{"version":"2.1.265","anchor":"new-tether-request-threading-protocol-for-api-continuity","canonical_anchor":"new-tether-request-threading-protocol-for-api-continuity","heading":"New 'tether' protocol threads API requests across turns (off by default)","tier":"soon","area":"API Protocol","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265\/e\/new-tether-request-threading-protocol-for-api-continuity","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265","markdown":"### New 'tether' protocol threads API requests across turns (off by default)\n\nAn off-by-default 'tether' subsystem lets assistant turns continue a previous server-side thread instead of starting fresh, with telemetry and echo auditing\n\n**Unclear.** Nothing has been read about whether tengu_curious_tower or tengu_curious_tower_stateless_models is on or off for any account, so it's unclear whether this is active anywhere yet.\n\n**What**\n\n- A new subsystem decides, per assistant turn, whether an API request should continue a previous server-side \"thread\" (`previous_message_id`) or start a new one. It tracks per-agent thread state, retries on thread-related errors (`thread_not_found`, `thread_fingerprint_mismatch`, `thread_already_continued`), and falls back to stateless mode when the server rejects thread continuation. This feature is gated and off by default.\n\n- Three new telemetry events were added for it: one fired when deciding to create\/continue a thread, one on the final outcome of the live request, and one (\"echo audit\") auditing divergence between sent and echoed conversation turns.\n\n- The echo-audit piece compares the message content sent versus what the server echoed back, classifying differences such as reordered, turn_split, turn_dropped, added\/dropped tool_use, tool_name_changed, or caller_dropped, and reports them via `tengu_tether_echo_audit`.\n\n**Why** Threading requests server-side can reduce redundant context sent per turn, but only works if server and client stay in sync; the echo-audit and outcome telemetry let this be verified and the retry\/fallback logic keeps conversations working even when the server rejects or loses a thread.\n\n- Flag `tengu_curious_tower`: Not enough to say (read for one account on one subscription tier against v2.1.265; this account: no value returned, anonymous baseline: no value returned, compiled default: off)\n- Flag `tengu_curious_tower_stateless_models`: Not enough to say (read for one account on one subscription tier against v2.1.265; this account: no value returned, anonymous baseline: no value returned, compiled default: not a boolean we can read)\n- Area: API Protocol\n- Tier: Nothing to try yet\n- Useful: 5\/5\n- Signal: 5\/5\n- Present in the build but not switched on"}