Skip to content

Fix llama aliases and roleplayed tool calls#101

Merged
VickyXAI merged 1 commit into
BlockRunAI:mainfrom
0xCheetah1:fix/llama-alias-tool-calls
Jul 13, 2026
Merged

Fix llama aliases and roleplayed tool calls#101
VickyXAI merged 1 commit into
BlockRunAI:mainfrom
0xCheetah1:fix/llama-alias-tool-calls

Conversation

@0xCheetah1

Copy link
Copy Markdown
Contributor

Summary

  • Add llama shortcuts for the current free Maverick model and reject unknown bare /model aliases with a local error
  • Broaden roleplayed tool-call detection so free models can recover bare JSON, OpenAI envelopes, Hermes envelopes, and tool_call XML wrappers
  • Add resolver and detector test coverage, including the resolver test in npm test

Tests

  • npx -y -p node@22 npm test

@VickyXAI VickyXAI merged commit 39698a8 into BlockRunAI:main Jul 13, 2026
2 checks passed
VickyXAI pushed a commit that referenced this pull request Jul 13, 2026
…-model tool calls

Lands the open PR queue (#82, #99, #98, #101), each reviewed and hardened
against Franklin's spend-accounting and untrusted-input invariants:
- franklin predict headless prediction mode (#82)
- /market command + agent_talent marketplace tool (#99, rebase of #83)
- broadened free-model tool-call recovery + llama aliases (#101)
- Renovate org preset (#98)

Review hardening: frameUntrusted on all external market/marketplace output;
402 amount bounded before signing ($5/hire backstop + catalog-price cap);
/market run records spend; bare tool-call envelope requires a registered tool
name; predict --json accumulates usage across turns.

Verified: 554/554 local, tsc clean.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants