Sweep 19 Sep 2026 · 02:36Z Build v2.1.278 500 read Stable v2.1.267 Latest v2.1.278 Next v2.1.278 Feeds RSS JSON llms.txt Unofficial
Claude Code v2.1.265 ·

New 'tether' protocol threads API requests across turns (off by default)

An off-by-default 'tether' subsystem lets assistant turns continue a previous server-side thread instead of starting fresh, with telemetry and echo auditing

TierNothing to try yethow much it should matter to you
Useful5my rating, 1 to 5
Signal5worth watching, 1 to 5
AreaAPI Protocolwhat it touches
KindIn Developmentin v2.1.265,
Group of 3 Nothing to try yet Notable

An off-by-default 'tether' subsystem lets assistant turns continue a previous server-side thread instead of starting fresh, with telemetry and echo auditing

What

  • 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.
  • 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.
  • 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.

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.

Read from
Feature flag
tengu_curious_tower Not enough to say

Nothing 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 v2.1.265: off

tengu_curious_tower_stateless_models Not enough to say

Nothing 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 v2.1.265: not a boolean we can read

Read once, for one account on one subscription tier, against v2.1.265. It isn't a statement about your account. What a flag value here can and cannot tell you

What has happened since
Flag reading moved The flag server now returns "fable-5-1, opus-5, opus-4-8" for tengu_curious_tower_stateless_models, read as this 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.
Flag reading moved The flag server now returns "fable-5-1, opus-5, opus-4-8, sonnet-5" for tengu_curious_tower_stateless_models, read as this 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.
Flag reading moved The flag server now returns on for tengu_curious_tower, read as this 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.
Flag reading moved The flag server now returns off for tengu_curious_tower, read as this 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.
Flag reading moved The flag server now returns on for tengu_curious_tower, read as this 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.
Flag reading moved The flag server now returns off for tengu_curious_tower, read as this 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.

See this across every release →

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtNothing has been read about whether tengu_curious_tower or tengu_curious_tower_stateless_models is on or off for any account, so it's…
The name it cites is new in this buildNew in this build: tengu_curious_tower

See this entry in the whole of v2.1.265 →