Compare commits

...

3 Commits

Author SHA1 Message Date
8576a71b4f Merge pull request 'docs: record DAVE profile language fix' (#81) from codex/handoff-profile-language-enforcement into codex/production-intelligence-terminal
All checks were successful
Codex Template Compliance / template-compliance (push) Successful in 7s
Release Dry Run / release-dry-run (push) Successful in 17s
Build / test-and-image (push) Successful in 29s
2026-07-06 07:20:17 +00:00
c0fb9d1e66 docs: record DAVE profile language fix
All checks were successful
Codex Template Compliance / template-compliance (pull_request) Successful in 7s
Build / test-and-image (pull_request) Successful in 25s
2026-07-06 09:18:52 +02:00
59b496aee1 Merge pull request 'fix: enforce Security Manager profile language across DAVE' (#80) from codex/issue-79-profile-language-enforcement into codex/production-intelligence-terminal
All checks were successful
Codex Template Compliance / template-compliance (push) Successful in 7s
Release Dry Run / release-dry-run (push) Successful in 17s
Build / test-and-image (push) Successful in 33s
2026-07-06 07:16:59 +00:00

View File

@@ -19,6 +19,11 @@ Last updated: 2026-07-05
## Latest Completed Work ## Latest Completed Work
- Issue #79 / PR #80 fixed proactive DAVE alerts ignoring the onboarding profile language. The screenshot showed German dynamic presence followed by an English `[AGENT PRIORITY]` alert. Merge commit: `59b496aee19b446a7cdeae74d119778cfbd92d8f`.
- The validated profile language is now an explicit required runtime parameter for direct provider chat, multi-tool reasoning, final-only synthesis, dynamic presence, and proactive sweep analysis. This no longer depends on the model choosing to call `get_security_profile`.
- Server-generated wrappers are localized (`DAVE // PRIORITÄT`, `Belege`, `Werkzeuge`, `AKTIV`). Provider, tool-finalization, and presence language tests were added. PR runs 959-960 and production runs 961-963 passed.
- The registry image was redeployed to Dockge. Live verification read only the encrypted profile language code and confirmed `de`; the container was `running/healthy`, profile persisted, agent and presence enabled, and no sweep error was present.
- Issue #76 / PR #77 fixed a second local-model protocol leak: ChatML-style output such as `<|tool_call>call:get_evidence{query:"...",limit:5}<tool_call|>` was previously treated as user-facing text. Merge commit: `7f140021f037cbc351c9a3b39a5eb3610bfc4939`. - Issue #76 / PR #77 fixed a second local-model protocol leak: ChatML-style output such as `<|tool_call>call:get_evidence{query:"...",limit:5}<tool_call|>` 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 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 exact observed Russia-query format and a malformed-tag variant are regression fixtures. PR runs 935-936 and production runs 937-939 passed.