
 | Anthropic             | `pip install "agentx-python[anthropic]"`     | `patch_anthropic_client` |
 | Google ADK            | `pip install "agentx-python[google-adk]"`    | `AgentXADKPlugin`        |
 | Google GenAI (Gemini) | `pip install "agentx-python[google-genai]"`  | `patch_genai_client`     |
+| LiteLLM               | `pip install "agentx-python[litellm]"`       | `AgentXLiteLLMLogger`    |
+| LlamaIndex             | `pip install "agentx-python[llamaindex]"`    | `AgentXLlamaIndexHandler`|
+| AutoGen                | `pip install "agentx-python[autogen]"`       | `AgentXAutoGenObserver`  |
 
 Or plain Python — wrap any function with `@tracer.trace(...)` and it just works, no framework required.
 
@@ -273,6 +292,12 @@ for signal in client.monitor.signals.list(severity="high"):
     print(signal.summary, signal.occurrence_count)
 ```
 
+Per-agent coverage/threshold settings (sample rate, retention, and threshold overrides like the built-in "Latency regression" pattern's threshold) are `client.monitor.profile.get()`/`.update()`:
+
+```python
+client.monitor.profile.update("agent_123", threshold_overrides={"latencyMs": 15000})
+```
+
 See **[TRACING.md](TRACING.md)** for the complete Monitor guide.
 
 ---
@@ -302,7 +327,40 @@ print(report.recommendations)      # list of prioritized, actionable fixes
 
 Ask a case's question several extra ways each run, LLM-paraphrased server-side, to catch agents that break on phrasing rather than substance, and override the judge's prompt/model per config, see [Smoke testing](EVALUATIONS.md#smoke-testing-phrasing-robustness) and [Configuring the judge](EVALUATIONS.md#configuring-the-judge) in the full guide.
 
-See **[EVALUATIONS.md](EVALUATIONS.md)** for the full guide — dataset builder, framework adapters, similarity metrics, smoke testing, judge configuration, and the complete API reference.
+Since AgentX doesn't own your agent's code, `client.evaluations.prompts` lets AgentX become your prompt's *source of truth* instead — the same problem LangSmith's Prompt Hub and Langfuse's Prompt Management solve. Pull a version at runtime, tag your eval runs (or live traces) with it, and let a judge propose a rewrite from your real worst-rated results — a human always has to approve before it publishes:
+
+```python
+prompt = client.evaluations.prompts.get("support-agent-system-prompt")
+# use prompt.text as your own agent's system prompt
+
+client.evaluations.run(
+    dataset_id="evds_…",
+    subject={"kind": "custom_agent", "metadata": {"promptName": prompt.name}},
+).execute(my_agent_fn)
+```
+
+See [Prompt registry](EVALUATIONS.md#prompt-registry) in the full guide, or [self-host's docs](https://docs.agentx.so/self-host#prompt-registry) for the "Suggest improvement" dashboard flow (self-host only — no hosted-SaaS equivalent yet).
+
+See **[EVALUATIONS.md](EVALUATIONS.md)** for the full guide — dataset builder, framework adapters, similarity metrics, smoke testing, judge configuration, prompt registry, and the complete API reference.
+
+---
+
+## Self-host
+
+Prefer to run Trace/Evaluate/Monitor locally instead of the hosted dashboard — no account, bring your own LLM keys? This SDK ships a launcher for [AgentX-trace-eval](https://github.com/AgentX-ai/AgentX-trace-eval), a separate, portable governance engine:
+
+```bash
+agentx-trace-eval --dev
+```
+
+The first run downloads the engine (and dashboard) into `~/.agentx/bin` and prints a local API key; every run after that just starts it. Point this SDK at it instead of the hosted API:
+
+```bash
+export AGENTX_API_BASE_URL=http://localhost:4700/api/v1
+export AGENTX_API_KEY=<printed by agentx-trace-eval on first run>
+```
+
+`agentx-trace-eval` isn't this SDK's own code — the engine itself is a separate, compiled binary, downloaded on demand rather than bundled into this package, so installing `agentx-python` doesn't get any heavier for the (much more common) case of just talking to the hosted AgentX API. See that repo's README for what's included, and `AGENTX_INSTALL_DIR`/`AGENTX_TRACE_EVAL_VERSION`/`AGENTX_TRACE_EVAL_SKIP_WEB` env vars to control where/what it installs.
 
 ---
 
@@ -314,3 +372,4 @@ See **[EVALUATIONS.md](EVALUATIONS.md)** for the full guide — dataset builder,
 - **Tracing docs** — [TRACING.md](TRACING.md)
 - **Evaluations docs** — [EVALUATIONS.md](EVALUATIONS.md)
 - **Monitor docs** — [docs.agentx.so/sdk/monitor](https://docs.agentx.so/sdk/monitor)
+- **Self-host** — [AgentX-trace-eval](https://github.com/AgentX-ai/AgentX-trace-eval)

agentx_python-0.6.9/agentx_python.egg-info/PKG-INFO → agentx_python-0.6.11/README.md

@@ -1,51 +1,3 @@
-Metadata-Version: 2.4
-Name: agentx-python
-Version: 0.6.9
-Summary: Official Python SDK for AgentX (https://www.agentx.so/)
-Home-page: https://github.com/AgentX-ai/AgentX-python
-Author: Robin Wang and AgentX Team
-Author-email: contact@agentx.so
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Requires-Python: >=3.6
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: urllib3>=1.26.11
-Requires-Dist: certifi
-Requires-Dist: requests
-Requires-Dist: pydantic>=2.0.0
-Provides-Extra: langchain
-Requires-Dist: langchain-core>=0.1.0; extra == "langchain"
-Provides-Extra: crewai
-Requires-Dist: crewai>=0.80.0; extra == "crewai"
-Provides-Extra: openai-agents
-Requires-Dist: openai-agents>=0.0.3; extra == "openai-agents"
-Provides-Extra: anthropic
-Requires-Dist: anthropic>=0.25.0; extra == "anthropic"
-Provides-Extra: google-adk
-Requires-Dist: google-adk>=1.0.0; extra == "google-adk"
-Provides-Extra: google-genai
-Requires-Dist: google-genai>=1.0.0; extra == "google-genai"
-Provides-Extra: all
-Requires-Dist: langchain-core>=0.1.0; extra == "all"
-Requires-Dist: crewai>=0.80.0; extra == "all"
-Requires-Dist: openai-agents>=0.0.3; extra == "all"
-Requires-Dist: anthropic>=0.25.0; extra == "all"
-Requires-Dist: google-adk>=1.0.0; extra == "all"
-Requires-Dist: google-genai>=1.0.0; extra == "all"
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: license-file
-Dynamic: provides-extra
-Dynamic: requires-dist
-Dynamic: requires-python
-Dynamic: summary
-
 ![Logo](https://agentx-resources.s3.us-west-1.amazonaws.com/AgentX-logo-387x60.png)
 
 [![PyPI version](https://img.shields.io/pypi/v/agentx-python)](https://pypi.org/project/agentx-python/)
@@ -72,6 +24,7 @@ Also see [SDK Developer Docs](https://developers.agentx.so), [API Reference Docs
 - [Production tracing](#production-tracing) — record live agent runs from any framework
 - [Monitor](#monitor) — automatic production monitoring, patterns and signals
 - [Custom agent evaluations](#custom-agent-evaluations) — LLM-as-a-judge, cosine / Jaccard similarity
+- [Self-host](#self-host) — run Trace/Evaluate/Monitor on your own machine instead of the hosted dashboard
 - [Links](#links)
 
 ---
@@ -234,9 +187,13 @@ Each integration auto-captures LLM calls, tool calls, and token usage — instal
 | LangChain             | `pip install "agentx-python[langchain]"`     | `AgentXCallbackHandler`  |
 | CrewAI                | `pip install "agentx-python[crewai]"`        | `AgentXCrewObserver`     |
 | OpenAI Agents SDK     | `pip install "agentx-python[openai-agents]"` | `AgentXTracingProcessor` |
+| OpenAI (raw client)   | `pip install "agentx-python[openai]"`        | `patch_openai_client`    |
 | Anthropic             | `pip install "agentx-python[anthropic]"`     | `patch_anthropic_client` |
 | Google ADK            | `pip install "agentx-python[google-adk]"`    | `AgentXADKPlugin`        |
 | Google GenAI (Gemini) | `pip install "agentx-python[google-genai]"`  | `patch_genai_client`     |
+| LiteLLM               | `pip install "agentx-python[litellm]"`       | `AgentXLiteLLMLogger`    |
+| LlamaIndex             | `pip install "agentx-python[llamaindex]"`    | `AgentXLlamaIndexHandler`|
+| AutoGen                | `pip install "agentx-python[autogen]"`       | `AgentXAutoGenObserver`  |
 
 Or plain Python — wrap any function with `@tracer.trace(...)` and it just works, no framework required.
 
@@ -273,6 +230,12 @@ for signal in client.monitor.signals.list(severity="high"):
     print(signal.summary, signal.occurrence_count)
 ```
 
+Per-agent coverage/threshold settings (sample rate, retention, and threshold overrides like the built-in "Latency regression" pattern's threshold) are `client.monitor.profile.get()`/`.update()`:
+
+```python
+client.monitor.profile.update("agent_123", threshold_overrides={"latencyMs": 15000})
+```
+
 See **[TRACING.md](TRACING.md)** for the complete Monitor guide.
 
 ---
@@ -302,7 +265,40 @@ print(report.recommendations)      # list of prioritized, actionable fixes
 
 Ask a case's question several extra ways each run, LLM-paraphrased server-side, to catch agents that break on phrasing rather than substance, and override the judge's prompt/model per config, see [Smoke testing](EVALUATIONS.md#smoke-testing-phrasing-robustness) and [Configuring the judge](EVALUATIONS.md#configuring-the-judge) in the full guide.
 
-See **[EVALUATIONS.md](EVALUATIONS.md)** for the full guide — dataset builder, framework adapters, similarity metrics, smoke testing, judge configuration, and the complete API reference.
+Since AgentX doesn't own your agent's code, `client.evaluations.prompts` lets AgentX become your prompt's *source of truth* instead — the same problem LangSmith's Prompt Hub and Langfuse's Prompt Management solve. Pull a version at runtime, tag your eval runs (or live traces) with it, and let a judge propose a rewrite from your real worst-rated results — a human always has to approve before it publishes:
+
+```python
+prompt = client.evaluations.prompts.get("support-agent-system-prompt")
+# use prompt.text as your own agent's system prompt
+
+client.evaluations.run(
+    dataset_id="evds_…",
+    subject={"kind": "custom_agent", "metadata": {"promptName": prompt.name}},
+).execute(my_agent_fn)
+```
+
+See [Prompt registry](EVALUATIONS.md#prompt-registry) in the full guide, or [self-host's docs](https://docs.agentx.so/self-host#prompt-registry) for the "Suggest improvement" dashboard flow (self-host only — no hosted-SaaS equivalent yet).
+
+See **[EVALUATIONS.md](EVALUATIONS.md)** for the full guide — dataset builder, framework adapters, similarity metrics, smoke testing, judge configuration, prompt registry, and the complete API reference.
+
+---
+
+## Self-host
+
+Prefer to run Trace/Evaluate/Monitor locally instead of the hosted dashboard — no account, bring your own LLM keys? This SDK ships a launcher for [AgentX-trace-eval](https://github.com/AgentX-ai/AgentX-trace-eval), a separate, portable governance engine:
+
+```bash
+agentx-trace-eval --dev
+```
+
+The first run downloads the engine (and dashboard) into `~/.agentx/bin` and prints a local API key; every run after that just starts it. Point this SDK at it instead of the hosted API:
+
+```bash
+export AGENTX_API_BASE_URL=http://localhost:4700/api/v1
+export AGENTX_API_KEY=<printed by agentx-trace-eval on first run>
+```
+
+`agentx-trace-eval` isn't this SDK's own code — the engine itself is a separate, compiled binary, downloaded on demand rather than bundled into this package, so installing `agentx-python` doesn't get any heavier for the (much more common) case of just talking to the hosted AgentX API. See that repo's README for what's included, and `AGENTX_INSTALL_DIR`/`AGENTX_TRACE_EVAL_VERSION`/`AGENTX_TRACE_EVAL_SKIP_WEB` env vars to control where/what it installs.
 
 ---
 
@@ -314,3 +310,4 @@ See **[EVALUATIONS.md](EVALUATIONS.md)** for the full guide — dataset builder,
 - **Tracing docs** — [TRACING.md](TRACING.md)
 - **Evaluations docs** — [EVALUATIONS.md](EVALUATIONS.md)
 - **Monitor docs** — [docs.agentx.so/sdk/monitor](https://docs.agentx.so/sdk/monitor)
+- **Self-host** — [AgentX-trace-eval](https://github.com/AgentX-ai/AgentX-trace-eval)

{agentx_python-0.6.9 → agentx_python-0.6.11}/agentx/agentx.py

@@ -44,7 +44,9 @@ class AgentX:
 
         # Monitor: create/reuse patterns (client.monitor.patterns) that a trace can be checked
         # against at send time via tracer.trace(..., monitor=True, pattern_ids=[...]), then read
-        # back the resulting alerts/findings with client.monitor.signals.
+        # back the resulting alerts/findings with client.monitor.signals. Per-agent coverage and
+        # detection settings (sample rate, retention, threshold overrides like the built-in
+        # "Latency regression" pattern's threshold) are client.monitor.profile.
         self.monitor = MonitorClient(
             api_key=self.api_key,
             sdk_version=VERSION,

agentx_python-0.6.11/agentx/cli.py

@@ -0,0 +1,158 @@
+"""
+`agentx-trace-eval` — thin launcher for AgentX's self-hostable governance engine (Trace,
+Evaluate, Monitor), published separately at github.com/AgentX-ai/AgentX-trace-eval (a Go CLI
+wrapping a Bun-compiled TypeScript engine, not Python). That compiled engine binary is tens of
+megabytes; most `pip install agentx-python` installs are just this SDK talking to the hosted
+AgentX SaaS and would never touch it, so it isn't bundled in this package. Instead, this command
+downloads the matching release into ~/.agentx/bin the first time it's needed (mirroring
+AgentX-trace-eval's own install.sh) and then hands off to the real `agentx-server` binary.
+
+Usage:
+    agentx-trace-eval --dev
+    agentx-trace-eval --port 5000 --db-url postgres://...
+"""
+
+import os
+import platform
+import shutil
+import stat
+import sys
+import tarfile
+import tempfile
+from pathlib import Path
+from typing import Tuple
+
+import requests
+
+REPO = "AgentX-ai/AgentX-trace-eval"
+INSTALL_DIR = Path(os.environ.get("AGENTX_INSTALL_DIR", str(Path.home() / ".agentx" / "bin")))
+_BIN_NAMES = ("agentx", "agentx-server", "agentx-engine")
+
+
+def _platform_tag() -> Tuple[str, str]:
+    system = platform.system()
+    if system == "Darwin":
+        os_name = "darwin"
+    elif system == "Linux":
+        os_name = "linux"
+    else:
+        raise SystemExit(
+            f"agentx-trace-eval: unsupported OS {system!r} (self-host currently supports macOS and Linux)"
+        )
+
+    machine = platform.machine().lower()
+    if machine in ("arm64", "aarch64"):
+        arch = "arm64"
+    elif machine in ("x86_64", "amd64"):
+        arch = "amd64"
+    else:
+        raise SystemExit(f"agentx-trace-eval: unsupported architecture {machine!r}")
+
+    return os_name, arch
+
+
+def _release_url(asset: str, version: str) -> str:
+    if version == "latest":
+        return f"https://github.com/{REPO}/releases/latest/download/{asset}"
+    return f"https://github.com/{REPO}/releases/download/{version}/{asset}"
+
+
+def _download(url: str, dest: Path) -> None:
+    response = requests.get(url, stream=True, timeout=60)
+    response.raise_for_status()
+    with open(dest, "wb") as f:
+        for chunk in response.iter_content(chunk_size=1 << 16):
+            f.write(chunk)
+
+
+def _extract_tar(archive: Path, dest_dir: Path) -> None:
+    with tarfile.open(archive) as tar:
+        try:
+            # filter="data" (PEP 706, Python 3.12+) rejects absolute paths/symlink escapes.
+            # Belt-and-suspenders here since these are trusted release assets built by our own CI
+            # (see REPO above), not arbitrary user-supplied archives.
+            tar.extractall(dest_dir, filter="data")
+        except TypeError:
+            tar.extractall(dest_dir)  # Python < 3.12: filter kwarg doesn't exist yet
+
+
+def _install(version: str = "latest") -> None:
+    os_name, arch = _platform_tag()
+    INSTALL_DIR.mkdir(parents=True, exist_ok=True)
+
+    print(f"agentx-trace-eval: downloading agentx ({os_name}/{arch})...", file=sys.stderr)
+    with tempfile.TemporaryDirectory() as tmp:
+        tmp_dir = Path(tmp)
+        archive = tmp_dir / "agentx.tar.gz"
+        url = _release_url(f"agentx_{os_name}_{arch}.tar.gz", version)
+        try:
+            _download(url, archive)
+        except requests.HTTPError as exc:
+            raise SystemExit(
+                f"agentx-trace-eval: failed to download {url} ({exc}).\n"
+                "No published release found; see AgentX-trace-eval's README for building from source."
+            )
+
+        _extract_tar(archive, tmp_dir)
+
+        found_any = False
+        for name in _BIN_NAMES:
+            src = tmp_dir / name
+            if not src.exists():
+                continue
+            found_any = True
+            dest = INSTALL_DIR / name
+            shutil.move(str(src), str(dest))
+            dest.chmod(dest.stat().st_mode | stat.S_IEXEC | stat.S_IXGRP | stat.S_IXOTH)
+
+        if not found_any:
+            raise SystemExit(f"agentx-trace-eval: downloaded archive from {url} didn't contain any of {_BIN_NAMES}")
+
+    if os.environ.get("AGENTX_TRACE_EVAL_SKIP_WEB"):
+        return
+
+    # Best-effort: the dashboard is a separate, platform-independent asset (see
+    # AgentX-trace-eval's README's "Dashboard release"). Missing it shouldn't block getting the
+    # engine running headless, so a failure here warns and continues rather than raising.
+    print("agentx-trace-eval: downloading dashboard...", file=sys.stderr)
+    web_dir = INSTALL_DIR / "web"
+    with tempfile.TemporaryDirectory() as tmp:
+        web_archive = Path(tmp) / "agentx-web.tar.gz"
+        web_url = _release_url("agentx-web.tar.gz", version)
+        try:
+            _download(web_url, web_archive)
+        except requests.HTTPError:
+            print(
+                f"agentx-trace-eval: no dashboard bundle found at {web_url}, continuing without one",
+                file=sys.stderr,
+            )
+            return
+        if web_dir.exists():
+            shutil.rmtree(web_dir)
+        web_dir.mkdir(parents=True)
+        _extract_tar(web_archive, web_dir)
+
+
+def ensure_installed(version: str = "latest") -> Path:
+    """Downloads agentx-server (+ its engine) into ~/.agentx/bin if not already present there.
+    Returns the path to the agentx-server executable. Set AGENTX_INSTALL_DIR to change where
+    this looks/installs; set AGENTX_TRACE_EVAL_VERSION to pin a release tag instead of latest."""
+    server_path = INSTALL_DIR / "agentx-server"
+    if not server_path.exists():
+        _install(version=version)
+    return server_path
+
+
+def main() -> None:
+    version = os.environ.get("AGENTX_TRACE_EVAL_VERSION", "latest")
+    server_path = ensure_installed(version=version)
+    if not server_path.exists():
+        raise SystemExit(f"agentx-trace-eval: {server_path} still missing after install, giving up")
+
+    # os.execv replaces this process rather than spawning a subprocess: signals, stdio, and the
+    # exit code all pass straight through to agentx-server, same as invoking it directly.
+    os.execv(str(server_path), [str(server_path)] + sys.argv[1:])
+
+
+if __name__ == "__main__":
+    main()

{agentx_python-0.6.9 → agentx_python-0.6.11}/agentx/evaluations/client.py

@@ -17,6 +17,7 @@ from agentx.evaluations.models import (
     EvaluationSettings,
     EvaluationSubject,
     ModelInfo,
+    Prompt,
     Report,
 )
 
@@ -77,12 +78,14 @@ class EvaluationsClient:
                 "accept": "*/*",
             }
         )
-        # Expose dataset / evaluation-settings builder factories
+        # Expose dataset / evaluation-settings / prompt builder factories
         from agentx.evaluations.datasets import DatasetClient
         from agentx.evaluations.evaluation_settings import EvaluationSettingsClient
+        from agentx.evaluations.prompts import PromptClient
 
         self.datasets = DatasetClient(self)
         self.settings = EvaluationSettingsClient(self)
+        self.prompts = PromptClient(self)
 
     # ------------------------------------------------------------------
     # Low-level HTTP
@@ -195,6 +198,27 @@ class EvaluationsClient:
         )
         return EvaluationSettings(**data)
 
+    # ------------------------------------------------------------------
+    # Prompt registry endpoints — see agentx.evaluations.prompts.PromptClient for the concept
+    # (the external-agent analog to native autotune). Deliberately read-mostly: no publish here,
+    # a new version only ever comes from the dashboard's human-approved propose/publish flow.
+    # ------------------------------------------------------------------
+
+    def create_prompt(self, payload: dict) -> Prompt:
+        data = self._request("POST", "/prompts", json=self._with_workspace(payload))
+        return Prompt(**data)
+
+    def list_prompts(self) -> List[Prompt]:
+        data = self._request("GET", "/prompts", params=self._workspace_params())
+        return [Prompt(**p) for p in (data if isinstance(data, list) else data.get("prompts", []))]
+
+    def get_prompt(self, name: str, version: Optional[int] = None) -> Prompt:
+        params = self._workspace_params() or {}
+        if version is not None:
+            params = {**params, "version": version}
+        data = self._request("GET", f"/prompts/{name}", params=params or None)
+        return Prompt(**data)
+
     # ------------------------------------------------------------------
     # Run endpoints
     # ------------------------------------------------------------------

{agentx_python-0.6.9 → agentx_python-0.6.11}/agentx/evaluations/models.py

@@ -128,6 +128,30 @@ class EvaluationSettings(BaseModel):
         extra = "ignore"
 
 
+# ---------------------------------------------------------------------------
+# Prompt registry — the external-agent analog to AgentX's native autotune. AgentX doesn't own
+# your agent's code, so instead of branching/applying a config it becomes the prompt's source of
+# truth (same shape as LangSmith's Prompt Hub / Langfuse's Prompt Management): pull a version at
+# runtime with ``client.evaluations.prompts.get(name)``, use ``prompt.text`` as your agent's
+# system prompt, and tag your eval runs so the existing version-comparison view can tell you
+# which published version scored higher — see ``client.evaluations.prompts`` docs.
+# ---------------------------------------------------------------------------
+
+
+class Prompt(BaseModel):
+    id: str = Field(alias="_id")
+    name: str
+    description: Optional[str] = None
+    version: int
+    text: str
+    created_at: Optional[str] = Field(default=None, alias="createdAt")
+    updated_at: Optional[str] = Field(default=None, alias="updatedAt")
+
+    class Config:
+        populate_by_name = True
+        extra = "ignore"
+
+
 # ---------------------------------------------------------------------------
 # Evaluation subject
 # ---------------------------------------------------------------------------

agentx_python-0.6.11/agentx/evaluations/prompts.py

@@ -0,0 +1,49 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, List, Optional
+
+from agentx.evaluations.models import Prompt
+
+if TYPE_CHECKING:
+    from agentx.evaluations.client import EvaluationsClient
+
+
+class PromptClient:
+    """Thin wrapper surfaced as ``client.evaluations.prompts`` — the external-agent analog to
+    AgentX's native autotune. AgentX doesn't own your agent's code, so instead of branching and
+    applying a config, it becomes the prompt's source of truth (the same shape as LangSmith's
+    Prompt Hub / Langfuse's Prompt Management): create/pull versions here, use ``prompt.text`` as
+    your agent's own system prompt, and tag your eval runs with the pulled version so the
+    existing version-comparison view (``client.evaluations`` run comparisons on a dataset) can
+    tell you which published version actually scored higher.
+
+    Deliberately read-mostly from here: there is no ``publish`` on this client. A prompt only
+    gets a new version through the dashboard's human-approved propose/publish flow, so a
+    rewritten prompt never reaches your running agent without someone explicitly approving it.
+
+    Example::
+
+        prompt = client.evaluations.prompts.get("support-agent-system-prompt")
+        # ... call your own LLM using prompt.text as the system prompt ...
+        client.evaluations.init_run(
+            dataset_id=dataset_id,
+            subject=EvaluationSubject(
+                metadata={
+                    "promptName": prompt.name,
+                    "version": f"{prompt.name}@v{prompt.version}",
+                }
+            ),
+        )
+    """
+
+    def __init__(self, client: "EvaluationsClient"):
+        self._client = client
+
+    def create(self, name: str, text: str, description: Optional[str] = None) -> Prompt:
+        return self._client.create_prompt({"name": name, "text": text, "description": description})
+
+    def get(self, name: str, version: Optional[int] = None) -> Prompt:
+        return self._client.get_prompt(name, version=version)
+
+    def list(self) -> List[Prompt]:
+        return self._client.list_prompts()

{agentx_python-0.6.9 → agentx_python-0.6.11}/agentx/evaluations/runner.py

@@ -335,6 +335,7 @@ class EvaluationsRunner:
         self._client = client
         self.datasets = client.datasets
         self.settings = client.settings
+        self.prompts = client.prompts
 
     def list_models(self, provider: Optional[str] = None) -> List[ModelInfo]:
         """List the LLM models AgentX supports — the same set selectable for