* signals: port to layered taxonomy with dual-emit OTel
Made-with: Cursor
* fix: silence collapsible_match clippy lint (rustc 1.95)
Made-with: Cursor
* test: parity harness for rust vs python signals analyzer
Validates the brightstaff signals port against the katanemo/signals Python
reference on lmsys/lmsys-chat-1m. Adds a signals_replay bin emitting python-
compatible JSON, a pyarrow-based driver (bypasses the datasets loader pickle
bug on python 3.14), a 3-tier comparator, and an on-demand workflow_dispatch
CI job.
Made-with: Cursor
* Remove signals test from the gitops flow
* style: format parity harness with black
Made-with: Cursor
* signals: group summary by taxonomy, factor misalignment_ratio
Addresses #903 review feedback from @nehcgs:
- generate_summary() now renders explicit Interaction / Execution /
Environment headers so the paper taxonomy is visible at a glance,
even when no signals fired in a given layer. Quality-driving callouts
(high misalignment rate, looping detected, escalation requested) are
appended after the layer summary as an alerts tail.
- repair_ratio (legacy taxonomy name) renamed to misalignment_ratio
and factored into a single InteractionSignals::misalignment_ratio()
helper so assess_quality and generate_summary share one source of
truth instead of recomputing the same divide twice.
Two new unit tests pin the layer headers and the (sev N) severity
suffix. Parity with the python reference is preserved at the Tier-A
level (per-type counts + overall_quality); only the human-readable
summary string diverges, which the parity comparator already classifies
as Tier-C.
Made-with: Cursor
Update all GitHub Actions workflows and Dockerfiles to use Python 3.14
as the default version. Remove the upper bound on requires-python in
model_choice_with_test_harness to allow 3.14+. The CLI's
requires-python stays at >=3.10 for broad compatibility.
* cleaning up plano cli commands
* adding support for wildcard model providers
* fixing compile errors
* fixing bugs related to default model provider, provider hint and duplicates in the model provider list
* fixed cargo fmt issues
* updating tests to always include the model id
* using default for the prompt_gateway path
* fixed the model name, as gpt-5-mini-2025-08-07 wasn't in the config
* making sure that all aliases and models match the config
* fixed the config generator to allow for base_url providers LLMs to include wildcard models
* re-ran the models list utility and added a shell script to run it
* updating docs to mention wildcard model providers
* updated provider_models.json to yaml, added that file to our docs for reference
* updating the build docs to use the new root-based build
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
* fixed reasoning failures
* adding debugging
* made several fixes for transmission isses for SSeEvents, incomplete handling of json types by anthropic, and wrote a bunch of tests
* removed debugging from supervisord.conf
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
* agents framework demo
* more changes
* add more changes
* pending changes
* fix tests
* fix more
* rebase with main and better handle error from mcp
* add trace for filters
* add test for client error, server error and for mcp error
* update schema validate code and rename kind => type in agent_filter
* fix agent description and pre-commit
* fix tests
* add provider specific request parsing in agents chat
* fix precommit and tests
* cleanup demo
* update readme
* fix pre-commit
* refactor tracing
* fix fmt
* fix: handle MessageContent enum in responses API conversion
- Update request.rs to handle new MessageContent enum structure from main
- MessageContent can now be Text(String) or Items(Vec<InputContent>)
- Handle new InputItem variants (ItemReference, FunctionCallOutput)
- Fixes compilation error after merging latest main (#632)
* address pr feedback
* fix span
* fix build
* update openai version
* first commit with tests to enable state mamangement via memory
* fixed logs to follow the conversational flow a bit better
* added support for supabase
* added the state_storage_v1_responses flag, and use that to store state appropriately
* cleaned up logs and fixed issue with connectivity for llm gateway in weather forecast demo
* fixed mixed inputs from openai v1/responses api (#632)
* fixed mixed inputs from openai v1/responses api
* removing tracing from model-alias-rouing
* handling additional input types from openairs
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
* resolving PR comments
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
* making first commit. still need to work on streaming respones
* making first commit. still need to work on streaming respones
* stream buffer implementation with tests
* adding grok API keys to workflow
* fixed changes based on code review
* adding support for bedrock models
* fixed issues with translation to claude code
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
* adding function_calling functionality via rust
* fixed rendered YAML file
* removed model_server from envoy.template and forwarding traffic to bright_staff
* fixed bugs in function_calling.rs that were breaking tests. All good now
* updating e2e test to clean up disk usage
* removing Arch* models to be used as a default model if one is not specified
* if the user sets arch-function base_url we should honor it
* fixing demos as we needed to pin to a particular version of huggingface_hub else the chatbot ui wouldn't build
* adding a constant for Arch-Function model name
* fixing some edge cases with calls made to Arch-Function
* fixed JSON parsing issues in function_calling.rs
* fixed bug where the raw response from Arch-Function was re-encoded
* removed debug from supervisord.conf
* commenting out disk cleanup
* adding back disk space
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
* first commit to get Bedrock Converse API working. Next commit support for streaming and binary frames
* adding translation from BedrockBinaryFrameDecoder to AnthropicMessagesEvent
* Claude Code works with Amazon Bedrock
* added tests for openai streaming from bedrock
* PR comments fixed
* adding support for bedrock in docs as supported provider
* cargo fmt
* revertted to chatgpt models for claude code routing
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local>
Co-authored-by: Adil Hafeez <adil.hafeez@gmail.com>
* fixed for claude code routing. first commit
* removing redundant enum tags for cache_control
* making sure that claude code can run via the archgw cli
* fixing broken config
* adding a README.md and updated the cli to use more of our defined patterns for params
* fixed config.yaml
* minor fixes to make sure PR is clean. Ready to ship
* adding claude-sonnet-4-5 to the config
* fixes based on PR
* fixed alias for README
* fixed 400 error handling tests, now that we write temperature to 1.0 for GPT-5
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-257.local>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local>
* adding support for model aliases in archgw
* fixed PR based on feedback
* removing README. Not relevant for PR
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-136.local>
* pushing draft PR
* transformations are working. Now need to add some tests next
* updated tests and added necessary response transformations for Anthropics' message response object
* fixed bugs for integration tests
* fixed doc tests
* fixed serialization issues with enums on response
* adding some debug logs to help
* fixed issues with non-streaming responses
* updated the stream_context to update response bytes
* the serialized bytes length must be set in the response side
* fixed the debug statement that was causing the integration tests for wasm to fail
* fixing json parsing errors
* intentionally removing the headers
* making sure that we convert the raw bytes to the correct provider type upstream
* fixing non-streaming responses to tranform correctly
* /v1/messages works with transformations to and from /v1/chat/completions
* updating the CLI and demos to support anthropic vs. claude
* adding the anthropic key to the preference based routing tests
* fixed test cases and added more structured logs
* fixed integration tests and cleaned up logs
* added python client tests for anthropic and openai
* cleaned up logs and fixed issue with connectivity for llm gateway in weather forecast demo
* fixing the tests. python dependency order was broken
* updated the openAI client to fix demos
* removed the raw response debug statement
* fixed the dup cloning issue and cleaned up the ProviderRequestType enum and traits
* fixing logs
* moved away from string literals to consts
* fixed streaming from Anthropic Client to OpenAI
* removed debug statement that would likely trip up integration tests
* fixed integration tests for llm_gateway
* cleaned up test cases and removed unnecessary crates
* fixing comments from PR
* fixed bug whereby we were sending an OpenAIChatCompletions request object to llm_gateway even though the request may have been AnthropicMessages
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-4.local>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-9.local>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-10.local>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-41.local>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-136.local>
* fixed issue with groq LLMs that require the openai in the /v1/chat/completions path. My first change
* updated the GH actions with keys for Groq
* adding missing groq API keys
* add llama-3.2-3b-preview to the model based on addin groq to the demo
---------
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
* Fix llm_routing provider element
We replaced provider with provider_interface to make it more clear to developers about provider api/backend being used. During that upgrade we removed support for mistral in provider to encourage developers to start using provider_interface. But this demo was not updated to use provider_interface as it was using mistral. This code change fixes it by replacing provider with provider_interface.
Signed-off-by: Adil Hafeez <adil.hafeez@gmail.com>
* fix the path
* move
* add more details
* fix
* Apply suggestions from code review
* fix
* fix
---------
Signed-off-by: Adil Hafeez <adil.hafeez@gmail.com>
* Some fixes on model server
* Remove prompt_prefilling message
* Fix logging
* Fix poetry issues
* Improve logging and update the support for text truncation
* Fix tests
* Fix tests
* Fix tests
* Fix modelserver tests
* Update modelserver tests
