@respan/cli 0.8.0 → 0.9.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -257,13 +257,19 @@ If a Priority 1 framework is found, use its instrumentation. Do NOT also add Pri
257
257
 
258
258
  **Priority 2 — Direct LLM SDKs** (only if no P1 framework covers this provider):
259
259
 
260
- | Library | Python package | JS/TS package | Respan instrumentation (Python) | Respan instrumentation (JS/TS) | Docs |
261
- |---------|---------------|---------------|--------------------------------|-------------------------------|------|
262
- | OpenAI SDK | \`openai\` | \`openai\` | \`respan-instrumentation-openai\` | \`@respan/instrumentation-openai\` | [docs](https://respan.ai/docs/integrations/openai-sdk.md) |
263
- | Anthropic SDK | \`anthropic\` | \`@anthropic-ai/sdk\` | \`respan-instrumentation-anthropic\` | \`@respan/instrumentation-anthropic\` | [docs](https://respan.ai/docs/integrations/anthropic.md) |
264
- | Google Gen AI | \`google-genai\` | — | via OpenInference | — | [docs](https://respan.ai/docs/integrations/google-genai.md) |
265
- | LiteLLM | \`litellm\` | — | via exporter | — | [docs](https://respan.ai/docs/integrations/litellm.md) |
266
- | Amazon Bedrock | \`boto3\` | — | via OpenInference | — | [docs](https://respan.ai/docs/integrations/aws-bedrock.md) |
260
+ These are **auto-instrumented** — just \`Respan()\` / \`new Respan()\`, no extra packages needed:
261
+
262
+ | Library | Python package | JS/TS package | Docs |
263
+ |---------|---------------|---------------|------|
264
+ | OpenAI SDK | \`openai\` | \`openai\` | [docs](https://respan.ai/docs/integrations/openai-sdk.md) |
265
+ | Anthropic SDK | \`anthropic\` | \`@anthropic-ai/sdk\` | [docs](https://respan.ai/docs/integrations/anthropic.md) |
266
+ | Azure OpenAI | \`openai\` (azure config) | \`openai\` | [docs](https://respan.ai/docs/integrations/providers/azure.md) |
267
+ | Google Vertex AI | \`google-cloud-aiplatform\` | — | [docs](https://respan.ai/docs/integrations/vertex-ai.md) |
268
+ | AWS Bedrock | \`boto3\` | — | [docs](https://respan.ai/docs/integrations/aws-bedrock.md) |
269
+ | Cohere | \`cohere\` | — | [docs](https://respan.ai/docs/integrations/providers/cohere.md) |
270
+ | Together AI | \`together\` | — | [docs](https://respan.ai/docs/integrations/together-ai.md) |
271
+
272
+ **Note:** LiteLLM in JS uses the OpenAI-compatible API, so the OpenAI auto-instrument covers it. For Python LiteLLM, see [LiteLLM guide](https://respan.ai/docs/integrations/litellm.md). For Google GenAI (\`@google/genai\`), see [Google GenAI guide](https://respan.ai/docs/integrations/google-genai.md).
267
273
 
268
274
  **1c. Read the actual code and understand the workflow:**
269
275
 
@@ -348,36 +354,50 @@ Wait for user confirmation before proceeding.
348
354
 
349
355
  ### 3. Implement
350
356
 
351
- **a) Install packages** — run the install command with exact versions.
357
+ **a) Install packages:**
358
+
359
+ For direct LLM SDKs (Priority 2) — just the core SDK:
360
+ \`\`\`bash
361
+ # Python
362
+ pip install respan-ai
363
+
364
+ # TypeScript
365
+ npm install @respan/respan
366
+ \`\`\`
367
+
368
+ For agent frameworks (Priority 1) — also install the instrumentor. Check the docs link in the table above for the exact packages.
352
369
 
353
370
  **b) Add initialization code** — at the top of the entrypoint, before any LLM client is created:
354
371
 
355
- TypeScript:
372
+ For **direct LLM SDKs** (auto-instrumented):
373
+ \`\`\`python
374
+ # Python
375
+ from respan import Respan
376
+ Respan()
377
+ \`\`\`
356
378
  \`\`\`typescript
379
+ // TypeScript
357
380
  import { Respan } from "@respan/respan";
358
- import { OpenAIInstrumentor } from "@respan/instrumentation-openai";
359
-
360
- const respan = new Respan({
361
- appName: "<project-name>",
362
- instrumentations: [new OpenAIInstrumentor()],
363
- });
381
+ const respan = new Respan();
364
382
  await respan.initialize();
365
383
  \`\`\`
366
384
 
367
- Python:
385
+ For **agent frameworks** (explicit instrumentor — fetch the docs URL from the table for the exact pattern):
368
386
  \`\`\`python
387
+ # Python example (OpenAI Agents)
369
388
  from respan import Respan
370
- from respan_instrumentation_openai import OpenAIInstrumentor
371
-
372
- respan = Respan(
373
- app_name="<project-name>",
374
- instrumentations=[OpenAIInstrumentor()],
375
- )
389
+ from respan_instrumentation_openai_agents import OpenAIAgentsInstrumentor
390
+ Respan(instrumentations=[OpenAIAgentsInstrumentor()])
391
+ \`\`\`
392
+ \`\`\`typescript
393
+ // TypeScript example (OpenAI Agents)
394
+ import { Respan } from "@respan/respan";
395
+ import { OpenAIAgentsInstrumentor } from "@respan/instrumentation-openai-agents";
396
+ const respan = new Respan({ instrumentations: [new OpenAIAgentsInstrumentor()] });
397
+ await respan.initialize();
376
398
  \`\`\`
377
399
 
378
- **c) Add workflow wrappers** — if the user approved them in the plan.
379
-
380
- For integration-specific init patterns, fetch the docs URL from the table above.
400
+ **c) Add workflow wrappers** — if the user chose structured traces in the plan.
381
401
 
382
402
  ### 4. Verify
383
403
 
@@ -3976,5 +3976,5 @@
3976
3976
  ]
3977
3977
  }
3978
3978
  },
3979
- "version": "0.8.0"
3979
+ "version": "0.9.0"
3980
3980
  }
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@respan/cli",
3
- "version": "0.8.0",
3
+ "version": "0.9.0",
4
4
  "description": "Respan CLI - manage your LLM observability from the command line",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",