From 60ec835cc3686a4487e45176c57b26f4f422566e Mon Sep 17 00:00:00 2001 From: MrSphay Date: Sun, 5 Jul 2026 23:17:47 +0200 Subject: [PATCH] docs: record tagged tool parser fix --- docs/agent-handoff.md | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/docs/agent-handoff.md b/docs/agent-handoff.md index 6a5c494..43c00d3 100644 --- a/docs/agent-handoff.md +++ b/docs/agent-handoff.md @@ -19,6 +19,11 @@ Last updated: 2026-07-05 ## Latest Completed Work +- Issue #76 / PR #77 fixed a second local-model protocol leak: ChatML-style output such as `<|tool_call>call:get_evidence{query:"...",limit:5}` was previously treated as user-facing text. Merge commit: `7f140021f037cbc351c9a3b39a5eb3610bfc4939`. +- The controlled agent now parses bounded tagged calls into the normal allowlisted tool path without `eval`, recognizes tagged JSON envelopes, and treats malformed protocol-like output as a repairable protocol error. Tool tags are never accepted as final Telegram text. +- The exact observed Russia-query format and a malformed-tag variant are regression fixtures. PR runs 935-936 and production runs 937-939 passed. +- The registry image was redeployed to Dockge. Live health reported `running/healthy`, Telegram agent enabled with 14 tools, dynamic DAVE presence enabled, encrypted profile preserved, and no sweep error. + - Canonical repository: `https://git.wilkensxl.de/Code-Inc/intelligence-terminal` - LiteLLM implementation merge: `5c4bf80eb0c19bd59080f5432a2a344798d7a3ce` - Merged PR: `#48 feat: add LiteLLM provider and publish Code-Inc image`