Continuing a server-side conversation thread can now skip resending the system prompt and tools list, with a fallback if the server disagrees
When Claude Code continues an existing server-side conversation thread (a 'tether') and the previously sent data still matches, it can now leave out the system prompt and/or the tools list from the outgoing request, trusting the server to already have them. This is tracked in telemetry as omittedSystem, omittedTools, and omittedBytes.
- If the server rejects a continuation because its fingerprint of the conversation doesn't match, a circuit breaker trips for that session, logs a warning, and forces Claude Code to send the full system prompt and tools list for the rest of the session.
- Two new tracking flags,
relayHeldStatelessandclassifierHeldStateless, were added to related telemetry.
This behavior only runs when a gate called tengu_quiet_heron is turned on for an account; nothing is yet known about whether it's on anywhere.
Skipping data the server already has can reduce the size of requests when continuing a long-running conversation. The fingerprint-mismatch fallback exists so that if the server and client ever disagree about what's already been sent, Claude Code recovers automatically by sending everything again rather than failing.
tengu_quiet_heron Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.269: off
tengu_lucid_anchor Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.269: off
Read once, for one account on one subscription tier, against v2.1.269. It isn't a statement about your account. What a flag value here can and cannot tell you
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Whether the `tengu_quiet_heron` gate is enabled for any account is unknown; the finding does not say.
New in this build: tengu_quiet_heron