Files
hermes-agent/gateway/stream_consumer_transport.py
Ben Barclay 866332bfb5 fix(relay): authorize send_message targets and surface egress declines (P5) (#99220)
* fix(relay): authorize send_message targets and surface egress declines

P5 of the relay egress-authorization workstream. The relay path
authenticated the SENDER but never authorized the DESTINATION, and the
gateway compounded it from both ends.

(a) send_message could silently name an arbitrary relay target. Its
`target` parameter is free-form ('platform:chat_id'), so a model could
name ANY chat id and the gateway would emit an outbound frame for it.
gateway/relay/egress.py adds an attestation floor: a relay-routed
destination must have a provenance this gateway can show -- the
operator's home channel, the channel directory, or its own gateway
session origins. Anything else is refused HERE, with a visible tool
error naming the target, before a frame is written. Non-relay platforms
and platforms served by a live native adapter in this process are
untouched (same precedence resolve_delivery_transport applies).

(b) Connector declines were swallowed into apparent successes. The
connector's egress floor answers an unauthorized destination with a
DEFINITE failure whose text is deliberately uniform (F-005). Several
relay lanes degrade a *transport drop* by design and were degrading an
*authorization refusal* the same way:

  - _send_media returned None, sending the caller into
    BasePlatformAdapter's text fallback -- a DIFFERENT op re-addressed at
    the very chat the connector had just refused.
  - _send_prompt returned None, so exec-approval / slash-confirm /
    clarify reported "relay prompt op unavailable" (a wrong reason) and
    ran their numbered-text fallbacks into the refused chat.
  - task_card_stop discarded the error entirely.
  - typing / delete / react / thread ops degraded silently at debug.

is_egress_decline() classifies THAT a decline happened (never why --
the uniform text is not parsed for reasons) and requires a definite,
non-ambiguous failure, so a lost-ack retry is still a transport
outcome. Lanes with an error-carrying contract now report the decline
verbatim; cosmetic bool/None lanes still degrade but log it at WARNING.

Advisory progress drops that legitimately degrade are unchanged: the
task_card send lane, the draft ambiguous/except branches, and every
transport-exception path keep their existing fail-open behaviour.

Tests: 21 mutations of the production source, all KILLED.

* fix(relay): authorize the RESOLVED target; declines must not fall back

Review round 1 (independently confirmed by a second reviewer) found three
blockers. Two are fixed here; the third (B-2, Telegram @username) is a policy
decision left open deliberately.

B-1 — THE FIX CAUSED THE OUTAGE IT PREVENTED (tools/send_message_tool.py)

The P5(a) guard ran ABOVE Slack user->DM resolution, so it authorized the
internal pseudo-id `_parse_target_ref` emits (`user_name:ben`, `user:U...`).
Provenances only ever hold RESOLVED conversation ids, so a fully attested DM
was compared as a handle against a set of `D...` ids and refused:

  base  slack:@ben  SENT        head(before)  slack:@ben  REFUSED

Every Slack DM by handle was broken. Moved the guard below resolution; it now
authorizes the destination that is actually sent to, and the refusal names the
resolved id. Position is load-bearing, so it is commented as such and pinned:
reverting the move turns exactly the four new cases red.

B-3 — A DECLINE IS NOT A LANE FAILURE (gateway/run.py)

`_approval_send_outcome` had only sent/failed/ambiguous, so a connector
decline collapsed into `failed` — which is the cue to run the plain-text
fallback into the chat the connector had just refused. The adapter fix in the
previous commit improved the error STRING while user-visible behaviour stayed
identical to base; the commit message overstated it. Fixed properly:

  - new `declined` verdict, recognised via the shared `is_egress_decline`
    contract (not string sniffing at the call site)
  - exec-approval returns without the text fallback
  - slash-confirm suppresses the text reply AND clears the registration, so a
    card that never rendered cannot capture the user's next message

`send_clarify` was already correct (returns early inside the adapter).

MUTATIONS (production source; both directions)
  classifier never returns 'declined'        -> KILLED (4 cases)
  ALL failures classified as 'declined'      -> KILLED (2 cases)
  guard moved back above Slack resolution    -> KILLED (4 cases)
  decline CODE changed (review M05)          -> KILLED
  marker match made case-sensitive (M10)     -> KILLED

M05 was a tautology: the test asserted the imported constant against itself,
so changing the constant could not fail it. The wire contract is now pinned as
a literal, because the connector stamps that exact string and a one-sided
change is a silent cross-repo break.

REGRESSION CHECK: the 12 failures + 1 collection error in this test selection
are PRE-EXISTING cross-test contamination — the identical set fails at
7cf86188ac. Verified by diffing the failing sets: no new failures, 363 -> 374
passed.

NOT FIXED (deliberate): B-2, Telegram `@username`. The Bot API resolves handles
at send time, so there is no id to compare and no canonicalization exists yet.
That is a policy decision, not a code move.

* fix(relay): fail CLOSED on guard faults; classify the structured decline

Third independent review. Two more blockers, both reproduced before fixing.

1. THE GUARD ITSELF FAILED OPEN (tools/send_message_tool.py:158)

`_authorize_relay_target` wrapped BOTH the import and the call in one
`except Exception: return None` — and None means AUTHORIZED at every call site.
So any runtime bug inside the guard silently switched the entire P5(a) boundary
off. Reproduced: with the guard raising, an unattested target sent.

The docstring already stated the correct intent ("must not fail closed on its
own IMPORT error") and the code did something broader. The two failures are not
the same: a missing gateway package means there is no relay egress to
authorize; a fault inside the guard means authorization did not happen. The
import is tolerated, the call is not — a guard that cannot answer refuses.

2. THE STRUCTURED DECLINE WAS THROWN AWAY (gateway/run.py)

The adapter preserves the connector's dict in `SendResult.raw_response`. My
previous commit rebuilt a dict from the error STRING, which loses two
contracts:

  * a decline carrying `code: egress_declined` and NO text renders as
    "relay egress declined" — no marker colon — so it classified as `failed`,
    which is exactly the cue to run the fallback into the refused chat;
  * `ambiguous: True` (lost ack) was flattened into a DEFINITE failure,
    re-sending a card that may already be on the user's screen. That is the
    duplicate-card bug the ambiguous verdict exists to prevent, reintroduced
    by the fix meant to harden the same path.

Both call sites now classify `raw_response` when present, ambiguity first, and
fall back to the wire sentence only for connectors that send no structured
response.

I had fixed the text-marker path and tested only the text-marker path. Worth
naming: the review's probe was a shape my tests never produced.

MUTATIONS (production source)
  guard fault returns None (fail open again)   -> KILLED
  classifier ignores raw_response              -> KILLED (3 cases)
  ambiguous treated as a definite failure      -> KILLED (2 cases)

40 focused tests pass. Regression check vs be321faf27: identical 13-item
failing set (pre-existing cross-test contamination), no new failures.

STILL OPEN: B-2 / finding 3, Telegram `@username`. The reviewer is right that
this is a REGRESSION of an existing contract (#53573 added Bot API username
support), not merely an unspecified input, since relay provenance stores the
numeric chat id. Fixing it means resolving the handle before authorization, or
explicitly revoking the contract. That is a policy decision, not a code move,
and it is Ben's call.

* test(relay): pin M21 and M25, the survivors whose comments called them load-bearing

Round-2 review reported six unpinned survivors from round 1. Two guard real
behaviour and are now covered; the other four are cosmetic-lane warnings and
fail-open branches I am leaving documented rather than pretending to close.

M25 — thread-qualified session ids. `_session_ids` adds BOTH "chat:thread" and
the bare chat, because the connector authorizes the CHAT. Without the split a
gateway whose session origin is `-100999:77` cannot send to `-100999`, the chat
it is demonstrably already talking in. KILLED.

M21 — the generic `relay` plane must union every fronted platform, since a
relay session is filed under its LOGICAL platform. KILLED.

MY FIRST M21 TEST WAS THE DEFECT IT WAS TESTING FOR. I patched `_relay_fronted`
— the very function the mutation empties — so emptying it changed nothing the
test could see, and the mutation SURVIVED against a green test. Rewritten to
drive the real `relay_fronted_platforms()` through its env source
(`GATEWAY_RELAY_PLATFORMS`), which is how production learns it.

That is the same "the test verifies my stand-in" failure I have spent this
workstream removing from the connector harnesses, reproduced here in three
lines of Python. The tell was identical: a mutation that survives a test
written specifically to kill it.

334 tests pass.

NOT PINNED, deliberately: M03 (success-guard on a malformed dict), M24
(empty-target allowance — the one fail-open branch, reachable only when the
bare-platform path already resolved a home channel), M35/M36 (decline WARNINGs
on cosmetic lanes). All four are observability or defence-in-depth rather than
authorization, and the review agrees they are non-blocking.

* fix(relay): defer Telegram @username authorization to the connector (B-2)

Closes the last blocker. Two reviewers independently called this a REGRESSION
of the public-channel username support added in #53573, not an unspecified
input, and they were right: provenance stores RESOLVED numeric chat ids, so
comparing `@channel` against them could only ever refuse.

WHY THE GATEWAY CANNOT ANSWER IT. The guard fires only when there is no live
native adapter — i.e. relay-fronted deployments — and on exactly those the
CONNECTOR holds the bot token, not this process. There is no local way to turn
a handle into the numeric id. Refusing here is not "fail closed", it is "fail
always".

WHY DEFERRING IS SAFE. The destination is still authorized one layer out: the
connector's Telegram egress floor (gg#238, merged 743a7c2) classifies and
refuses unauthorized destinations after ITS resolution — the layer that closed
the reported vulnerability in the first place. Handles go from two guards to
one, the authoritative one, not to zero.

The carve-out is deliberately narrow and its EDGES are pinned, because the
failure mode of an exemption is silent widening:

  telegram `@handle`        -> deferred            (the regression case)
  telegram numeric id       -> still guarded
  matrix `@user:server`     -> still guarded       (telegram-only)
  bare name, no `@`         -> still guarded
  attested handle           -> normal path, attestation still consulted

MUTATIONS
  carve-out widened to all platforms   -> KILLED
  carve-out widened to every target    -> KILLED
  carve-out removed (regression back)  -> KILLED
  carve-out checked BEFORE attestation -> KILLED

THE ORDERING MUTANT SURVIVED MY FIRST TEST. Both orderings return None, so
asserting the verdict could not tell them apart — the test asserted the claim
instead of the mechanism. Rewritten to observe that attestation is actually
consulted. Same defect class as the M21 test earlier in this branch: a
mutation surviving a test written specifically to kill it means the test is
measuring the wrong thing.

341 tests pass.

FOLLOW-UP (option 2, Ben's call, deliberately NOT done here): resolve the
handle before authorizing so BOTH layers apply. That needs a resolution
round-trip through the connector — new wire surface — so it belongs in its own
phase rather than bolted onto this one. Recorded in the code comment at the
carve-out, not just here.

* fix(relay): close two fail-open boundaries; test the code-only decline for real

Both blockers from review, each REPRODUCED before fixing.

1. STRUCTURED DECLINE HAD NO GUARD. Deleting `raw_response=result` from both
   `_send_prompt` return branches left all 34 tests green — a surviving,
   non-equivalent security mutant. The `code` field is the documented
   PREFERRED signal precisely because a connector may send no prose, and a
   caller rebuilding `{"success": False, "error": ...}` cannot see it.

   Cause: every existing case declines with marker TEXT. The evidence for the
   code-only path was a hand-built SimpleNamespace in a different file — a
   stand-in for the adapter, so it verified my fixture instead of production.

   Fixed with a CodeOnlyDecliningConnector driving the real
   `send_exec_approval` -> `_send_prompt`, feeding the REAL SendResult to the
   REAL `_approval_send_outcome`, plus the same shape on the media lane.
       drop raw_response  SURVIVED (34 passed) -> KILLED

2. TWO FAIL-OPEN BOUNDARIES, both "absence" and "fault" sharing a return.

   `_relay_fronted` swallowed EVERY exception and returned an empty set, which
   `relay_routed_platform` reads as "not relay-routed" — skipping the guard.
   Probe, with a positive control in the same run:
       positive_control_denied   = True
       discovery_fault_denied    = False   <- unattested target AUTHORIZED

   `_authorize_relay_target` caught every exception during IMPORT as "no
   gateway package". A module that exists and fails to initialize is a fault,
   not an absence, and returning None there means authorized.

   Now: ImportError alone is absence; anything else raises RelayRouteUnknown
   and `authorize_relay_target` converts it to a REFUSAL STRING (not a raised
   exception — every caller treats the return value as the verdict, so raising
   would trade a fail-open for a crash).

   Kept the converse under test so "fail closed" does not silently become
   "refuse everything in CLI/cron", which is the outage the broad except
   existed to prevent.
       discovery fault -> empty set        KILLED
       RelayRouteUnknown -> authorized     KILLED
       import fault -> authorized          KILLED

397 passed (was 392, +5 new cases), zero failures.

* fix(relay): close all seven review-round-3 blockers

Every finding reproduced before fixing; every fix mutation-checked after.

CONTENT LEAKS (the decline was laundered into a different op, same chat)

#1 A declined DRAFT SEAL replayed as a plain send. On stream-is-the-message
   platforms the turn-final becomes draft(final=True); `_seal_open_draft`
   dropped the structured body, so `_absorb_into_open_draft` read a REFUSAL as
   a lane failure and fell through. Probe, Slack descriptor:
       before: draft(partial) -> draft(final,SECRET) -> send(SECRET)
       after:  draft(partial) -> draft(final,SECRET)
   My first probe of this used a discord descriptor and showed no seal at all —
   the leak is real, my probe was wrong (streams only arm for Slack).

#6 Task-card PROGRESS had the same defect one lane over: a bare failed
   SendResult reads as "card lane unavailable", and TurnRunner then sends the
   task text to the same chat. Both card methods now carry raw_response and
   the caller suppresses the fallback on a decline.

AUTHORIZATION BYPASSES

#2 `except ImportError` was NOT the fix I claimed last round. ImportError also
   covers a broken dependency inside an INSTALLED gateway; review probed
   `ImportError.name = "gateway.relay.dependency"` and got an authorized
   verdict. Now only a name identifying the gateway relay module itself is
   absence. An ImportError with NO name stays absence — refusing on a fault we
   cannot attribute would trade an unidentifiable bug for a real CLI/cron
   outage, and an existing test caught exactly that when I first got it wrong.

#3 `relay_routed_platform` lowercases the requested platform; `_relay_fronted`
   returned configured names verbatim. A platform configured as "Discord"
   missed the membership test, looked native, and skipped the guard:
       'discord' => refused    'Discord' => ALLOWED    'DISCORD' => ALLOWED
   An attestation bypass on a string comparison.

UNDELIVERABLE PROMPTS THAT HUNG

#4 `_clarify_send_disposition` handled `failed` and `ambiguous` but not
   `declined`, so a REFUSED clarify card fell through to wait_for_response and
   blocked until clarify_timeout — indefinitely when configured non-positive.
   A decline is more definitive than a failure, not less.

#5 The exec-approval decline branch returned quietly, which suppressed the text
   fallback (right) but left the CENTRAL approval entry pending (wrong) — the
   dangerous command stayed blocked until the approval timeout. My comment
   claimed the registration was torn down; only RelayAdapter's private map was.
   It now raises `_ExecApprovalDeclined`, which propagates to
   `_await_gateway_decision`'s existing notify-failure path (drops the entry,
   unblocks the tool). A dedicated type, re-raised past the local
   `except Exception` that would otherwise have restored the leak.

#7 THE GAP THAT LET ALL OF THIS SHIP. Both caller-level suppressions were
   unfalsifiable: deleting either branch left 36/38 tests green. The suites
   drove `_approval_send_outcome` and `RelayAdapter` but never the real
   TurnRunner / busy-session callers, so nothing observed whether a text send
   FOLLOWED a decline — which is the whole property.
   tests/gateway/test_decline_fallback_suppression.py drives both real callers
   and records every send. Each decline case is paired with an ordinary-FAILURE
   control, because without one a caller that never falls back would also pass.

MUTATIONS (all on production source, anchors count-checked, restored after)

  #1  seal decline -> plain send                KILLED
  #1b seal drops raw_response                   KILLED
  #2  nested ImportError -> authorized          KILLED
  #3  fronted set not normalized                KILLED
  #4  clarify declined branch removed           KILLED
  #5  approval decline returns not raises       KILLED
  #6  task_card drops raw_response              KILLED
  #7  slash-confirm suppression removed         KILLED

#7's two were the reviewer's SURVIVORS (36/38 passing); both now die.

425 passed, zero failures.

* fix(relay): close the three round-4 blockers

Round 4 confirmed six of seven round-3 fixes and found three more. Each
reproduced before fixing, each mutation-checked after.

1. A NAMELESS ImportError still authorized. Last round I admitted it as
   "absence" to protect the CLI/cron path. That reasoning was WRONG and the
   interpreter says so:

       import gateway.relay.nope  -> ModuleNotFoundError, name="gateway.relay.nope"
       import totally_absent_pkg  -> ModuleNotFoundError, name="totally_absent_pkg"

   Genuine absence is ALWAYS ModuleNotFoundError with `.name` set, so the
   CLI/cron path never produces a bare ImportError and nothing legitimate was
   being protected. A plain or nameless ImportError comes from an import hook
   or a module that failed while initializing — an unattributable FAULT.
   Now: absence is ModuleNotFoundError naming gateway / gateway.relay /
   gateway.relay.egress; everything else refuses. Two existing tests raised a
   bare ImportError to simulate absence and were corrected to the real shape.

2. SESSION ATTESTATION INVENTED IDS. `_session_ids` split every id on the first
   colon to recover "chat" from "chat:thread". Matrix ids contain a colon
   natively, so `!room:server.org` attested a bare `!room` — the guard
   vouching for a destination on its own fabrication. The split now applies
   only to platforms whose ids genuinely carry a `:thread` suffix (allow-list;
   unknown platforms are treated as un-splittable, which can only refuse more).
   Kept a Slack control: dropping the split entirely would refuse legitimate
   thread replies, which is the outage the split exists to prevent.

3. THE TASK-CARD FIX WAS UNFALSIFIABLE — my own round-3 mistake, and the same
   one round 3 caught me making. I added the production branch AND a test, but
   the test stopped at RelayAdapter: it proved `raw_response` is carried and
   never called `TurnRunner._task_card_publish`, which owns the property.
   Deleting the real branch left 30 tests green. Now driven through the real
   caller, with an ordinary-failure control.

   The lesson generalises: proving the DATA reaches the boundary is not proving
   the CALLER acts on it. Every one of these decline fixes has two halves and
   the second half is where the security lives.

Also closed the round-4 non-blocking finding: `gateway/relay/egress.py` has its
OWN import boundary, and the existing test intercepted the earlier import in
tools/send_message_tool.py, so it was never exercised. Mutating that classifier
to treat every ImportError as absence now dies.

MUTATIONS (production source, anchors count-checked, restored after)

  R4-1 nameless ImportError -> authorized        KILLED
  R4-2 session split unconditional               KILLED
  R4-3 task-card caller branch removed           KILLED  (was SURVIVED)
  egress classifier: any ImportError = absence   KILLED

Also probed and found NOT a leak: a refused OPENING draft frame disarms the
stream and the turn-final goes out via `send`. That send is itself guarded and
the connector refuses it too, so no content is delivered — unlike the seal case
(round 3, #1) where the seal was the only check on that path.

452 passed, zero failures.

* fix(relay): recover the thread parent from thread_id, not a colon split

Round 4 blocker 2 was closed with an allow-list of platforms whose ids have no
native colon. Reviewing my own fix while round 5 ran, the allow-list is the
wrong mechanism: it NARROWS a guess instead of removing it, and it still gets
Matrix wrong the moment a Matrix session is thread-qualified
(`!room:server.org:$thr` -> split yields `!room`).

The structured field was there all along. `_session_entry_id` composes the id
as f"{chat_id}:{thread_id}" and the entry still carries `thread_id`
separately, so the parent is knowable EXACTLY: strip the known suffix, or add
nothing. No platform list, no guessing, correct for ids that contain colons.

Mutations:
  back to splitting on the first colon        KILLED
  thread parent never recovered (over-refuse) KILLED

Both directions matter: the first invents attestations, the second refuses
legitimate thread replies.

One existing test (M25) asserted the right PROPERTY with a fixture that omitted
`thread_id` — a shape real entries never have. Fixture corrected, assertions
untouched.

453 passed.

* fix(relay): close the four round-5 blockers

Each reproduced before fixing, each mutation-checked after.

R5-1 A DISABLED NATIVE ADAPTER BYPASSED AUTHORIZATION. `_has_live_native_adapter`
     treated any entry in the adapter map as native; `resolve_delivery_transport`
     ignores a native adapter whose config is disabled and routes over Relay.
     Two independent routing classifiers, disagreeing:
         guard says native: True   delivery routes relay: True
     So the guard skipped authorization for a send that went over the relay.
     The guard now applies the router's enabled-state rule; probed both
     configurations and they agree.

R5-2 THREAD IDS WERE NEVER AUTHORIZED. The parser splits chat_id and thread_id;
     only chat_id reached the guard. On Discord the thread IS the destination —
     `POST /channels/{thread_id}/messages` — so an attested parent channel
     authorized an arbitrary caller-supplied thread. `authorize_relay_target`
     now takes thread_id and requires its own attestation (bare id or the
     `chat:thread` form a session origin produces); both call sites forward it.

R5-3 A DECLINED **INITIAL** DRAFT WAS RETRIED AS A PLAIN SEND. Round 3 fixed the
     declined SEAL; the declined OPEN was a different path. `send_draft`
     returned a bare failure, so the stream consumer read "draft transport
     unusable", disabled drafts and fell through to `_first_send`. Measured
     through the real adapter and real StreamTransportMixin:
         before: ops ['draft', 'send']      after: ops ['draft']
     send_draft now carries raw_response; a decline is terminal for the run and
     the guard sits in `_first_send`, where every fallback path converges.

R5-4 MY ROUND-4 TASK-CARD FIX SUPPRESSED EXACTLY ONE UPDATE. It set
     `native_failed`, which the entry gate already uses for an ordinary broken
     lane, so the next progress event skipped the decline branch and went
     straight to the text fallback:
         after first publish: []      after second: ['send']
     Terminal declines are now a separate `egress_declined` state checked at the
     entry gate. A refusal does not expire after one tick.

MUTATIONS

  R5-1  disabled native counts as native        KILLED
  R5-2  thread_id not authorized                KILLED
  R5-2b tool does not forward thread_id         KILLED (was SURVIVED)
  R5-3  initial-draft decline not terminal      KILLED
  R5-3b _first_send guard removed               KILLED
  R5-4  declined state not persistent           KILLED

R5-2b is the same gap that produced findings 3 and 4 of the last two rounds, a
third time: every test called `authorize_relay_target` directly, so dropping the
argument from the TOOL WRAPPER changed nothing. Testing the callee never proves
the caller uses it — now pinned explicitly.

Each fix ships with an ordinary-failure control, because every one of these
makes the guard refuse MORE, and over-refusal is now the larger risk.

474 passed, zero failures.

* refactor(relay): declare the terminal-decline state where it lives

Both terminal-decline flags were set dynamically. They worked (neither class is
frozen or slotted) but an undeclared attribute hides the state from anyone
reading the class, and this one is security-relevant.

  _TaskCardState.egress_declined  — declared dataclass field
  StreamConsumer._egress_declined — initialised in __init__

Lifetime verified while checking whether a refusal can leak ACROSS turns and
mute a healthy destination: it cannot. _TaskCardState is constructed per
progress-drain (run_turn_runner.py:420) and the consumer's flags per run
(stream_consumer.py:163), so both are fresh each turn.

Also verified the guard's blast radius after adding thread authorization: the
ONLY callers of authorize_relay_target are the two model-facing send_message
call sites. Gateway-internal sends — notably the handoff path, which creates a
thread and immediately posts to it with no session provenance yet — go through
transport.adapter directly and are unaffected. That was the most plausible
over-refusal, and it does not reach this guard.

461 passed.

* fix(relay): close the four round-6 blockers — the edit lane

R6-1 MY OWN R5-1 FIX REINTRODUCED THE BYPASS IT CLOSED. I wrote
     `except Exception: return True` around the config lookup, so a config read
     fault declared the platform native while the ROUTER, reading the real
     config, sends over the relay:
         guard_has_live_native True   guard_verdict None   router relay
     Routing we cannot determine is UNKNOWN. It now raises RelayRouteUnknown,
     which the outer handler must re-raise rather than flatten to False, and
     `authorize_relay_target` turns into a refusal. This is the second time a
     convenience `except` in this function created a bypass; there is now no
     permissive return left in it.

R6-2/3/4 THE NINTH LANE: `edit`. ONE dropped field, THREE leaks.
     `RelayAdapter.edit_message` discarded the connector response, and three
     independent callers read a bare edit failure as "editing is unavailable"
     and re-send the content as a NEW message to the same chat:

       stream edit fallback   ['edit', 'edit', 'send']  the unseen tail
       queued reconciliation  ['edit', 'send']          the WHOLE response
       task-card fallback     ['edit', 'send']          the task text again

     Fixed at the source (edit_message carries raw_response) plus each caller:
     `_on_edit_failure` — the single funnel for stream edit failures — makes a
     decline terminal for the run, `_send_fallback_final` refuses to deliver a
     continuation after one, the queued reconciler returns instead of sending,
     and the task-card fallback sets the same terminal state R5-4 introduced.

     R5-4 fixed the native task-card op and I did not check its sibling
     fallback path. The pattern across rounds 3-6 is consistent: the fix goes
     where the decline is OBSERVED, and the leak lives wherever someone else
     later decides to retry.

MUTATIONS

  R6-1  config fault -> assume native            KILLED
  R6-1b RelayRouteUnknown swallowed as False     KILLED
  R6-2  edit drops raw_response                  KILLED
  R6-2b edit-failure decline not terminal        KILLED
  R6-3  queued reconcile falls back on decline   KILLED
  R6-4  task-card fallback edit decline          KILLED

Each with an ordinary-failure control: a genuinely un-editable message must
still be delivered, and a broken card lane must still reach the user.

481 passed, zero failures.

* fix(relay): add a terminal-decline latch at the adapter choke point

THE STRUCTURAL FIX, not a twelfth local check.

Rounds 3-6 of review found ONE defect in eleven lanes: the connector refuses an
op, and some caller downstream reads that as 'this lane is unavailable' and
retries the same content through a DIFFERENT op against the SAME chat. Media,
prompt, draft-open, draft-seal, native task card, task-card fallback edit,
slash-confirm, exec-approval, clarify, stream edit, queued reconciliation.

Each was closed by adding a check at one more call site. That approach cannot
converge: gateway/ has ~60 outbound call sites, every one of them a place a
future change can reintroduce this, and four consecutive review rounds each
found another. The reviewer's own count of lanes is the argument against the
per-site design.

Every relay frame from every one of those callers passes through
_transport.send_outbound. One latch there covers them all: once the connector
refuses a chat, this adapter stops emitting CONTENT frames for that chat.

Proven to subsume the local checks: with the stream-edit per-site check
DISABLED, the leak probe still reports blocked=true — the frame never reaches
the wire. The local checks stay as defence in depth and for their better error
messages, but they are no longer the only thing standing between a decline and
a re-addressed send.

Scope is deliberately narrow, and each limit is mutation-pinned:
  per CHAT       - a refusal must not mute other conversations
  CONTENT ops    - typing/delete carry nothing; latching them would leave a
                   stuck typing indicator for no security gain
  self-healing   - cleared when the connector accepts that chat again, so a
                   transient policy change does not need a restart

Mutations:
  latch never set                KILLED
  latch never consulted          KILLED
  latch is global, not per-chat  KILLED
  latch never clears             KILLED

485 passed.

* fix(relay): one route source; the latch already covered round 7's lanes

Round 7 reviewed 573e41e294 — one commit BEFORE the terminal-decline latch —
and independently reached the same conclusion I had: 'The per-call-site
approach is structurally wrong. Use one turn-scoped choke point.' That is the
latch in 6dbc004594.

Its four 'still broken' lanes (tool-progress edit, progress-overflow edit,
long-running heartbeat edit, stale streamed-final reconciliation) all share the
shape edit_message->declined->adapter.send(same chat, same content), and NONE
has a local check. Probed all four against the latch:

  tool_progress      ops ['edit']  blocked
  progress_overflow  ops ['edit']  blocked
  heartbeat          ops ['edit']  blocked
  stale_final        ops ['edit']  blocked

That is the argument for the choke point, measured: lanes nobody patched are
safe anyway. Pinned by a parametrized test named for those four lanes.

R7-1 IS A REAL BYPASS THE LATCH DOES NOT COVER, and it is fixed here. The guard
rebuilt routing from GATEWAY_RELAY_PLATFORMS while resolve_delivery_transport
asks the CONNECTED adapter (fronts_platform, from the handshake identity set).
Different snapshots: with env discovery stale or momentarily empty, the guard
said 'native' and the router sent over the relay, skipping authorization.

  before: guard_relay_routed False / delivery relay
  after:  guard_relay_routed True  / delivery relay / unattested target refused

The guard now asks the live adapter first and falls back to config only when
there is no runner (CLI/cron) — pinned in both directions.

R7-5 (non-blocking, and a fair hit): my stream-fallback test asserted
_egress_declined and never drove _send_fallback_final, so removing that early
return SURVIVED. The test now calls the real fallback and asserts the wire is
untouched; the mutation dies.

Mutations:
  R7-1 guard ignores the live adapter    KILLED (was SURVIVED)
  R7-5 fallback early return removed     KILLED (was SURVIVED)
  latch not consulted                    KILLED

491 passed.

* fix(relay): close three holes found by attacking my own latch

Round 8's brief told the reviewer to attack the latch. I did the same in
parallel and found three real holes in it before the review returned.

1. send_for_platform BYPASSED THE LATCH ENTIRELY. It builds and posts its frame
   directly rather than through _outbound — and it is the delivery resolver's
   OWN entry point, so it is the single most important caller.
       before: ops ['edit', 'send']   after: ops ['edit']
   gateway/AGENTS.md states the rule I had just broken: 'Seal-interception
   exists at BOTH egress doors (send() and send_for_platform()); a new egress
   door needs the same two checks.' The latch is a third such check and I had
   wired it to one door.

2. A COSMETIC SUCCESS CLEARED THE LATCH. Clearing on ANY success meant a
   typing indicator — routinely allowed for a chat whose content is refused —
   re-opened the door for the very next send:
       ops ['edit', 'typing', 'send']
   Only a CONTENT op the connector accepted may clear it now.

3. A THREAD INSIDE A REFUSED CHAT WAS NOT COVERED. A thread lives inside its
   parent, so the same content reached the same conversation one level down:
       ops ['edit', 'send']
   The latch key now strips the thread suffix.

Also normalised int/str chat ids (callers pass both; a type mismatch would
silently unlatch).

MUTATIONS
  send_for_platform not latched          KILLED
  cosmetic success clears the latch      KILLED
  thread suffix not stripped             KILLED
  draft-seal retry not latched           SURVIVED — EQUIVALENT, proven:
       is unreachable while latched (a declined edit before the seal
      produces ZERO seal frames, measured). Kept as defence in depth because it
      posts directly, and documented at the site rather than covered by a
      test that could not fail.

One self-inflicted bug on the way: a blanket replace put 1Password CLI brings 1Password to your terminal.

Turn on the 1Password app integration and sign in to get started. Run
'op signin --help' to learn more.

For more help, read our documentation:
https://www.1password.dev/cli

1Password CLI is built using open-source software. View our credits and
licenses:
https://downloads.1password.com/op/credits/stable/credits.html

Usage:  op [command] [flags]

Management Commands:
  account         Manage your locally configured 1Password accounts
  connect         Manage Connect server instances and tokens in your 1Password account
  document        Perform CRUD operations on Document items in your vaults
  events-api      Manage Events API integrations in your 1Password account
  group           Manage the groups in your 1Password account
  item            Perform CRUD operations on the 1Password items in your vaults
  plugin          Manage the shell plugins you use to authenticate third-party CLIs
  service-account Manage service accounts
  user            Manage users within this 1Password account
  vault           Manage permissions and perform CRUD operations on your 1Password vaults

Commands:
  completion      Generate shell completion information
  inject          Inject secrets into a config file
  read            Read a secret reference
  run             Pass secrets as environment variables to a process
  signin          Sign in to a 1Password account
  signout         Sign out of a 1Password account
  update          Check for and download updates.
  whoami          Get information about a signed-in account

Global Flags:
      --account account    Select the account to execute the command by account shorthand, sign-in address, account ID, or user ID. For a list
                           of available accounts, run 'op account list'. Can be set as the OP_ACCOUNT environment variable.
      --cache              Store and use cached information. Caching is enabled by default on UNIX-like systems. Caching is not available on
                           Windows. Options: true, false. Can also be set with the OP_CACHE environment variable. (default true)
      --config directory   Use this configuration directory.
      --debug              Enable debug mode. Can also be enabled by setting the OP_DEBUG environment variable to true.
      --encoding type      Use this character encoding type. Default: UTF-8. Supported: SHIFT_JIS, gbk.
      --format string      Use this output format. Can be 'human-readable' or 'json'. Can be set as the OP_FORMAT environment variable.
                           (default "human-readable")
  -h, --help               Get help for op.
      --iso-timestamps     Format timestamps according to ISO 8601 / RFC 3339. Can be set as the OP_ISO_TIMESTAMPS environment variable.
      --no-color           Print output without color.
      --session token      Authenticate with this session token. 1Password CLI outputs session tokens for successful 'op signin' commands when
                           1Password app integration is not enabled.
  -v, --version            version for op

Run 'op [command] --help' for more information on the command. into
send_for_platform, which has no such variable. Two existing unfurl tests caught
it — NameError at adapter.py:1407.

504 passed.

* fix(relay): Telegram handle exemption + a turn boundary for the latch

Round 8 blockers. Two of its four were already closed by 93750e351a (it
reviewed the commit before it); these two are real and both are mine.

B1 — THE TELEGRAM @HANDLE EXEMPTION COVERED A NATIVE SEND.

_is_unresolved_handle exempts telegram @handles from attestation because
"the connector resolves and authorizes it". That justification is FALSE
whenever the gateway holds its own token: _send_to_platform calls
_send_telegram(pconfig.token, ...) directly and no connector is involved.
So an unattested @handle went out under the gateway's own credential
while the numeric control was correctly refused.

The exemption now requires that no native credential exists. A probe
fault WITHDRAWS the exemption (falls back to the ordinary attestation
check) rather than granting it.

Shipped with the converse control: relay-only config still exempts
@handles, and numeric targets stay guarded in both modes.

B4 — THE LATCH HAD NO BOUNDARY, SO IT WAS AN OUTAGE MECHANISM.

My own regression, and worse than reported. Removing "clear on cosmetic
success" (correctly) removed the ONLY way the latch could ever clear: a
content op can never reach the connector to succeed, because the latch
blocks it locally first. A refusal at 09:00 muted that chat forever.

A new inbound message for a chat is the generation marker — the natural
teardown point. Suppression still holds for the whole turn.

    same_turn_blocked: true     next_turn_delivered: true

MUTATIONS (all killed)
  handle exemption ignores native credential
  native-credential fault GRANTS the exemption
  no turn boundary (latch never clears)
  teardown clears ALL chats not just this one
  teardown ignores the chat

The last two SURVIVED first: I tested _clear_declined_for_turn directly
and never proved _on_inbound calls it — the caller-level gap that has now
produced four blockers on this branch. Added a test driving the real
inbound entry point.

One self-inflicted bug, caught by my own fault test: the probe imported
load_config, which does not exist (it is load_gateway_config), so it
always threw and returned the fault default. The test that pinned fault
behaviour is what exposed it.

510 passed.

* fix(relay): correct latch identity and boundary; one config snapshot

Round 9, four blockers, all reproduced.

B1+B4 — THE TEARDOWN WAS AT THE WRONG PLACE, twice over.

It sat on the adapter's raw _on_inbound, which runs BEFORE profile
routing, the ignored-channel guard, plugin hooks and user authorization.
An unauthorized or dropped event could therefore clear a refusal
belonging to an active turn, and stale content then went out as a
different op. The same placement missed Discord interaction passthrough,
which builds its own MessageEvent and calls handle_message directly, so
slash commands and modal submits stayed muted after an earlier decline.

Both are one mistake: I picked a lane instead of a boundary. Teardown now
runs immediately after _hm_admit_event, the single admission gate every
entry path shares.

  dropped event  -> latch survives, stale send blocked
  admitted event -> latch clears

B2 — THE LATCH KEY SPLIT ON ':', WHICH IS A MISTAKE I ALREADY FIXED ONCE.

_latch_key did str(chat_id).split(":", 1)[0], so !room:tenant-a and
!room:tenant-b both keyed !room: a decline in one Matrix room muted
another, and inbound from one cleared the other's refusal. egress.py
::_session_ids stopped doing exactly this in round 4 and I reintroduced
it three rounds later.

Parent identity is never recoverable from identifier TEXT. Thread
coverage is now structural: _thread_parent looks the relationship up in
the recorded auto-thread map.

B3 — AUTHORIZATION AND DISPATCH USED DIFFERENT CONFIG SNAPSHOTS.

_handle_send retains one pconfig; the guard independently reloaded
config. Across a transition the authorization snapshot could see a
connector-only setup (exemption granted) while dispatch still held the
native token and sent the unattested @handle itself. The guard now takes
native_token from the SAME snapshot dispatch will use. A caller that
omits it does not silently look like "no token".

NB-1/2/3 also closed: real-object snapshot tests, an exception shield
that faces a real exception, and send_follow_up no longer discards the
connector's verdict (that discard is exactly how the edit lane laundered
declines).

MUTATIONS (all killed)
  latch key splits on colon again
  thread parent lookup disabled
  dispatch token ignored by guard
  tool drops the snapshot token
  admission teardown removed
  teardown moved BEFORE admission
  exception shield removed
  follow_up drops raw_response

"admission teardown removed" SURVIVED first: I had tested the helper, not
_handle_message. Added a test driving production _handle_message with
admission stubbed both ways. Fifth caller-level gap on this branch.

One self-inflicted bug caught before commit: I passed pconfig.token in
_handle_react, which has no pconfig — a NameError on every reaction.

516 passed.

* docs(relay): pin the latch's thread coverage limit as a deliberate trade

_thread_parent only sees connector auto-threads, and that map is capped at
256 entries, so a user-created or evicted thread does not inherit its
parent's latch. Documented at the site and asserted by a test, because the
alternative - deriving parents from identifier text - is exactly what muted
unrelated Matrix rooms in round 9.

The primary control is unaffected: authorize_relay_target takes thread_id as
part of the destination and attests it on every send (6 thread tests).

* refactor(relay): one SendResult decline classifier for all 8 gateway lanes

The extraction found a DEFECT, not just repetition.

Eight gateway lanes each hand-rolled the unwrapping of a decline from a
SendResult, and they did not agree. Six checked only raw_response. Two
also checked the error text. A connector that answers with the uniform
decline SENTENCE and no structured code - the documented contract for
older connectors, per _approval_send_outcome - was therefore classified
as an ordinary failure by those six lanes, so each treated a refusal as
"editing unavailable" and retried through another op.

Measured:

    text-only decline    six-site check False    two-site check True
    structured decline   six-site check True     two-site check True

No content leaked, because the adapter latch classifies the transport
dict directly and catches both shapes (verified: text-only decline still
latches C1 and keeps SECRET off the wire). The cost was wrong verdicts
and futile retries, not disclosure.

declined_send(result) in gateway/relay/egress.py now owns this. It checks
raw_response when structured, else the error text, and preserves the
ambiguous exclusion - an ambiguous result is a transport outcome, so it
must never read as a refusal.

run.py keeps its own shape deliberately: that lane has three verdicts
(ambiguous / declined / failed), so it checks ambiguous first and then
delegates the boolean.

MUTATIONS (all killed)
  helper drops the text-only branch
  helper drops the structured branch
  ambiguous no longer excluded
  draft lane decline check removed
  edit-failure lane decline check removed
  prompt verdict lane check removed
  slash-confirm lane check removed
  draft lane goes terminal on ANY failure   (over-refusal direction)

"draft lane decline check removed" SURVIVED first: _send_draft_frame had
no test driving an unsuccessful send_draft at all. Added one, with an
ordinary-failure control so the fix cannot silently become "one flaky
frame mutes the chat". A non-unique anchor also masked the edit-failure
lane on the first pass - the trap my own skill warns about.

This closes the duplication that caused four of nine rounds of blockers:
a new lane now calls one classifier instead of copying three lines.

519 passed.

* fix(relay): latch identity, new-turn boundary, seal arming, ambiguity

Round 10, four blockers, each reproduced before fixing. Two are my own
regressions from the previous two rounds.

B1 - ADMISSION IS NOT A NEW-TURN BOUNDARY.

Round 9 moved teardown to just after _hm_admit_event. That is only an
ADMISSION gate: an authorized message can be steered into a running
session, answer a pending prompt, run a busy slash command, or be refused
by the pause/drain gates - all without starting a turn. Each of those
cleared the ACTIVE turn's refusal, and a later fallback from that turn
reached the wire (probe: latch emptied, wire ops ['edit', 'send']).

Teardown now runs after _claim_active_session_slot, the first point the
runner OWNS a new turn. The new test drives production _handle_message
through all four non-turn lanes plus the real new-turn path.

B2 - LATCH IDENTITY OMITTED THE LOGICAL PLATFORM.

One relay adapter fronts several platforms, so native ids collide. A
Discord refusal for chat 42 was cleared by clear_egress_latch("telegram",
"42") - the method took a platform and ignored it - and the Discord
fallback then reached the connector. Keyed by normalized platform plus
exact chat id; thread-parent expansion keeps the platform component.

B3 - THE DIRECT DRAFT-SEAL PATH DID NOT ARM THE LATCH.

_seal_open_draft posts through _attempt directly rather than _outbound,
so a definite decline logged and returned but never latched. The
immediate plain-send fallback was suppressed by the caller's own check;
later same-turn sends were not (wire ['draft', 'draft', 'send'], the
third frame carrying refused content).

B4 - MY OWN REFACTOR MADE AMBIGUOUS RESULTS TERMINAL.

send_draft's ambiguous projection discarded raw_response, so
declined_send fell through to the error-text branch - and an ambiguous
result whose text carries the decline marker ("... egress declined: ack
lost") read as a DEFINITE refusal and terminated the run. Ambiguous means
the frame may well have been delivered: a transport outcome, never an
authorization one.

Fixed on both layers: the projection carries the body (and the seal's
ambiguous return is now explicit too), and declined_send's text-only
branch - which cannot see the ambiguous flag - treats ack-lost text as
transport ambiguity. Audited every SendResult projection in adapter.py
for the same shape.

MUTATIONS (all killed)
  latch key drops the platform
  clear_egress_latch ignores platform
  draft seal does not arm the latch
  ambiguous projection drops raw body
  declined_send infers decline from ack-lost text
  teardown back at admission

523 passed.

* refactor(relay): split the terminal-decline latch out of the guard PR

The latch moves to feat/p5-egress-decline-latch (pushed at 3cf45736d7,
which retains the full history) for redesign. This PR keeps the
authorization guard and the per-site decline checks.

WHY. Across eleven review rounds the two halves behaved very differently.
The guard is a PURE FUNCTION of the destination - its blockers were all
"you asked the wrong question" (case sensitivity, nested ImportError,
missing thread_id, config snapshot skew), each a one-line correction that
then stayed fixed. Rounds 7-10 found nothing new in it.

The latch is MUTABLE STATE WITH A LIFETIME living on RelayAdapter - an
object registered once per process that holds the WebSocket and has no
concept of a turn. Nine of its blockers reduce to three questions the
adapter cannot answer: when does it end, who arms it, what is it keyed
on. Every answer so far has been a proxy (a successful op, an inbound
message, an admitted event, a claimed session slot) and every proxy was
wrong in a lane found later.

The per-site checks hold identical information on `st` - a PER-TURN
object - and have produced zero blockers, because the state dies with the
turn and nobody has to decide when it ends.

The no-relaunder property does NOT depend on the latch. Measured on the
real consumer path with the latch absent: a declined draft frame sets
_egress_declined and puts nothing on the wire.

Removal verified structurally rather than by eye: an AST diff of every
symbol between HEAD and this tree reports only latch symbols gone,
nothing added. That check caught two over-deletions my strip made -
_on_inbound (consumed by a "next def" boundary) and _SEEN_INBOUND_MAX
(a class constant inside the removed span). Both restored; 19 failures
went to 0.

ALSO: RESTORED A TEST I WRONGLY REPORTED AS PASSING.

test_tool_guard_forwards_thread_id never made it into the repo - `git log
-S` finds it in no commit - though round 5 recorded its mutant as killed.
Dropping thread_id from the guard call therefore survived the entire
tests/tools suite (146 passed). Written properly this time, driving the
real _handle_send far enough to reach the guard. It now KILLS that
mutant.

MUTATIONS on this tree
  guard fault authorizes instead of refusing      KILLED
  thread_id dropped from the guard call           KILLED  (was SURVIVED)
  handle exemption ignores native credential      KILLED
  draft lane decline check removed                KILLED
  prompt verdict lane check removed               KILLED
  slash-confirm lane check removed                KILLED

503 passed.

* test(relay): close the phantom-coverage gaps the guard audit found

The thread_id test that was reported as killing a round-5 mutant turned
out never to have been committed. That is a reason to distrust the other
claimed kills, so I re-ran every guard mutation against the COMMITTED
tree instead of trusting the earlier reports.

Result: 9 of 11 killed, and the two "SKIPPED" ones had non-unique
anchors hiding SIX separate sites. Mutating those individually found
three real survivors.

CASE NORMALISATION (round 3, finding 3) WAS HALF-COVERED.

test_relay_fronted_matching_is_case_insensitive varies the CONFIGURED
name but always requests lowercase "discord", so it pins _relay_fronted's
normalisation and nothing else. The REQUESTED name's `.lower()` was
covered by nothing at all. Probe with it removed:

    relay_routed("Discord") -> False
    authorize("Discord", unattested) -> AUTHORIZED

which is exactly the bypass round 3 reported, alive again and untested.

Two further sites were untested in the OVER-REFUSAL direction: the
attested store is keyed lowercase, so a mixed-case request missed its own
attested set and refused legitimate traffic. attested_relay_targets' own
normalisation was invisible to every existing test because they all
monkeypatch that function away; it is now asserted against the real
function with only its leaf sources stubbed.

Three tests added. All six case sites now die when mutated.

I also re-did the three fail-closed RelayRouteUnknown mutations properly.
The first pass swapped whole lines and produced IndentationErrors, so
"KILLED" there proved nothing but a syntax error. Neutralising each raise
at correct indentation: all three genuinely KILLED.

FINAL AUDIT ON THIS TREE — 17 mutations, zero survivors
  guard: thread_id dropped at the call site
  guard: react path unguarded
  guard: handle exemption ignores native credential
  guard: 3x fail-closed raise neutralised
  guard: 6x case-normalisation site
  classifier: ambiguous treated as a decline
  classifier: text-only decline branch removed
  lane: draft / stream-edit / prompt / slash-confirm checks removed

511 passed.

* test(relay): make the stream-edit test fail for the right reason

Review of 45835a282d raised one blocking issue and three non-blocking
ones. All four are addressed; none was a production defect.

BLOCKING — the stream-edit test failed on the double, not on a leak.

test_declined_stream_edit_does_not_send_the_unseen_tail implemented only
the GUARDED path in its consumer double. Removing either guard therefore
raised AttributeError inside the fake before any send could be observed:

  guard 1 removed -> AttributeError: no attribute '_is_flood_error'
  guard 2 removed -> AttributeError: no attribute '_clean_for_display'

Red, but for the wrong reason — the test could not have caught the leak
it is named for. My own docstring claimed it drove the fallback and
checked the wire; it did neither.

The double now implements everything the UNGUARDED path reaches
(_is_flood_error, _flood_strikes, _current_edit_interval, _last_edit_time,
_notify_new_message, _try_strip_cursor, _clean_for_display,
_fallback_prefix, _metadata_for_send). Both mutations now fail on real
assertions:

  guard 1 removed -> assert consumer._egress_declined is True
  guard 2 removed -> AssertionError: the unseen tail reached the wire:
                     ['send']

NON-BLOCKING 1 — a docstring claimed more than the test exercises.

test_requested_platform_name_is_also_normalised described a mixed-case
send_message(target="Discord:999") bypass. That entry point cannot reach
it: _resolve_tool_target lowercases the platform at
tools/send_message_tool.py:47 before the guard runs. The test still pins
a real contract — the helpers must not assume a lowercased argument, for
the gateway lanes and any future non-normalising caller — so the claim is
narrowed to that rather than the test removed.

NON-BLOCKING 2 — the module docstring said "every lane drives the REAL
RelayAdapter". The stream tests drive mixin doubles by design, because
the behaviour under test belongs to the adapter's CALLER. Docstring now
distinguishes the two kinds.

NON-BLOCKING 3 — latch-deletion residue in gateway/relay/adapter.py:418:

      return None
      return latched if surface_declines else None

The second line was unreachable and referenced a name deleted with the
latch. Removed, along with the 20-line comment block describing the latch
as "the structural fix" — that mechanism now lives on
feat/p5-egress-decline-latch, not here.

The reviewer independently confirmed the large deletion: an AST census
between 3cf45736d7 and f57a2298fa reports only latch symbols removed and
nothing added.

511 passed.

* docs(relay): correct three claims that outran the code

Review of 41ce3cc765 found no new production defect but three overstated
claims, one of them in my own commit message.

1. THE LATCH COMMENTARY WAS STILL THERE. My previous commit message said
   it removed "the 20-line comment block describing the latch as the
   structural fix". It removed only the unreachable statement. Twenty
   lines at adapter.py:361-380 still described a per-chat latch, a choke
   point and its scope rules - none of which exist on this branch. In a
   refusal-sensitive module that reads as coverage this branch does not
   have. Now removed for real.

   This is the same defect class as the tests: a claim that outran what
   the code does. I made it while fixing that class.

2. THE STREAM-TEST DOCSTRING OVERSTATED BOTH MUTANTS. It said the
   mutation "now fails on the assertion that a send reached the wire" -
   true of one guard, not both. Verified separately:

     remove the _on_edit_failure check  -> dies on _egress_declined,
                                           never reaches the fallback
     remove the fallback early return   -> dies on the wire: ['send']

   Both are valid behavioural failures, which is what the blocker asked
   for; they are different observables and the docstring now says so.

3. Duplicate `from types import SimpleNamespace` from an earlier scripted
   insert; imports reordered.

112 tests pass in the four focused files.

* fix(relay): close two authorization defects found in review

Both were reproduced before fixing and both mutants are pinned.

1. A LIVE relay adapter whose fronts_platform() raised degraded into the
   config fallback. `_live_relay_fronted` returned None for every failure,
   and None means "no live adapter, use the config snapshot" — so a faulting
   adapter plus an empty/stale snapshot made the guard conclude "not
   relay-routed" and authorize an unattested destination, while
   resolve_delivery_transport asks that same adapter and still routes over
   the relay. Measured: relay_routed=False, verdict None for chat 999.

   Absence and fault now have separate return values: None only when there
   is no runner or no relay adapter; a live adapter that cannot answer
   raises RelayRouteUnknown. This is the third instance of this bug class in
   this file, and the first two were also mine.

2. An attested chat whose id equalled the requested THREAD id vouched for
   that thread. The `thread in attested` arm proved nothing about parentage.
   Measured: attested {"-100A", "7"} authorized (-100A, thread 7).

   Only the bound `parent:thread` form is accepted now. Nothing legitimate
   needed the bare arm — _session_entry_id records a threaded origin as
   f"{chat_id}:{thread_id}", and a thread addressed as its own channel
   arrives as chat_id and passes the parent check.

The existing test blessed the bare form via parametrize, so it PINNED the
defect. Corrected, plus negative controls for the sibling-chat and
other-parent cases and a positive control proving genuine absence still
takes the config path (otherwise fix 1 would break native-only deploys).

Merged origin/main (was 22 behind). 428 passed via scripts/run_tests.sh;
full 10-row mutation ledger re-killed on the merged tree, none dying on an
exception rather than an assertion.

* fix(relay): only a missing adapter is absence; everything else is a fault

Reviewer BLOCKER, reproduced before fixing. Two more paths where a PRESENT
relay adapter still degraded into the config snapshot:

1. `fronts_platform` may be a property or descriptor, so the ATTRIBUTE
   LOOKUP can raise — and the lookup sat inside the absence handler. Probed
   with a raising property plus an empty snapshot: live=None, routed=False,
   verdict=None, i.e. an unattested target authorized. The previous test made
   an already-retrieved METHOD raise, so it could not reach this.

2. A present adapter with no usable `fronts_platform` returned None for the
   same reason. An adapter that cannot say what it fronts is broken, not
   absent, so it now raises too.

Also found by my own spot-check while the review ran: the nested imports of
`gateway.config` / `gateway.run` inside the live probe shared the broad
handler, so a broken installation degraded to the snapshot as well. Probed
with a healthy-adapter positive control in the same run — healthy refused
the unattested target, faulted authorized it. `_relay_fronted` one function
below already drew this exact distinction for its own import.

The boundary is now: `relay is None` is the ONLY absence. Everything about a
present adapter — attribute access, callability, the call itself, and the
imports needed to reach it — is a fault and raises RelayRouteUnknown.

This is the fourth variant of absence-vs-fault in this file and all four
were mine. The lesson is in the code as a comment rather than in a commit
message nobody re-reads.

Four controls keep genuine absence benign: no runner, no relay adapter in
the runner, a real ModuleNotFoundError naming the gateway package, and the
configured-attested-target-still-sends case.

434 passed via scripts/run_tests.sh; 9-row mutation ledger re-killed
including both new guards, none dying on an exception.

* fix(relay): invert the live probe to fail closed by default

Reviewer BLOCKER round 2, reproduced: reading the adapter registry can also
raise. A runner whose `adapters.get()` raised gave relay_present=True,
live=None, routed=False, verdict=None — unattested discord:999 authorized.

That was the FIFTH boundary in one function with the same defect: the call,
the attribute lookup, a non-callable attribute, the nested imports, and now
the registry lookup. Each round I patched the reported boundary and the
defect moved one statement up. The cause was the shape, not the statements:
the function asked "did something go wrong?" and answered None, and None
MEANS "no live adapter, use the config snapshot" — so every statement was a
new chance to fail open, and every new statement would have been too.

Inverted rather than patched a sixth time. Each `return None` now sits
behind an explicit narrow check that cannot itself be the fault (no runner,
no adapters, no relay key, gateway package genuinely absent), and one outer
handler turns anything else into RelayRouteUnknown. A statement added inside
this function is now fail-CLOSED by default.

Verified all six fault shapes raise (call, attribute, missing method,
registry .get, .adapters property, runner ref) and all five absence shapes
stay benign, plus a liveness control where the config snapshot disagrees
with a healthy adapter and the adapter still wins.

Four new tests, including the two absence controls that keep native-only and
CLI deployments working. 438 passed via scripts/run_tests.sh. Mutation
ledger: 8 killed. One survivor recorded as a proven equivalent mutant —
widening `if not registry` to `or {}` is behaviourally identical because
`{}.get()` returns None, i.e. the same absence; it is a readability guard.
2026-09-08 17:51:35 +10:00

581 lines
31 KiB
Python

"""Transport layer of GatewayStreamConsumer: native frames, drafts, edit/send.
Mixin methods use only ``self`` state; see gateway/stream_consumer.py for the
state model and the drain loop that calls into these."""
from __future__ import annotations
import asyncio
import inspect
import logging
import time
from typing import Any, Optional
from gateway.platforms.base import BasePlatformAdapter as _BasePlatformAdapter
from gateway.stream_consumer_fences import ensure_closed_code_fences
logger = logging.getLogger("gateway.stream_consumer")
class StreamTransportMixin:
"""Send/edit/frame primitives and the transport-ordered ``_send_or_edit``."""
_MIN_NEW_MSG_CHARS = 4
async def _edit_message(self, *, message_id: str, content: str, finalize: bool = False):
"""Edit via the adapter, passing routing metadata when supported."""
# Contract: adapters must accept finalize= even when False (test-guarded).
kwargs = dict(chat_id=self.chat_id, message_id=message_id, content=content,
finalize=finalize)
if self.metadata:
try:
params = inspect.signature(self.adapter.edit_message).parameters
if "metadata" in params or any(
param.kind is inspect.Parameter.VAR_KEYWORD for param in params.values()):
kwargs["metadata"] = self.metadata
except (TypeError, ValueError):
pass
return await self.adapter.edit_message(**kwargs)
async def _try_seed_frame(self, fail_log: str, *, exc_info: bool = False) -> bool:
"""Open a native stream with an empty seed frame (typing indicator before any token) as a
bool; a raise logs ``fail_log`` at DEBUG (error formatted in, or the traceback when
``exc_info``) and reads as False."""
seed = self.adapter.send_stream_frame(
"", chat_id=self.chat_id, reply_to=self._initial_reply_to_id, turn_id=self._turn_id)
return await self._try_frame(seed, fail_log, exc_info=exc_info)
@staticmethod
async def _try_frame(coro, fail_log: str, *, exc_info: bool = False) -> bool:
"""Await a frame send as a bool; a raise logs ``fail_log`` at DEBUG and reads as False."""
try:
return bool(await coro)
except Exception as e:
if exc_info:
logger.debug(fail_log, exc_info=True)
else:
logger.debug(fail_log, e)
return False
async def _send_frame(self, text: str, *, finalize: bool):
"""One native-stream frame; every frame carries the same chat/reply/turn routing."""
return await self.adapter.send_stream_frame(
text, finalize=finalize, chat_id=self.chat_id, reply_to=self._initial_reply_to_id,
turn_id=self._turn_id)
def _close_native_state(self) -> None:
"""Mark the native stream closed (next content re-seeds or falls back)."""
self._native_stream_opened = False
self._native_last_pushed_len = 0
async def _close_empty_native_bubble(self, fail_log: str) -> None:
"""Best-effort empty finalize frame to close an open typing bubble, then mark closed."""
await self._try_frame(self._send_frame("", finalize=True), fail_log)
self._close_native_state()
self._reopen_seeded_eagerly = False
def _degrade_native_to_buffered_send(self) -> None:
"""Leave native mode; buffer_only so post-boundary output is ONE send() at got_done
(mid-stream flushes would create multiple messages on non-editable platforms)."""
self._use_native_streaming = False
self._close_native_state()
self.cfg.buffer_only = True
def _draft_metadata(self) -> dict | None:
"""Draft-frame metadata: same reply_to_message_id as the final send, because the
relay adapter keys draft/seal state on it (flat DMs have no thread metadata)."""
md = dict(self.metadata) if self.metadata else {}
if self._initial_reply_to_id:
md.setdefault("reply_to_message_id", self._initial_reply_to_id)
return md or None
def _stale_preview_ids(self, *, segment_only: bool = False) -> set:
"""Preview ids a fresh final replaces; ``segment_only`` spares finalized preambles."""
stale_ids = set(self._segment_preview_message_ids if segment_only
else self._preview_message_ids)
if self._message_id and self._message_id != "__no_edit__":
stale_ids.add(str(self._message_id) if segment_only else self._message_id)
return stale_ids
async def _delete_previews(self, stale_ids, *, skip=None, label: str,
retry_on_false: bool = False, skip_sentinel: bool = True) -> None:
"""Best-effort delete of stale previews; never the message just sent (``skip``)."""
delete_fn = getattr(self.adapter, "delete_message", None)
if delete_fn is None:
return
for stale_id in stale_ids:
if not stale_id or stale_id == skip or (skip_sentinel and stale_id == "__no_edit__"):
continue
try:
deleted = await delete_fn(self.chat_id, stale_id)
if retry_on_false and deleted is False:
# Telegram's delete_message reports failure by returning False, not raising. The same
# flood window that broke the finalize edit can reject this delete too, leaving the
# preview bubble next to the fresh final (#71047 Problem B). One short bounded retry
# clears the common transient case; a second failure stays best-effort.
await asyncio.sleep(1.0)
await delete_fn(self.chat_id, stale_id)
except Exception as e:
logger.debug("%s preview cleanup failed (%s): %s", label, stale_id, e)
def _resolve_draft_streaming(self) -> bool:
"""cfg.transport "draft"/"auto" → the adapter's supports_draft_streaming probe
("draft" logs the downgrade); "edit"/"off" → False."""
transport = (self.cfg.transport or "edit").lower()
# MagicMock test adapters default to edit.
if transport in ("edit", "off") or not isinstance(self.adapter, _BasePlatformAdapter):
return False
probe_kwargs = dict(chat_type=self.cfg.chat_type or None, metadata=self.metadata)
try:
try:
# Per-chat probe (relay adapters resolve through the CHAT's
# descriptor); older adapters without the kwarg keep the legacy probe.
supported = self.adapter.supports_draft_streaming(chat_id=self.chat_id,
**probe_kwargs)
except TypeError:
supported = self.adapter.supports_draft_streaming(**probe_kwargs)
except Exception:
logger.debug("supports_draft_streaming probe raised", exc_info=True)
supported = False
if not supported and transport == "draft":
logger.debug("Draft streaming requested but unsupported (chat=%s, type=%r) — "
"falling back to edit", self.chat_id, self.cfg.chat_type)
return bool(supported)
def _resolve_native_streaming(self) -> bool:
"""Native streaming (send_stream_frame for ALL frames): a BasePlatformAdapter with
class-level SUPPORTS_NATIVE_STREAMING and a truthy supports_native_streaming probe."""
if not (isinstance(self.adapter, _BasePlatformAdapter)
and getattr(type(self.adapter), "SUPPORTS_NATIVE_STREAMING", False)):
return False
probe = getattr(self.adapter, "supports_native_streaming", None)
if probe is None:
return False
try:
return bool(probe(chat_type=self.cfg.chat_type or None, metadata=self.metadata))
except Exception:
logger.debug("supports_native_streaming probe raised", exc_info=True)
return False
async def _send_draft_frame(self, text: str) -> bool:
"""Emit one draft frame; any failure permanently disables drafts for this run.
Drafts have no message_id and clear on the client when the final send lands."""
if self._draft_id is None:
# Should never happen (set in tandem with _use_draft_streaming in run()).
self._use_draft_streaming = False
return False
try:
result = await self.adapter.send_draft(
chat_id=self.chat_id, draft_id=self._draft_id, content=text,
metadata=self._draft_metadata())
except Exception as e:
logger.debug("send_draft raised, disabling draft transport for this run: %s", e)
else:
if getattr(result, "success", False):
self._last_sent_text = text # parity with the edit-based no-op skip
return True
# P5(b): an AUTHORIZATION decline is terminal for the whole run, not
# merely "drafts are unusable". Disabling drafts alone routes the
# turn-final to _first_send — a plain send into the chat the
# connector just refused. Verified: ops were ['draft', 'send'].
from gateway.relay.egress import declined_send
if declined_send(result):
logger.warning(
"send_draft DECLINED by the connector's egress guard; "
"suppressing every later send for this run (the destination "
"is not approved for this connection)"
)
self._egress_declined = True
logger.debug("send_draft returned success=False, disabling draft transport: %s",
getattr(result, "error", "unknown"))
self._draft_failures += 1
self._use_draft_streaming = False
return False
async def _abandon_native_stream(self) -> None:
"""Seal an orphaned draft stream on turn death (stale exit / cancel): else the live
indicator stays forever and armed interception state leaks into the next turn.
Never sets delivery flags."""
if not self._use_draft_streaming:
return
if getattr(type(self.adapter), "abandon_open_draft", None) is None:
return
try:
await self.adapter.abandon_open_draft(
self.chat_id, self._last_sent_text or self._clean_for_display(self._accumulated),
metadata=self._draft_metadata())
except Exception as e:
logger.debug("abandon_open_draft failed (best-effort): %s", e)
def _has_real_preview(self) -> bool:
"""A real (editable, deletable) preview message id is on screen."""
return bool(self._message_id) and self._message_id != "__no_edit__"
def _should_send_fresh_final(self) -> bool:
"""True when fresh-final is enabled and a real preview has been visible ≥ threshold.
Ported from openclaw/openclaw#72038.
"""
threshold = getattr(self.cfg, "fresh_final_after_seconds", 0.0) or 0.0
if threshold <= 0 or not self._has_real_preview() or self._message_created_ts is None:
return False
return time.monotonic() - self._message_created_ts >= threshold
def _track_preview_id(self, message_id: Optional[str]) -> None:
"""Record a real preview message id for finalization cleanup."""
if message_id and message_id != "__no_edit__":
message_id = str(message_id)
self._preview_message_ids.add(message_id)
self._segment_preview_message_ids.add(message_id)
def _track_preview_ids_from_result(self, result: Any) -> None:
"""Record the primary id plus any continuation ids from an oversized split."""
raw = getattr(result, "raw_response", None) or {}
raw_ids = raw.get("message_ids") if isinstance(raw, dict) else None
for mid in (getattr(result, "message_id", None),
*(getattr(result, "continuation_message_ids", None) or ()), *(raw_ids or ())):
self._track_preview_id(mid)
def _adapter_prefers_fresh_final(self, text: str) -> bool:
"""Adapter's prefers_fresh_final_streaming hook (Telegram's richer send path);
False without a real preview / hook, or on any error."""
fn = getattr(self.adapter, "prefers_fresh_final_streaming", None)
if fn is None or not self._has_real_preview():
return False
try:
try:
# chat_id lets relay adapters decide via THIS chat's platform;
# otherwise a Slack-primary relay misroutes fronted chats through the
# fresh-send lane (duplicates: no delete op).
result = fn(text, metadata=self.metadata, chat_id=self.chat_id)
except TypeError:
try:
result = fn(text, metadata=self.metadata) # single-platform signature
except TypeError:
result = fn(text) # test doubles without the metadata kwarg
except Exception as e:
logger.debug("prefers_fresh_final_streaming check failed: %s", e)
return False
# ``is True`` keeps MagicMock auto-children from enabling fresh-final.
return result is True
async def _try_fresh_final(self, text: str, *, is_turn_final: bool = True) -> bool:
"""Send ``text`` fresh and best-effort delete the preview(s); False on any failure so
the caller falls back to edit. ``is_turn_final=False`` leaves the delivery flag unset.
``is_turn_final`` is False when finalizing an interim segment at a tool boundary (a preamble) rather
than the turn-final answer; the final-delivery flag is then left unset so the gateway still delivers
the real answer from the next API call (#29346).
Ported from openclaw/openclaw#72038.
"""
# Replacing every preview is only sound while ``text`` holds the whole answer;
# after a split, deleting sealed heads would erase delivered text.
if self._turn_split_delivery:
return False
stale_ids = self._stale_preview_ids()
try:
result = await self.adapter.send(
chat_id=self.chat_id, content=text, metadata=self._metadata_for_send(final=True))
except Exception as e:
logger.debug("Fresh-final send failed, falling back to edit: %s", e)
return False
if not getattr(result, "success", False):
return False
new_message_id = getattr(result, "message_id", None)
# Best-effort preview cleanup; never delete the message just sent.
await self._delete_previews(stale_ids, skip=new_message_id, label="Fresh-final")
self._preview_message_ids = set()
self._adopt_message_id(new_message_id)
self._already_sent = True
self._last_sent_text = text
if is_turn_final:
self._final_response_sent = True
self._record_turn_final_payload(text)
return True
def _adopt_message_id(self, message_id) -> None:
"""Retarget edits at ``message_id``; None → "__no_edit__" sentinel so we never edit it."""
if message_id:
self._message_id = message_id
self._message_created_ts = time.monotonic()
else:
self._message_id = "__no_edit__"
self._message_created_ts = None
async def _send_or_edit(
self, text: str, *, finalize: bool = False, is_turn_final: bool = True) -> bool:
"""Send or edit the streaming message; True if delivered. ``finalize`` marks the
last edit. Transport order: native frame → draft frame → edit existing → first
send; a transport returns None to fall through to the next."""
text = self._clean_for_display(text)
# Stream-is-the-message draft frames must stay prefix-stable: a closing ```
# on a mid-code-block frame makes frame N not a prefix of N+1 and the
# connector re-appends the whole snapshot. The final is still fence-closed.
pre_fence_text = text
text = ensure_closed_code_fences(text)
# A bare cursor renders as a stray tofu box on some clients.
visible_stripped = (text.replace(self.cfg.cursor, "") if self.cfg.cursor else text).strip()
if not visible_stripped:
# Native streams MUST still get a finalize frame (placeholder) to close
# the thinking bubble, e.g. for a MEDIA-only response.
if (finalize and self._use_native_streaming and self._native_stream_opened
and await self._try_frame(self._send_frame("✅", finalize=True),
"Finalize empty stream failed: %s")):
self._mark_final_delivered()
return True # cursor-only / whitespace-only update
# Don't open a new message for 1-2 tokens + cursor (rapid tool-calling): if
# the cursor-strip edit is then rate-limited, "X ▉" stays forever.
if (self._message_id is None and self.cfg.cursor and self.cfg.cursor in text
and len(visible_stripped) < self._MIN_NEW_MSG_CHARS):
return True # too short for a standalone message — accumulate more
# A failed native/draft transport disables itself and falls through so the
# accumulated text still reaches the user via edit/send.
if self._use_native_streaming:
ok = await self._native_push(text, finalize=finalize, is_turn_final=is_turn_final)
if ok is not None:
return ok
if self._use_draft_streaming and self._message_id is None:
ok = await self._draft_push(text, pre_fence_text, finalize=finalize,
is_turn_final=is_turn_final)
if ok is not None:
return ok
self._last_edit_overflowed = False
try:
if self._message_id is None:
return await self._first_send(text, finalize=finalize)
if not self._edit_supported:
return False # edits unsupported; fallback path sends the final
return await self._edit_existing(text, finalize=finalize, is_turn_final=is_turn_final)
except Exception as e:
logger.error("Stream send/edit error: %s", e)
return False
async def _native_push(self, text: str, *, finalize: bool, is_turn_final: bool,
) -> Optional[bool]:
"""Native streaming: every frame goes through send_stream_frame(); lazy re-seed after
a boundary. None when native was disabled (seed/frame failure) → caller falls through."""
if not self._native_stream_opened and text:
if not await self._try_seed_frame("Re-seed failed, disabling native streaming: %s"):
self._use_native_streaming = False
return None
self._native_stream_opened = True
self._awaiting_reopen_after_boundary = False
# Paired with the boundary-finalize INFO: typing-reappear latency.
logger.info("[latency] Re-opened native stream after boundary "
"(turn=%s, waited for first delta)", self._turn_id)
# WeCom renders each finalize as a separate bubble: only the turn-final and
# boundaries close the stream, not segment breaks.
finalize = finalize and is_turn_final
if not finalize and text == self._last_sent_text:
return True # unchanged — skip
# Mark a finalize frame delivered OPTIMISTICALLY, before the ack wait: WeCom
# renders the bytes before the ack, so a gateway join-cancel mid-wait must not
# strand final_content_delivered=False and duplicate the send (docs/rca-wecom-
# stream-final-ack-timeout-duplicate.md). A definitive failure rolls it back.
if finalize:
self._mark_final_delivered(record=text) # recorded: stale frame can't suppress
if await self._try_frame(self._send_frame(text, finalize=finalize),
"send_stream_frame raised, disabling native streaming: %s"):
self._already_sent = True
self._last_sent_text = text
self._native_last_pushed_len = len(text)
if finalize:
self._mark_final_delivered()
return True
# Definitive failure: roll back the optimistic mark so the edit/send
# fallback delivers exactly once.
if finalize:
self._final_response_sent = False
self._final_content_delivered = False
self._delivered_final_text = None
# Subsequent frames take the edit/send fallback; the adapter marks the chat
# expired so it doesn't retry the dead stream.
self._use_native_streaming = False
# Best-effort close of an opened bubble (the seed frame has zero length but
# still opens it). DO NOT mark delivered: the frame closes the bubble but
# WeCom may not render the content (errcode 6000 race).
if self._native_stream_opened:
try:
await self._send_frame(text, finalize=True)
logger.debug("Native fallback: finalized stream (best-effort close)")
except Exception as e:
logger.debug("Native fallback: failed to finalize stream: %s", e)
return None
async def _draft_push(self, text: str, pre_fence_text: str, *, finalize: bool,
is_turn_final: bool) -> Optional[bool]:
"""Draft frame while no message_id exists; None = not applicable / drafts just failed.
Skipped when finalizing (the real send clears the draft), EXCEPT stream-is-the-message
adapters keep ONE stream per turn: a segment-break finalize must not become a real
send (it would seal at every tool boundary)."""
stream_is_msg = self._stream_is_message()
if finalize and not (stream_is_msg and not is_turn_final):
return None
frame_text = pre_fence_text if stream_is_msg else text
# Strip the cursor: native streams render their own indicator, and
# "...text▉" is never a prefix of "...text more▉", which forces the
# connector's whole-text re-append on EVERY tick (stacked copies).
if self.cfg.cursor and frame_text.endswith(self.cfg.cursor):
frame_text = frame_text[: -len(self.cfg.cursor)]
if frame_text == self._last_sent_text:
return True
# Deliberately NOT _already_sent on success: the gateway's fallback final
# send must still fire so the user gets a real message.
return True if await self._send_draft_frame(frame_text) else None
async def _first_send(self, text: str, *, finalize: bool) -> bool:
"""First send, threaded to the user's message (correct topic/thread)."""
if getattr(self, "_egress_declined", False):
# The connector refused this destination earlier in the run (see
# _send_draft_frame). This is where every fallback path converges,
# so the check belongs here rather than at each caller.
logger.warning(
"suppressing the plain-send fallback: the connector already "
"declined this destination for this run"
)
return False
result = await self.adapter.send(
chat_id=self.chat_id, content=text, reply_to=self._initial_reply_to_id,
metadata=self._metadata_for_send(final=finalize, expect_edits=not finalize))
if not result.success:
self._edit_supported = False
return False
self._already_sent = True
self._last_sent_text = text
if result.message_id:
self._adopt_message_id(result.message_id)
self._track_preview_ids_from_result(result)
else:
# No editable id: fallback mode + sentinel so we don't re-enter first-send.
self._enter_fallback_mode(self._visible_prefix())
self._message_id = "__no_edit__"
self._notify_new_message()
return True
async def _edit_existing(self, text: str, *, finalize: bool, is_turn_final: bool) -> bool:
"""Edit the live preview (or replace it via fresh-final when finalizing)."""
# REQUIRES_EDIT_FINALIZE adapters need the finalize=True edit even when
# unchanged; everyone else short-circuits.
if text == self._last_sent_text and not (finalize and self._adapter_requires_finalize):
return True
# Fresh-final: replace a long-lived preview with a fresh message, or whenever
# the adapter prefers it (Telegram's send path renders richer markdown). An
# explicit hook returning False must NOT be overridden by the time threshold
# (delete is best-effort; both messages would stay on screen). Check the
# CLASS (MagicMock auto-creates attrs) plus instance __dict__ (test doubles).
has_prefers_hook = (
hasattr(type(self.adapter), "prefers_fresh_final_streaming")
or "prefers_fresh_final_streaming" in getattr(self.adapter, "__dict__", {}))
prefers_fresh = self._adapter_prefers_fresh_final(text) # probed every edit (hook contract)
if finalize and (
prefers_fresh or (not has_prefers_hook and self._should_send_fresh_final())
) and await self._try_fresh_final(text, is_turn_final=is_turn_final):
return True
result = await self._edit_message(message_id=self._message_id, content=text,
finalize=finalize)
if not result.success:
return await self._on_edit_failure(result, text, finalize=finalize,
is_turn_final=is_turn_final)
self._already_sent = True
self._track_preview_ids_from_result(result)
# Oversized edit split across continuations: message_id is now the LAST
# continuation, which holds only the final chunk — retarget edits and reset
# skip-if-same. getattr keeps SimpleNamespace test mocks working.
if ((getattr(result, "continuation_message_ids", ()) or ())
and result.message_id and result.message_id != self._message_id):
self._last_edit_overflowed = True
self._turn_split_delivery = True
self._adopt_message_id(str(result.message_id))
self._last_sent_text = ""
self._notify_new_message()
else:
self._last_sent_text = text
self._flood_strikes = 0
return True
def _enter_fallback_mode(self, prefix: str) -> None:
"""Edits are over for this stream: send only the missing tail at got_done."""
self._fallback_prefix = prefix
self._fallback_final_send = True
self._edit_supported = False
self._already_sent = True
async def _on_edit_failure(self, result, text: str, *, finalize: bool, is_turn_final: bool,
) -> bool:
"""Classify a failed edit: partial overflow, flood backoff, or fallback mode. Always
False; the caller's finalize path may still deliver the tail."""
# P5(b): an AUTHORIZATION decline is terminal for the run. Every branch
# below treats a failed edit as "editing is unavailable" and hands the
# unseen tail to the fallback, which SENDS it as a new message to the
# chat the connector just refused. Measured: ops were
# ['edit', 'edit', 'send'].
from gateway.relay.egress import declined_send
if declined_send(result):
logger.warning(
"edit DECLINED by the connector's egress guard; suppressing "
"every later send for this run (the destination is not "
"approved for this connection)"
)
self._egress_declined = True
self._edit_supported = False
return False
turn_final = finalize and is_turn_final
if (turn_final and self.cfg.cursor and self._last_sent_text.endswith(self.cfg.cursor)
and self._visible_prefix() == text):
# Cosmetic final edit was rate-limited but the full answer is already on
# screen (cursor stuck): mark delivered so the gateway doesn't send it
# twice, and record the on-screen payload.
self._final_content_delivered = True
self._record_turn_final_payload(text)
# ``text`` is already cleaned/fence-closed here and equals the visible prefix — the on-screen
# content IS this finalize payload (#71643). Record it on split turns too: post-#78541 an unrecorded
# split reads as a mismatch and would re-send this already-visible answer, reintroducing the
# duplicate #45517 fixed (#36965 / #25349).
raw_response = getattr(result, "raw_response", None)
if isinstance(raw_response, dict) and raw_response.get("partial_overflow"):
# Some overflow chunks landed but not the whole response: preserve the
# visible prefix so got_done sends the missing tail.
self._message_id = str(raw_response.get("last_message_id") or result.message_id
or self._message_id)
delivered_prefix = raw_response.get("delivered_prefix")
if isinstance(delivered_prefix, str) and delivered_prefix:
self._last_sent_text = delivered_prefix
self._fallback_preserve_partial_messages = text.startswith(delivered_prefix)
self._enter_fallback_mode(delivered_prefix)
else:
self._fallback_preserve_partial_messages = False
self._enter_fallback_mode(self._visible_prefix())
if getattr(result, "continuation_message_ids", ()):
self._notify_new_message()
return False
# Flood control: adaptive backoff (double the interval); disable edits only
# after _MAX_FLOOD_STRIKES in a row.
immediate_final_fallback = False
if self._is_flood_error(result):
self._flood_strikes += 1
self._current_edit_interval = min(self._current_edit_interval * 2, 10.0)
logger.debug("Flood control on edit (strike %d/%d), backoff interval → %.1fs",
self._flood_strikes, self._MAX_FLOOD_STRIKES, self._current_edit_interval)
immediate_final_fallback = (
turn_final and getattr(self.adapter, "FALLBACK_ON_FINAL_EDIT_FLOOD", False) is True)
if self._flood_strikes < self._MAX_FLOOD_STRIKES and not immediate_final_fallback:
self._last_edit_time = time.monotonic() # honor the new interval
return False
if immediate_final_fallback:
logger.debug("Turn-final edit hit flood control; entering fallback immediately")
logger.debug("Edit failed (strikes=%d), entering fallback mode", self._flood_strikes)
self._enter_fallback_mode(self._visible_prefix())
# A turn-final flood skips the cosmetic cursor strip: it would burn the same
# flood budget and delay the answer.
if not immediate_final_fallback:
await self._try_strip_cursor()
return False