Commit Graph
19 Commits
Author SHA1 Message Date
sam e0b6aa6105 feat(workflow): post line-anchored review comments with suggested fixes (#891)
* feat(workflow): post line-anchored review comments with suggested fixes

Bead archie-core-q9au (docs/prds/inline-review.md). A review's findings reached
the operator only as a flat list in the PR body, so the author had to map every
finding back to its line by hand and apply mechanical fixes by hand. Now the
line-anchored findings are also posted as inline review comments, carrying a
one-click suggestion when the reviewer could state the fix.

Domain (internal/domain/workflow):
- ReviewFinding gains Suggestion; Validate rejects one on anything but a
  confirmed finding, so the agent's record_finding call is refused with
  something it can act on. Validate splits into validateAnchor /
  validateClassification / validateDisposition, which also brings it back under
  the cyclop limit the gate enforces.
- StagePostReviewComments runs after StageOpenPR in the implement workflow. It
  posts only line-anchored findings (Line > 0); a whole-file finding has no line
  to attach to and stays in the body list, which remains the complete record.
  It is best-effort: the PR is open and the body already lists every finding, so
  a failed comment is logged, never a park -- the same reasoning as OpenPR's
  existing best-effort LinkBranch call.
- The suggestion fence is gated on Verdict == confirmed where the fence is
  written, because it is a one-click apply: a wrong suggestion breaks the code
  and the author has to notice.

Forge (internal/forge): ReviewCommentWriter + GitHub/Gitea implementations,
type-asserted like PullRequestReader so a forge that cannot is skipped rather
than faked (NoopForge is pinned as not satisfying it). GitHub loops one
CreateComment per comment and joins the failures, so one refused anchor cannot
drop the rest; Gitea carries them on a single COMMENT-state review.

Two deliberate departures from the PRD's sketch, both recorded in it:
- The interface is batch (CreateReviewComments), not one call per comment:
  Gitea's only inline shape is one submitted review, and the set then crosses
  NATS once instead of once per finding.
- The head SHA is resolved inside each forge implementation rather than by the
  caller. The stage runs in archie-agent, which holds no forge credentials and
  has no PullRequestReader; the daemon-side forgerpc handler is the only place
  that does.

Transport (internal/forgerpc): workflow.Forger gains the method, so the agent
reaches the daemon over the new create_review_comments subject; the server
type-asserts the writer and answers an incapable forge with an error the stage
logs. This is the one proxied method whose absence on an image skew does not
park a task.

The reviewer prompt and record_finding schema ask for a suggestion on a
confirmed, mechanically fixable defect only.

Regenerating the wfextract symbol table -- the documented way a new exported
workflow symbol reaches interpreted stage plugins -- also picked up symbols that
were missing from the committed table (the Status* and Source* constants,
ReviewCheck, Store, Task, and the _Store wrapper). Nil-guards were re-applied to
every wrapper afterwards, as that file's header requires.

Evidence: task check exit 0 (incl. 229 UI tests). Three mutations of the new
stage logic each fail a test that names the behaviour -- dropping the
confirmed-only gate, dropping the Line > 0 filter, and letting a posting failure
escape -- so the tests discriminate rather than passing vacuously.

* fix(build): drop the Dockerfile pin assertion

The guard fetched golangci-lint's go.mod at image build time to fail the build
when GOLANGCI_LINT_VERSION and GOFUMPT_VERSION disagreed. It only ever tripped
on self-inflicted pin drift, but it added a network fetch and a new failure
mode to the release build, which is not where that belongs.

The pins stay correct (golangci-lint 2.13.2, whose vendored gofumpt v0.11.0
equals GOFUMPT_VERSION) and the comment above them still states the invariant,
so the reasoning survives without the build-time machinery. The pin change
itself reaches the agent image through the normal release path: CI rebuilds
and pushes archie-agent on an archie/vX.Y.Z release, and a gateway-only
release deliberately does not.

* feat(workflow): add the remediate workflow for PR review remediation

Implements step 5 of docs/prds/pr-review-remediation.md: a remediate
workflow that resumes the task's existing worktree onto its PR branch
(worktree.Manager.Resume, not Prepare's refresh), runs a builder agent
against the review's actionable comments, commits and pushes to the
same branch, and replies via the forge's ReplyToReview. Task.RetryCount
doubles as the remediation round counter, capped by the repo's
max_retries; the round-cap stage parks the task and posts one comment
when it's hit.

Task gains a ReviewPayload field (JSON-encoded review unit) with full
store/proto/staterpc plumbing. workflow.Forger gains Comment and
ReplyToReview, proxied to archie-agent via a new forgerpc RPC. Resume
and its Dir lookup are added as an unexported optional Trees capability
rather than widening the exported interface, which is already at
golangci-lint's interfacebloat cap and is projected into wfextract's
Yaegi symbol table for repository-authored stage plugins.

The daemon-side reaction consumer that dispatches into this workflow
(subscribing ARCHIE_REACTIONS, grouping comments by review, enforcing
per-task serialization) is tracked separately in archie-core-8li9.4.

* feat(messaging): extract standalone messaging service binary and process composition

* feat(messaging): adapt channel frontends to consume Gateway ChatContract

* feat(messaging): remove in-process channels and Router from daemon bootstrap

Telegram, email and webhook now run only in the Messaging Service, which
reaches this process through the Gateway's ChatContract. The daemon builds
no channel and no gateway.Router, so the wiring that existed only to serve
them goes with it: setupGateways, setupEmailGateway, setupWebhookGateway,
setupTelegramGateway, buildTelegramRouter, makeTelegramReload and the
release-announcement path helper.

The seams those paths owned move to where they can still be honoured:

- Channel ValidateConfig runs in archiemessaging.compose, which now returns
  an error, so a configured-but-invalid front-end fails the service rather
  than being dropped silently.
- The inbound rate limiter moves to the Gateway process, which owns the only
  Router and therefore the only place a per-sender budget applies to every
  channel's turns.
- The daemon's gateway readiness probe becomes a ContractProbe against the
  Gateway. It cannot observe a channel lifecycle it no longer runs, and a
  channel-count probe would have reported every daemon degraded.
- telegramSetup is now chatSetup (in chat_setup.go), trimmed to the fields a
  chat turn runner actually reads.

Telegram operator features that were wired only in the daemon (/update,
release announcements, version reporting, SIGHUP reload) are not yet wired
in the Messaging Service: archie-core-8cda.6.6. Channel lifecycle reporting:
archie-core-8cda.6.8. The Gateway process builds no worktree manager, so
review_pr is unadvertised on every channel: archie-core-8cda.6.7.

* feat(messaging): re-wire the Telegram operator surface in the Messaging Service

setupTelegramGateway satisfied eight telegram.Gateway seams from the daemon's
own process. Each is resolved by where the fact it needs is owned, not by
where it used to be built; the decision table is in
docs/architecture/migration-decisions.md.

Wired here: /update (built from this service's own [chat.telegram] check and
install commands), the update-report relay (same sha256(bot_user)[:8] path the
daemon wrote, so a pending report is found rather than written afresh),
show_tool_calls, and /restart's config reload, which re-resolves the token and
allowlist from this service's own file and refuses a reload that resolves to
an empty token.

/version is sourced from the Gateway: ChatSnapshot gains a Version field
carrying the Gateway's rendered build block, read per call and bounded by the
dependency timeout. cmd/archie-messaging deliberately takes no version
ldflags, so it cannot report a partial upgrade as a matched one.

RunningVersions and ReleaseAnnouncements stay nil. Both need a component's
real running version, and the only versions this process can obtain are a
different binary's stamps -- reporting them would manufacture exactly the
false success the update check exists to catch, and the announcer without
parseable versions is a no-op that reads as configured. archie-core-8cda.6.9
carries the contract that unblocks them. Dangerous stays nil: no composition
has ever supplied a command authority.

Enrich is dropped from the update service: componentInstallTypeEnricher read
[nats], which this service must not decode, so the check command's own
reported install type stands.

* fix(workflow): guard inline review comments against head drift

Two findings from the review of q9au.

A comment's line numbers describe exactly one revision of the branch, but the
forge resolved the pull request's head at posting time -- after the review had
already read the worktree. A push in that window (a collaborator, a retry) meant
the findings were anchored to whatever now occupied those lines, mislabelling
instead of failing. The revision the review measured now travels with the
comment set: OpenPR records it from the same worktree read it already performs
(TaskContext.ReviewedHeadSHA), StagePostReviewComments threads it through
Forger to forgerpc, and the forge refuses the whole set once the head it reads
has moved off it -- which the best-effort stage logs, the PR body remaining the
record. An unmeasured revision posts unverified rather than dropping every
finding, so a worktree that cannot report one degrades instead of regressing.

Suggestion was documented single-line only, because GitHub applies a suggestion
fence up to its first line and a multi-line replacement would silently corrupt
the file. Only the verdict was validated, so a multi-line suggestion reached the
renderer and posted as that truncated fence. Validate now rejects an embedded
newline, which makes record_finding refuse it with feedback the model can act on
instead of the reviewer discovering the corruption later.
2026-09-19 23:37:23 +10:00
sam 3b266c71ce fix(telegram): keep every tool line that fits and mark every answer cut
Two defects in the activity/answer budget, both found in review.

The tool block returned as soon as the newest line alone fit, so a turn with
several short tool calls discarded history that was never over budget and
reported a "+N earlier" that was untrue -- those lines had room. The window
now widens from the newest line backwards while the result still fits, so
every line that fits is kept. The indicator appears only when something is
genuinely left out.

The opening frame sliced the answer to its budget without an ellipsis, so a
large first chunk -- or a turn that never opened a reply, leaving messageID 0
-- rendered text that appeared to begin mid-sentence, while later frames
marked the same cut. Telegram messages are immutable, so it could never be
corrected. Every frame now marks the cut; the special case only ever bought
one rune.

TestLiveReplyFramesStayWithinOneMessage asserted the ellipsis on the last
frame only, which is what let the unmarked opening frame through. It now
checks every frame, and the count bound follows: identical frames are
deduplicated by render(), so an unmarked opening frame was previously a
distinct body where a marked one is not. Verified by mutation -- restoring an
unmarked opening cut fails the test on frame 0.
2026-09-17 11:40:08 +00:00
sam 9bbce39df2 chore(telegram): resolve the state-store test conflict and drop dead clamp helper
Rebased onto main, which now carries an equivalent STATE_STORE_TOKEN isolation
guard in state_store_client_test.go from an independent baseline repair. The
two changes were the same fix expressed twice, so main's wording is kept and
this branch's duplicate is dropped -- the file is now identical to main and no
longer appears in the diff.

That leaves one commit, touching only internal/channels/telegram/live.go.

Removing clampToOneMessage, which this change orphaned: all three of its call
sites were replaced with clampToRunes directly, and `unused` flagged it. Dead
code left behind by a rewrite does not ship.
2026-09-17 11:31:05 +00:00
samcharles93 8dd8841a7a Telegram tool-activity block is uncapped and crowds out the answer (archie)
Implements #839
2026-09-17 11:27:52 +00:00
sam da28ddb5e6 refactor(ui): sever the archie-ui binary from every daemon runtime package
Completes the objective deletion gate for the UI Service
(archie-core-8cda.5.6): go list -deps ./cmd/archie-ui now links zero
banned packages -- no modernc.org/sqlite, no internal/store, gateway,
channels, memory, secret, agentexec, tools, skill, yaegiutil, curator,
or the workflow engine. The closure shrinks from 68 to 26 archie-core
packages. Each cut is a producer-side move; no consumer-side defensive
shims.

- Store contracts (TaskStore family, value types, sentinels) moved from
  internal/store to internal/domain/storecontract -- the approved contract
  location per state-store-contract rev. 2d, and NOT internal/contracts:
  that tree is buf generate output and tools/proto.sh check deletes
  hand-written files there. internal/store keeps aliases; sentinel
  message strings are byte-identical and remain the wire contract.
- Chat contracts (ChatContract, sessions, turns, streaming, commands)
  moved from internal/gateway to internal/domain/messaging; gateway keeps
  aliases. ToolCallEvent rendering helpers become gateway functions
  (methods cannot live on alias types).
- Task vocabulary (Task, statuses, mid-run Store, Definition) split into
  internal/domain/workflow/task; the pipeline engine stays in package
  workflow with aliases, so daemon-side callers are unchanged.
- overlay.DeniedKeys moved to internal/infrastructure/configuration:
  webui referenced the constant and that dragged the overlay SQLite
  store in.
- webui.Server's concrete runtime handles become webui-owned view
  interfaces with daemon-side bootstrap adapters: channel lifecycle
  (internal/channels/status), MemoryStatus, CuratorStatus, and a
  SkillCatalog seam replacing the direct skill.DefaultRoots/CatalogRoots
  calls. Each degrades to an empty page when unwired.
- config.SecretRef moved into internal/config (config vocabulary);
  internal/secret keeps an alias and Registry.Resolve absorbs the
  zero-value short-circuit.

Docs: state-store-contract rev. 2d relocation record; ui-service-boundary
deletion gate marked satisfied; ARCHITECTURE.md package map rows.
2026-09-10 03:03:33 +10:00
sam b966f6bd03 fix(telegram): send undelivered-media fallback after finalize as its own message
Closes archie-core-atv2.

Media delivery is fire-and-forget with a 30s budget, far longer than
the turn's text usually finishes -- so a large upload failing (or
timing out) after doFinalize has already retired the renderer goroutine
is the normal case, not an edge one. appendFallbackLine was still
writing into toolLines and calling requestRender, a non-blocking send
into a channel nothing reads any more once stopRendering has returned:
the line was silently dropped and the finalized message stood
unchanged, with nothing telling the user or the agent the file never
arrived.

stopRendering is the single point every finalize/abandon path funnels
through to retire the renderer, so it's the right place to mark the
reply finalized. appendFallbackLine now checks that flag and, once
set, sends the fallback as its own follow-up message instead of
appending to a buffer nothing will render again.
2026-09-02 01:18:54 +10:00
sam 47b17833cd refactor(telegram): render replies as structured rich blocks
Telegram's rich-message Markdown has no ATX heading support and its MarkdownV2
dialect needs escaping, so hand-building a Markdown string and sending it as
myMarkdown showed literal heading/code markers and mangled unescaped characters.
The previous fix layered blank-line insertion on top of a dialect that could
not render headings at all.

Replace the whole markdown-string pipeline with structured InputRichMessage
blocks: markdownToBlocks emits SectionHeading, Preformatted, List, BlockQuotation
and Paragraph (inline emphasis/code/links reduced to plain text so no marker can
leak), blocksToPlainText feeds the fallback send, and splitBlocks chunks at block
boundaries. sendBlocks, open, edit and the live renderer now send myBlocks.

Delete the dead string surgery (normalizeTelegramText, telegramMarkdown,
telegramPlainText, splitLongMessage, the fence-split cluster and their regexes)
and the tests that pinned it, removing about 1100 lines. splitBlocks and the
parser are unit-tested.
2026-08-28 01:42:09 +00:00
sam 7520e15778 fix(telegram): keep Markdown headings/lists as blocks and strip Markdown on plain fallback
- insert blank lines around ATX headings and list blocks so Telegram does not
  collapse them into the surrounding paragraph
- leave the SDK's compact triple-backtick tool fences unstyled (do not re-space)
- strip Markdown syntax when the rich send/edit falls back to plain, so the
  user never sees raw '#', '**', backticks or link brackets
- log telegramRenderVersion + mode on every outgoing message
2026-08-27 23:33:24 +00:00
sam e5e0316475 feat(telegram): send local files as uploads, not fetchable URLs
The agent could produce a file -- a transcript, a log dump, a screenshot --
and had no way to hand it over. Asked to send one it offered a "download"
link; nothing arrived and it had no signal that anything had failed. The
defect was not that it lied: success and silent non-delivery were
indistinguishable to it.

Three places made a local file undeliverable, and each is fixed here:

  - liveReply.Media skipped any attachment with an empty URL, so a local
    file was dropped before it ever reached a sender.
  - telegramMediaSender built every attachment as models.InputFileString,
    which tells Telegram to FETCH the string as a URL. A host path is not
    fetchable, so the send did nothing while reporting success. It now
    chooses by what the attachment carries: URL -> fetch, Path -> upload
    via models.InputFileUpload over an open file.
  - Nothing let the agent ask for a send at all. New send_file tool
    (internal/tools/sendfile) validates the file and returns a
    MultimodalResult naming it; the turn's channel delivers it.

Meaning changes, called out because the names did not:

  - MediaAttachment gains Path, the alternative to URL. Exactly one is
    meaningful for an outbound send.
  - tools.MultimodalResult.URLs used to mean remote-hosted media only; it
    now means media this result wants delivered, which may be local. JSON
    name unchanged so existing producers keep working.
  - errNoURL is now errNoSource: having neither source, not having no URL,
    is what makes an attachment undeliverable.

Failures are visible at every layer, which is the actual fix. send_file
errors on an absent, irregular, unreadable, oversized or confinement-
refused path, so the model sees it and can report it. The sender checks
Telegram's ceilings (10 MB photos, 50 MB otherwise) before the request and
reports the real size rather than leaving a 400 nobody reads. A delivery
that still fails now appends "could not send <name>" to the reply instead
of an empty link, which read as a delivered file.

Exposing a public URL for local files was explicitly rejected: it trades a
missing feature for a hosting and access-control problem.

send_file resolves paths through builtin.ResolveReadable -- the read tool's
own policy, exported rather than reimplemented -- so sending cannot reach
what reading cannot, whatever [chat] unrestricted_filesystem is set to.
2026-08-25 01:43:15 +10:00
sam cc53e5258d fix(telegram): compact tool output and drop turn caps
Render completed ToolCallEvents as Telegram-safe streaming blocks
with compact name/status and a short cleaned preview. Summarize
file contents and listings instead of dumping source or quoted
JSON. Collapse repeated legacy turn-budget failures.

Remove max_tokens turn gating and the 200000 turn_budget_chars
default so absent or commented config cannot restore an aggregate
cap. Keep per-result max_result_chars and spill.

Confine find/grep discovery to the active workspace/worktree.

Refs #604
2026-08-23 16:40:16 +00:00
sam fe7246be33 fix(telegram): render tool progress as bounded code blocks 2026-08-23 15:34:38 +00:00
sam d7308b9207 feat(telegram): deliver media attachments, capability-gated
telegramMediaSender routes a MediaAttachment to the matching Bot API
method (sendVideo/sendPhoto/sendAudio/sendDocument) rather than
sendMessage, which cannot carry a file. It is constructed per-launch
from the same *bot.Bot the update handler already has, matching
telegramApprover's lifetime rule: a /restart abandons an in-flight
send against the outgoing bot instance rather than silently
redirecting it through the new one.

liveReply.Media wires TurnStream into this: it checks
gateway.CapabilitiesOf before attempting delivery -- not just on
failure -- so a sender that already knows it cannot deliver a given
media kind never costs a doomed network round trip. Either path
(capability-limited or a failed send) falls back to rendering the
attachment's URL as a visible link, so a generated asset is never
silently dropped.

newMediaSender is an injectable field so tests can prove the
capability check actually short-circuits, since the real Telegram
sender always reports Media: true and can't exercise that path
itself.
2026-08-23 02:48:01 +10:00
sam b5064e570f fix(telegram): preserve URL boundaries in responses
Keep bare GitHub issue and pull-request links separate from following prose across one-shot sends, live edits, and long-message splitting. Preserve Markdown delimiters and newline boundaries while retaining plain-text fallbacks.
2026-08-15 23:09:28 +10:00
sam c2b6823eba fix(telegram): guarantee no message is stranded on gateway stop/restart
A daemon shutdown or /restart cancels turnCtx without any guarantee
that the goroutine owning a liveReply ever runs again to notice and
clean up after itself -- a full process exit gives it no chance at
all. Gateway now tracks every liveReply mid-turn in a registry and
Stop drains it, marking each as interrupted so nothing is left ending
in the "typing" cursor forever.

finalize and abandon now run their bodies inside a per-reply
sync.Once (the terminal field): a turn finishing naturally and a
concurrent Stop draining the same reply were reaching it from two
goroutines at once, both sending their own edit for the same message
with the outcome decided nondeterministically by which HTTP response
Telegram processed last -- including a complete real answer getting
silently overwritten by the restart marker. Only one side's body now
ever runs; the other blocks on the winner and then does nothing.

The drain itself is bounded (liveDrainTimeout, default 5s): a single
stalled Telegram API call must not hang gateway, and therefore
daemon, shutdown indefinitely. Entries still in flight past the
deadline keep running in the background rather than blocking Stop.

A liveReply created in the narrow window between Stop claiming the
registry and its own registration call is abandoned immediately
instead of being registered into (and lost from) a registry nothing
will drain again.

Regression tests cover the mutual-exclusion race directly (20
iterations of finalize and abandonRestarted racing on the same
reply, asserting exactly one outcome ever wins), the bounded drain
against a deliberately hung API call, and the post-stop registration
gap.
2026-08-15 02:19:53 +10:00
sam b6505f0232 docs(telegram): note the live-edit timestamp trade-off on liveReply
The finished reply is delivered by editing the message created at the
first streamed frame, and editMessageText does not change a
message's date, so a long tool-using turn's answer keeps its
turn-start timestamp and can sort before conversation that produced
it. Delete-and-resend would fix the ordering but reintroduce the
flicker/reorder streaming exists to avoid, so this documents the
accepted trade-off rather than changing behavior.
2026-08-15 01:48:33 +10:00
sam baef64163a fix(telegram): keep tool activity visible and mark failed/empty turns
Three more P2s from the same code-review pass: the live frame's
single clamped buffer mixed tool lines and answer text chronologically,
so early tool lines silently scrolled out of the frame once the answer
grew past liveBodyMaxRunes and only reappeared at finalize (which
already led with tools separately). Tool lines are now tracked
exclusively in toolLines; a new framedText helper keeps the tool block
whole and clamps only the answer tail, used consistently by the live
frame, an abandoned frame, and the finished message.

A tool-only turn with no reply text used to finalize as a bare,
immutable tool line indistinguishable from a real (if terse) answer;
finalText now appends an explicit "(no response)" marker in that case.

A provider error used to funnel into the same clean-partial path as a
deliberate /stop, so a failed turn was indistinguishable from a
successful short one. abandonFailed appends a "turn failed" marker
before dropping the cursor; /stop still goes through the unmarked
abandon path.

Regression tests cover all three paths plus the degenerate case where
a tool block alone exceeds the frame budget, verified red-then-green
against the pre-fix code.
2026-08-15 01:25:20 +10:00
sam 240c91a117 fix(telegram): harden live-reply delivery against /stop and multi-byte content
Three P1s from code review of PR #476: finalize sent the authoritative
reply through the same cancellable turnCtx a /stop kills, so a stop
landing mid-finalize stranded the live message with its cursor
forever; abandon had the identical hazard, saved only by its one
caller wrapping the context correctly. Both now strip cancellation
internally (context.WithoutCancel) rather than trusting callers to
remember.

Tool activity lines were composed unescaped into the same Markdown
body as the model's own reply, so a stray '*', '_', or backtick in
tool output/parameters could unbalance the whole message and take the
reply's formatting down with it. ToolCall now runs name, parameters,
and summary through bot.EscapeMarkdown before joining the line.

splitLongMessage sliced oversized lines on byte offsets, cutting
mid-rune for any multi-byte UTF-8 line crossing the 4000-byte bound
(CJK, emoji) and producing invalid UTF-8 parts. It now counts and
slices on runes throughout.

Regression tests cover all four paths, verified red-then-green
against the pre-fix code.
2026-08-15 01:06:27 +10:00
sam 0bbd6e75de fix(chat): harden inline tool call streaming
Telegram streaming callbacks now enqueue cancellable rendering rather than performing network I/O while draining the authoritative model stream. Final edit failures fall back to normal split delivery.

Completed tool events now correlate inputs by call ID and expose only bounded, conservative parameter shapes. Tool-call visibility is snapshotted per reply so reloads cannot change an in-flight turn.
2026-08-14 04:52:48 +10:00
sam 0d73f2fa5a feat(chat): show tool calls inline and stream replies into one message
Chat returned only the final answer, so a wrong tool choice, a
hallucinated action, or a footgun like `systemctl stop` against
`restart` was invisible from the conversation. Only text deltas were
threaded through the turn, and tool calls executed inside Generate with
nowhere to report.

Replace the delta callback with gateway.TurnStream, which carries text
fragments and completed tool calls on one ordered path from the model
loop to the channel. The sequence is the point: a tool line that
overtakes the sentence it interrupted describes a turn that never
happened. Text-only callers use gateway.DeltaFunc and are unaffected.

A tool is reported on its result, never on its call  --  the call part
carries no outcome yet, so reporting both would list every tool twice,
once with nothing to say.

Telegram renders it behind [chat.telegram] show_tool_calls, off by
default: this is debugging visibility, and it narrates every internal
step to provide it. The dashboard always shows it, being the operator's
own observability surface; its tool lines are live-only and are not
persisted with the conversation.

The Telegram live reply changes mechanism, and with it what a frame
MEANS. It used to stream through sendMessageDraft: drafts are ephemeral
30-second previews, so a tool call longer than that outlived the
preview, and successive frames were observed concatenated with their
cursors intact. It now sends one real message and edits it. An update
used to be "the next preview of the answer"; it is now "the whole
answer as it currently stands, replacing what is there". The cursor is
appended at render time and never stored, so exactly one exists and
always at the end, and a frame too long for one message is cut to its
tail rather than rejected outright.

A stopped or failed turn now edits the cursor away instead of leaving
it blinking on a message nothing will finish. That cleanup runs on a
live context because turnCtx is already dead, and it runs on both
failure branches: ai-sdk raises an aborted stream as ErrAborted with
ctx.Err() formatted in rather than wrapped, so errors.Is cannot be
trusted to tell a /stop from a fault.

Closes #467
2026-08-14 02:36:12 +10:00