llms.txt + llm_api example + modernize examples to the module-level API

Author: piotrekno1

.github/workflows/release.yml

@@ -47,11 +47,19 @@ jobs:
           OUTPUT: /tmp/release-notes.md
         run: python3 scripts/build_changelog_comment.py
 
+      - name: Build llms.txt artifacts
+        if: github.ref_type == 'tag'
+        env:
+          OUTPUT_DIR: llms-dist
+        run: python3 scripts/build_llms_txt.py
+
       - name: Create GitHub release
         if: github.ref_type == 'tag'
         uses: softprops/action-gh-release@v2
         with:
-          files: dist/*
+          files: |
+            dist/*
+            llms-dist/*
           body_path: /tmp/release-notes.md
 
       - name: Publish package to PyPI

CHANGELOG.md

@@ -7,6 +7,8 @@ under Unreleased and move into a version section at release time.
 
 ### Added
 
+- `examples/llm_api_example.py`: raw-HTTP LLM tracking with `wildedge.llm_api()`; existing examples updated to the module-level API (`wildedge.span` / `wildedge.flush` / `wildedge.register_model` instead of threading a client variable)
+- Releases ship `llms.txt` and `llms-full.txt` as GitHub release assets: the full documentation for that exact version in one file, generated by `scripts/build_llms_txt.py`. README quickstart rewritten around the module-level API.
 - `wildedge doctor --send-test-event`: sends one real span event through the full pipeline and reports the ingest response, proving DSN auth and connectivity end to end. The report gains an `environment` section (`WILDEDGE_*` variables, autoload PYTHONPATH status) plus `config_status` / `connectivity_status` fields.
 - `wildedge.llm_api()`: provider-agnostic tracking for LLM calls made with any HTTP client (OpenRouter, vLLM, Ollama, OpenAI/Anthropic-compatible endpoints). Times the block, normalizes usage payloads from either provider shape via `call.usage()` / `call.response()`, supports TTFT marks and async use, and records exceptions as error events. See `docs/llm_api.md`.
 - `register_model()` without a matching extractor defaults the model name to the explicit `model_id` instead of the placeholder object's type name.

README.md

@@ -55,18 +55,23 @@ Useful flags:
 ```python
 import wildedge
 
-client = wildedge.init(
-    dsn="...",  # or WILDEDGE_DSN env var
-    integrations=["transformers"],
-    hubs=["huggingface"],
-)
+wildedge.init(integrations=["transformers"])  # optional under `wildedge run`
 
-# models loaded after this point are tracked automatically
-```
+# models loaded after this point are tracked automatically; add traces,
+# spans and LLM API calls anywhere, no client instance to pass around:
+with wildedge.trace(run_id="run-1"):
+    with wildedge.span(kind="agent_step", name="plan"):
+        ...
 
-If no DSN is configured, the client becomes a no-op and logs a warning.
+with wildedge.llm_api(model="openai/gpt-4o-mini", provider="openrouter") as call:
+    call.response(data)  # LLM calls made with plain HTTP clients
+```
 
-`init(...)` is a convenience wrapper for `WildEdge(...)` + `instrument(...)`.
+One client per process: `wildedge run`, `init()`, and the module-level calls
+all share it, and `init()` without `dsn` reuses whatever already exists.
+Without a DSN everything is a silent no-op, so dev and CI need no
+configuration. See [Deployment](https://github.com/wild-edge/wildedge-python/blob/main/docs/deployment.md)
+for the full contract.
 ## Supported integrations
 
 **On-device**
@@ -90,6 +95,10 @@ If no DSN is configured, the client becomes a no-op and logs a warning.
 | `anthropic` | [anthropic_example.py](https://github.com/wild-edge/wildedge-python/blob/main/examples/anthropic_example.py) |
 | `openai` | [openai_example.py](https://github.com/wild-edge/wildedge-python/blob/main/examples/openai_example.py) |
 
+Calling an LLM API with a plain HTTP client instead of these libraries? Use
+[`wildedge.llm_api()`](https://github.com/wild-edge/wildedge-python/blob/main/docs/llm_api.md):
+[llm_api_example.py](https://github.com/wild-edge/wildedge-python/blob/main/examples/llm_api_example.py).
+
 **Hub tracking**
 
 Pass `hubs=` to track model download provenance. Hubs are framework-agnostic and can be combined with any integration.
@@ -135,6 +144,12 @@ Report security and privacy issues to: support@wildedge.dev
 
 ## Links
 
+- [Deployment guide](https://github.com/wild-edge/wildedge-python/blob/main/docs/deployment.md)
+- [Manual tracking](https://github.com/wild-edge/wildedge-python/blob/main/docs/manual-tracking.md)
+- [LLM API tracking](https://github.com/wild-edge/wildedge-python/blob/main/docs/llm_api.md)
 - [Compatibility Matrix](https://github.com/wild-edge/wildedge-python/blob/main/docs/compatibility.md)
-- [Changelog](https://github.com/wild-edge/wildedge-python/releases)
+- [Changelog](https://github.com/wild-edge/wildedge-python/blob/main/CHANGELOG.md)
 - [License](https://github.com/wild-edge/wildedge-python/blob/main/LICENSE)
+
+Each GitHub release ships `llms.txt` and `llms-full.txt`: the full
+documentation for that exact version in one file, built for AI assistants.

docs/llm_api.md

@@ -41,6 +41,9 @@ full response payload, dict or SDK object, OpenAI shape
 (`usage.prompt_tokens`, `choices[0].finish_reason`) or Anthropic shape
 (`usage.input_tokens`, top-level `stop_reason`).
 
+Runnable version: [examples/llm_api_example.py](../examples/llm_api_example.py),
+stdlib urllib against OpenRouter, no client library at all.
+
 ## Recording pieces individually
 
 When you do not have a full response payload, set what you know:

examples/agentic_example.py

@@ -26,7 +26,7 @@
 
 import wildedge
 
-we = wildedge.init(
+wildedge.init(
     app_version="1.0.0",
     integrations="openai",
 )
@@ -96,7 +96,7 @@ def calculator(expression: str) -> str:
 
 
 def call_tool(name: str, arguments: dict) -> str:
-    with we.span(
+    with wildedge.span(
         kind="tool",
         name=name,
         input_summary=json.dumps(arguments)[:200],
@@ -108,7 +108,7 @@ def call_tool(name: str, arguments: dict) -> str:
 
 def retrieve_context(query: str) -> str:
     """Fetch relevant context from the vector store (~120ms)."""
-    with we.span(
+    with wildedge.span(
         kind="retrieval",
         name="vector_search",
         input_summary=query[:200],
@@ -125,7 +125,7 @@ def run_agent(task: str, step_index: int, messages: list) -> str:
     messages.append({"role": "user", "content": f"{task}\n\nContext: {context}"})
 
     while True:
-        with we.span(
+        with wildedge.span(
             kind="agent_step",
             name="reason",
             step_index=step_index,
@@ -172,10 +172,10 @@ def run_agent(task: str, step_index: int, messages: list) -> str:
 system_prompt = "You are a helpful assistant. Use tools when needed."
 messages = [{"role": "system", "content": system_prompt}]
 
-with we.trace(agent_id="demo-agent", run_id=str(uuid.uuid4())):
+with wildedge.trace(agent_id="demo-agent", run_id=str(uuid.uuid4())):
     for i, task in enumerate(TASKS, start=1):
         print(f"\nTask {i}: {task}")
         reply = run_agent(task, step_index=i, messages=messages)
         print(f"Reply: {reply}")
 
-we.flush()
+wildedge.flush()

examples/anthropic_example.py

@@ -18,7 +18,7 @@
 
 import wildedge
 
-client = wildedge.init(
+wildedge.init(
     app_version="1.0.0",  # uses WILDEDGE_DSN if set; otherwise no-op
     integrations="anthropic",
 )
@@ -44,5 +44,5 @@
             print(event.delta.text, end="", flush=True)
     print("\n")
 
-client.flush()
+wildedge.flush()
 print("Done. Events flushed to WildEdge.")

examples/attachments_example.py

@@ -26,7 +26,7 @@ def redact(attachments: list[Attachment]) -> list[Attachment]:
     return [a for a in attachments if a.content_type != "application/secret"]
 
 
-client = wildedge.init(
+wildedge.init(
     app_version="1.0.0",
     attachments_enabled=True,
     max_attachments_per_inference=5,
@@ -35,7 +35,7 @@ def redact(attachments: list[Attachment]) -> list[Attachment]:
     attachment_filter=redact,
 )
 
-handle = client.register_model(
+handle = wildedge.register_model(
     object(),
     model_id="doc-classifier-v1",
     source="local",
@@ -59,4 +59,4 @@ def redact(attachments: list[Attachment]) -> list[Attachment]:
 print(f"tracked inference {inference_id[:8]}… with 2 attachments")
 
 # Bytes upload in the background; flush/close lets buffered events drain.
-client.close()
+wildedge.flush()

examples/feedback_example.py

@@ -21,14 +21,14 @@
 
 CONFIDENCE_THRESHOLD = 0.6
 
-client = wildedge.init(
+wildedge.init(
     app_version="1.0.0",  # uses WILDEDGE_DSN if set; otherwise no-op
     integrations="timm",
 )
 
 model = timm.create_model("resnet18", pretrained=True)
 model.eval()
-handle = client.register_model(
+handle = wildedge.register_model(
     model
 )  # auto-instrumented already; returns existing handle
 

examples/gguf_example.py

@@ -12,7 +12,7 @@
 
 import wildedge
 
-client = wildedge.init(
+wildedge.init(
     app_version="1.0.0",  # uses WILDEDGE_DSN if set; otherwise no-op
     integrations="gguf",
     hubs=["huggingface"],

examples/llm_api_example.py

@@ -0,0 +1,63 @@
+# /// script
+# requires-python = ">=3.10"
+# dependencies = ["wildedge-sdk"]
+#
+# [tool.uv.sources]
+# wildedge-sdk = { path = "..", editable = true }
+# ///
+"""Track LLM calls made over plain HTTP with wildedge.llm_api().
+
+No openai or anthropic client library involved: requests go through stdlib
+urllib against OpenRouter's OpenAI-compatible endpoint, and llm_api() records
+the same inference events the integrations emit (tokens, TTFT, stop reason),
+correlated into the surrounding trace and spans.
+
+Run with: uv run llm_api_example.py
+Requires: OPENROUTER_API_KEY environment variable. Set WILDEDGE_DSN to send events.
+"""
+
+import json
+import os
+import urllib.request
+import uuid
+
+import wildedge
+
+wildedge.init(app_version="1.0.0")  # uses WILDEDGE_DSN if set; otherwise no-op
+
+URL = "https://openrouter.ai/api/v1/chat/completions"
+MODEL = "openai/gpt-4o-mini"
+
+
+def chat(prompt: str) -> dict:
+    request = urllib.request.Request(
+        URL,
+        data=json.dumps(
+            {"model": MODEL, "messages": [{"role": "user", "content": prompt}]}
+        ).encode(),
+        headers={
+            "Authorization": f"Bearer {os.getenv('OPENROUTER_API_KEY')}",
+            "Content-Type": "application/json",
+        },
+    )
+    with urllib.request.urlopen(request, timeout=120) as response:
+        return json.load(response)
+
+
+PROMPTS = [
+    "What is on-device AI in one sentence?",
+    "Name three edge inference runtimes.",
+]
+
+with wildedge.trace(agent_id="llm-api-example", run_id=str(uuid.uuid4())):
+    for step, prompt in enumerate(PROMPTS):
+        with wildedge.span(kind="agent_step", name="ask", step_index=step):
+            with wildedge.llm_api(
+                model=MODEL, provider="openrouter", prompt=prompt
+            ) as call:
+                data = chat(prompt)
+                call.response(data)
+        print(f"Q: {prompt}\nA: {data['choices'][0]['message']['content']}\n")
+
+wildedge.flush()
+print("Done. Events flushed to WildEdge.")