{"version":"2.1.319","anchor":"endconversation-tool-description-added","canonical_anchor":"endconversation-tool-description-added","heading":"Revised EndConversation prompt prepared behind a flag","tier":"internal","area":"End Conversation","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319\/e\/endconversation-tool-description-added","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319","markdown":"### Revised EndConversation prompt prepared behind a flag\n\nA revised EndConversation tool prompt and hint wording now sit behind a flag check, with new pinned-value slots to carry it\n\n**Unclear.** Whether the revised text is used depends on a setting whose default is not stated.\n\n**What**\n\nEndConversation is a tool the model can use to end a conversation. This release prepares a revised version of its prompt:\n\n- The EndConversation tool description and its confirmation re-read prompt appear in the bundle with a revised-prompt flag check. The text is largely about background forks and self-harm exclusions.\n\n- The EndConversation hint in the list of deferred tools (tools loaded only when needed) can now use alternative wording: \"for sustained user abuse directed at the assistant, after a warning, or when the user requests it\". The default wording is unchanged.\n\n- New stored feature value slots appear: `endConversationRevisedPrompt`, `connectorUploadFlagWait` and `connectorUploadFlagKeptFor`.\n\n- Two query paths now pass a `sendSideQueryBeta` option through, defaulting to a helper call.\n\nThe stock `ToolSearch` description captured under this release is 953 characters, unchanged from the previous release.\n\n**Why**\n\nThe default prompt is unchanged. The revised wording, which describes when the model may end a conversation, applies only where the flag check turns it on.\n\n- Area: End Conversation\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}