docs(observability): add Future AGI as a supported OTLP backend#2621
docs(observability): add Future AGI as a supported OTLP backend#2621SuhaniNagpal7 wants to merge 1 commit intoi-am-bee:mainfrom
Conversation
Adds an "Enable Future AGI Observability" steps block to the stable and development observability pages, mirroring the existing Langfuse section. Future AGI exposes an OTLP/HTTP tracer endpoint at https://api.futureagi.com/tracer/v1/traces using x-api-key / x-secret-key auth, so it slots into the Agent Stack collector config without any code changes on the agent side. Also adds a Future AGI Docs link under Additional Resources. Signed-off-by: Suhani Nagpal <suhani@futureagi.com>
dosubot
Bot
added
the
size:M
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds documentation for integrating Future AGI observability into the agent stack, covering both development and stable documentation paths. The reviewer suggested several improvements for consistency and clarity: using literal placeholders for credentials in the YAML configuration to avoid environment variable propagation issues, adding the filter/phoenix processor to the telemetry pipeline to reduce noise, and simplifying the platform start command by removing redundant environment variables.
| collector: | ||
| exporters: | ||
| otlphttp/futureagi: | ||
| endpoint: "https://api.futureagi.com/tracer/v1/traces" | ||
| headers: | ||
| x-api-key: "${FI_API_KEY}" | ||
| x-secret-key: "${FI_SECRET_KEY}" | ||
| pipelines: | ||
| traces: | ||
| receivers: [ otlp ] | ||
| processors: [ memory_limiter, batch ] | ||
| exporters: [ otlphttp/futureagi ] |
There was a problem hiding this comment.
For consistency with the Langfuse section and to avoid potential issues with environment variable propagation to the collector container, it is recommended to use literal placeholders for credentials. Additionally, the filter/phoenix processor should be included in the pipeline to filter out internal instrumentation noise, ensuring cleaner traces in the Future AGI dashboard.
collector:
exporters:
otlphttp/futureagi:
endpoint: "https://api.futureagi.com/tracer/v1/traces"
headers:
x-api-key: "<YOUR_FI_API_KEY>"
x-secret-key: "<YOUR_FI_SECRET_KEY>"
pipelines:
traces:
receivers: [ otlp ]
processors: [ memory_limiter, filter/phoenix, batch ]
exporters: [ otlphttp/futureagi ]
| FI_API_KEY=your_api_key \ | ||
| FI_SECRET_KEY=your_secret_key \ | ||
| agentstack platform start -f config.yaml |
There was a problem hiding this comment.
Since the configuration file now uses placeholders for credentials (matching the Langfuse example), the environment variables can be removed from the start command.
agentstack platform start -f config.yaml
| collector: | ||
| exporters: | ||
| otlphttp/futureagi: | ||
| endpoint: "https://api.futureagi.com/tracer/v1/traces" | ||
| headers: | ||
| x-api-key: "${FI_API_KEY}" | ||
| x-secret-key: "${FI_SECRET_KEY}" | ||
| pipelines: | ||
| traces: | ||
| receivers: [ otlp ] | ||
| processors: [ memory_limiter, batch ] | ||
| exporters: [ otlphttp/futureagi ] |
There was a problem hiding this comment.
For consistency with the Langfuse section and to avoid potential issues with environment variable propagation to the collector container, it is recommended to use literal placeholders for credentials. Additionally, the filter/phoenix processor should be included in the pipeline to filter out internal instrumentation noise, ensuring cleaner traces in the Future AGI dashboard.
collector:
exporters:
otlphttp/futureagi:
endpoint: "https://api.futureagi.com/tracer/v1/traces"
headers:
x-api-key: "<YOUR_FI_API_KEY>"
x-secret-key: "<YOUR_FI_SECRET_KEY>"
pipelines:
traces:
receivers: [ otlp ]
processors: [ memory_limiter, filter/phoenix, batch ]
exporters: [ otlphttp/futureagi ]
| FI_API_KEY=your_api_key \ | ||
| FI_SECRET_KEY=your_secret_key \ | ||
| agentstack platform start -f config.yaml |
There was a problem hiding this comment.
Since the configuration file now uses placeholders for credentials (matching the Langfuse example), the environment variables can be removed from the start command.
agentstack platform start -f config.yaml
1 participant
Summary
Adds an "Enable Future AGI Observability" steps block to both
docs/stable/agent-integration/observability.mdxanddocs/development/agent-integration/observability.mdx, mirroring the existing Langfuse section.Future AGI is an open-source e2e agent engineering and optimization platform that helps you ship self-improving AI agents. It exposes an OTLP/HTTP tracer endpoint at
https://api.futureagi.com/tracer/v1/tracesusingx-api-key/x-secret-keyauth, so it slots into the Agent Stack collector config without any code changes on the agent side.Also adds a Future AGI Docs link under "Additional Resources".
What changed
### Enable Future AGI Observabilityblock with credentials, collectorconfig.yamlsnippet, andagentstack platform start -f config.yamlinstructions.Smoke test
Verified end-to-end against the published Future AGI tracer endpoint:
POST https://api.futureagi.com/tracer/v1/traceswithx-api-key+x-secret-keyheaders →HTTP 200 OK, request-id returned.project_nameresource attribute landed in the Future AGI dashboard under the named project.Test plan
mintlify broken-linkspasses (verified locally — no broken links found)mintlify devboots without MDX errors (verified locally — preview ready, both pages render at 200 with the new section)${FI_API_KEY}vs the literal<auth-string>placeholder used in the Langfuse block — happy to switch to literal for stylistic consistency if preferred)🤖 Generated with Claude Code