5 Commits
Author SHA1 Message Date
nanobot 59b4abaa14 chore: bump model defaults to Opus 4.7, Sonnet 4.6
Build Nanobot OAuth / build (pull_request) Successful in 7m4s
Build Nanobot OAuth / cleanup (pull_request) Has been skipped
Build Nanobot OAuth / build (push) Successful in 2m48s
Build Nanobot OAuth / cleanup (push) Successful in 1s
- Default model: anthropic/claude-opus-4-5 → anthropic/claude-opus-4-7
- Quota switcher: claude-opus-4-6 → claude-opus-4-7
- Update all provider defaults and test fixtures
- Update comments/docstrings referencing old model names
- Claude Opus 4.7 released 2026-04-16, same pricing as 4.6
2026-04-17 02:53:08 +02:00
nanobot 790bdd6b8a fix: remove dead code, fix JSON parsing, add facts validation
Build Nanobot OAuth / build (pull_request) Successful in 6m30s
Build Nanobot OAuth / cleanup (pull_request) Has been skipped
2026-03-04 14:06:44 +01:00
nanobot b25c09f5ed feat: extract facts with main agent LLM, bypass mem0 GPT-nano
Build Nanobot OAuth / build (pull_request) Successful in 6m5s
Build Nanobot OAuth / cleanup (pull_request) Has been skipped
Uses the main agent's existing LLM provider to extract facts from
conversations, then stores them with infer=False — bypassing mem0's
default GPT-nano call.

- extract_facts(): sends conversation to provider.chat() with one-liner prompt
- store_facts(): stores each fact via mem0 with infer=False
- consolidate(): calls extract_facts + store_facts instead of add_conversation
2026-03-04 13:50:02 +01:00
nanobotandcode-server bd03c151da Increase subagent max_iterations from 15 to 50 (#3)
Co-authored-by: nanobot <nanobot@wylab.me>
Co-committed-by: nanobot <nanobot@wylab.me>
2026-02-28 23:17:13 +00:00
nanobotandcode-server c4e78f4d80 feat: add optional model override for spawn subagents (#1)
Co-authored-by: Nanobot Agent <nanobot@wylab.me>
Co-committed-by: Nanobot Agent <nanobot@wylab.me>
2026-02-28 23:17:13 +00:00