QT/sure
1
0
Fork 0
mirror of https://github.com/we-promise/sure.git synced 2026-05-07 12:54:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Rebase PR #784 and fix OpenAI model/chat regressions (#1384)

Browse Source 
* Wire conversation history through OpenAI responses API

* Fix RuboCop hash brace spacing in assistant tests

* Pipelock ignores

* Batch fixes

---------

Co-authored-by: sokiee <sokysrm@gmail.com>
This commit is contained in:
Juan José Mata
2026-04-15 18:45:24 +02:00
committed by GitHub
parent 53ea0375db
commit 7b2b1dd367
24 changed files with 937 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
.env.local.example
View File

@@ -28,8 +28,22 @@ TWELVE_DATA_API_KEY =
OPENAI_ACCESS_TOKEN =
OPENAI_URI_BASE =
OPENAI_MODEL =
# OPENAI_REQUEST_TIMEOUT: Request timeout in seconds (default: 60)
# OPENAI_SUPPORTS_PDF_PROCESSING: Set to false for endpoints without vision support (default: true)
# LLM token budget. Applies to ALL outbound LLM calls: chat history,
# auto-categorize, merchant detection, provider enhancer, PDF processing.
# Defaults to Ollama's historical 2048-token baseline so small local models
# work out of the box — raise explicitly for cloud or larger-context models.
# LLM_CONTEXT_WINDOW = 2048 # Total tokens the model will accept
# LLM_MAX_RESPONSE_TOKENS = 512 # Reserved for the model's reply
# LLM_MAX_HISTORY_TOKENS = # Derived if unset (context - response - system_reserve)
# LLM_SYSTEM_PROMPT_RESERVE = 256 # Tokens reserved for the system prompt
# LLM_MAX_ITEMS_PER_CALL = 25 # Upper bound on auto-categorize / merchant batches
# OpenAI-compatible capability flags (custom/self-hosted providers)
# OPENAI_REQUEST_TIMEOUT = 60 # HTTP timeout in seconds; raise for slow local models
# OPENAI_SUPPORTS_PDF_PROCESSING = true # Set to false for endpoints without vision support
# OPENAI_SUPPORTS_RESPONSES_ENDPOINT = # true to force Responses API on custom providers
# LLM_JSON_MODE = # auto | strict | json_object | none
# (example: LM Studio/Docker config) OpenAI-compatible API endpoint config
# OPENAI_URI_BASE = http://host.docker.internal:1234/