Repository navigation
Move the GPT-4 and GPT-5 calls to Luna 6 with low reasoning - #656
Conversation
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
- Text-only Chat Completions calls (zep-ingest OpenAILLM, chunking examples, quickstart and dashboard agents, AutoGen notebook) use gpt-6-luna and reasoning_effort "low". OpenAICompatibleLLM does not send reasoning_effort unless the caller sets it. - Tool calls use the Responses API with low reasoning: the LangGraph notebook (ChatOpenAI use_responses_api), the OpenAI Agents SDK example (ModelSettings reasoning), and the ElevenLabs proxy, which now serves /v1/responses and restores reasoning items in tool loops. - Add mocked tests for zep-ingest, the ElevenLabs proxy, and the Go chunking example. Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Use the Responses API in each framework. Keep reasoning data across tool turns where supported. Co-Authored-By: Daniel Chalef <daniel@getzep.com>
The tool-capable LangGraph, Vercel AI, and Mastra examples use the Responses API with low reasoning effort. The text-only chunking example uses Chat Completions with reasoning_effort low. Mocked tests check the model, the endpoint, the reasoning setting, and the replay of reasoning items in tool loops. Co-Authored-By: Daniel Chalef <daniel@getzep.com>
…roxy - Forward instructions and previous_response_id without change, and append the Zep context only when Zep returns context. Do not add a default persona. - Limit the reasoning item map to 1,000 calls and expire each entry after one hour. - Add mocked tests for the no-context path, previous_response_id, and the map limits. Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Tool calls use the Responses API with low reasoning. The examples use stateless requests for Zero Data Retention. Mocked tests verify the tool round trips. Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Raise the LangChain core minimum to match LangGraph 1.2.5. Co-Authored-By: Daniel Chalef <daniel@getzep.com>
The adapters replay saved reasoning items before each matching function call. CrewAI examples do not request encrypted reasoning because its tool loop does not replay those items. Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Tool calls replay encrypted reasoning before each matching function call. The examples use the Responses API with low reasoning and store=False. Co-Authored-By: Daniel Chalef <daniel@getzep.com>
The Strands example now captures and replays encrypted reasoning without response IDs. The tool-loop tests cover two turns and parallel calls. Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
The example now uses an explicit reasoning profile. The requests include encrypted reasoning and set server-side storage to false. Co-Authored-By: Daniel Chalef <daniel@getzep.com>
|
I'll fix CI failures and address comments from users with write access that start with 'Devin'.
|
|
Review the following changes in direct dependencies. Learn more about Socket for GitHub.
|
There was a problem hiding this comment.
-
Critical — Responses replies break CLI output and memory persistence
examples/typescript/langgraph/agent.ts:29
Enabling Responses produces structured content blocks, but the CLI still interpolateslastAIMessage.content, andZepMemory.convertToZepMessage()only casts that content tostring. Replies display as[object Object], and persistence sends an array where Zep expects text. UselastAIMessage.textfor display and normalize content before persistence. Add coverage through the CLI/persistence path. -
Critical — Response continuations reference responses that were never stored
examples/python/elevenlabs-zep-example/llm-proxy/proxy_server.py:347
Every request forcesstore=False, whileprevious_response_idis forwarded unchanged. A client continuing a response produced by this proxy cannot resolve that response on OpenAI’s server. The reasoning cache cannot repair this because restoration requires function-call items ininput, whereas continuations can contain only tool outputs. Either reconstruct and replay the complete history locally or support stored responses explicitly. Test two consecutive requests usingprevious_response_id. -
Critical — Existing model overrides receive unsupported reasoning settings
ingestion/src/zep_ingest/llm/openai.py:35–46
Existing calls such asOpenAILLM(model="gpt-4o")now sendreasoning_effort="low", causing requests to non-reasoning models to fail. Requiring callers to discover and addreasoning_effort=Nonebreaks the existing override API. Apply the implicit default only to supported models, preserving explicit overrides, and add a regression test for a non-reasoning model.
Review was static; runtime dependencies were unavailable, and no network access was attempted.
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
There was a problem hiding this comment.
Devin Review found 4 findings. Devin automatically fixed all 4 findings.
Fixed by Devin (4)
- Example adapters retain every tool call — The adapters now remove reasoning entries when their matching tool calls leave the input history. The regression tests cover a new conversation and preserve the existing multi-round replay checks.
- Tool continuations duplicate user turns — The proxy now persists a user turn only when it is the final input item. A tool continuation can replay an earlier user turn without adding it to Zep again. The mocked tests cover both the continuation and a later user turn.
- Previous response IDs break continuations — The stateless proxy now rejects previous_response_id with HTTP 400 before any Zep or OpenAI call. Its documentation and tests require full input history instead of advertising a server-side continuation that cannot work with store=False.
- Nonreasoning model overrides fail — The automatic default now applies low reasoning only to Luna. Other model overrides omit the parameter unless the caller sets it. The ingestion checks pass.
Co-Authored-By: Daniel Chalef <daniel@getzep.com>
|
The proxy persists a user turn only when it is the final input item. The tool-continuation test checks that the prior user turn is not added again. This change is in 5f33c86, with the helper name made explicit in 17f8316. The example adapters now remove reasoning entries when the matching tool calls leave the input history. The new-conversation tests check that the maps are cleared. This change is in ee3937f, with the lifetime stated in the adapter docstrings in 17f8316. |
Summary
This PR moves active GPT-4.x, GPT-4o, and GPT-5.x calls and defaults to
gpt-6-lunawith explicit low reasoning. It replaces #645.reasoning_effort="low". Custom OpenAI-compatible providers remain neutral unless configured.Luna tool calls use the Responses API because Chat Completions does not support these calls with low reasoning. The adapters request encrypted reasoning and replay each item before its matching function call. LiveKit keeps its native stateful Responses path; this PR does not add a stateless LiveKit adapter.
The ElevenLabs proxy uses stateless Responses requests. Each request must include the full input history. Requests with
previous_response_idreturn HTTP 400 because the proxy does not store responses on the OpenAI server.Historical benchmark results, datasets, frozen fixtures, notebook outputs, and changelog history remain unchanged. The unsupported Community Edition configuration in
legacy/also remains unchanged.Tests
make allcheck passed with 682 tests passed and 2 skipped.go vet,go test, andgolangci-lint.Dependency audits still report advisories on unchanged Zod and LangSmith versions. This PR does not upgrade those dependencies.