Commit Graph
152 Commits
Author SHA1 Message Date
sam 5a92fc17a5 refactor: remove unused Operator param. 2026-08-29 00:20:40 +10:00
sam b2da85ead1 refactor: go modernisation fixes 2026-08-29 00:20:05 +10:00
sam 0af19ba983 refactor: remove unnecessary AI shit 2026-08-29 00:16:43 +10:00
sam ea1017af94 feat(webui): dashboard-aware chat — Archie sees the page, points you there
The web chat is now a persistent slide-over drawer available on any page
(not just the /chat route), and the agent is told which dashboard page the
operator is on so it can point them to the relevant page with a clickable chip.

Backend (gateway):
- Message gains a per-message Page field; the system prompt renders it in
  the <env> block (Current page), so Archie knows where the operator is.
- New dashboard_tools.go: a DashboardPages registry plus two web-only tools
  — page_index (lists every page and what it shows) and dashboard_navigate
  (validates a path, returns {path,label}; rejects unknown/empty paths).
- The web chat sink emits a dedicated navigate stream event when the model
  calls dashboard_navigate, independent of ShowToolCalls.

Frontend (webui):
- chat sends currentPage() (location.hash) with each stream request; a
  dashboard_navigate result renders as a clickable link chip (href=#/path).
- The chat is mounted once in a slide-over drawer with a topbar launcher,
  scrim and Esc-to-close; /chat opens the drawer instead of a second page.
- ui/dist rebuilt (committed) with the bundled changes.
- .gitignore: ignore .impeccable/ (impeccable tool critique snapshots).

New capability (per scope discipline): designed in
docs/prds/dashboard-aware-chat-navigation.md.

Tests: dashboard_tools_test (registry, resolve/reject, web-only gating),
prompt page-line cases, webui Message.Page + navigate-frame capture, and
chat-tools chip tests. task check is green.
2026-08-28 22:28:10 +10:00
sam 96c82cd4e0 feat(tasks): allow rejecting a task from any non-terminal state
An operator could only reject work that was waiting on a human decision, so a
task sitting in review (PR open) or running had no way to be refused even
when it was clearly dangerous.

- expose reject in taskstate.Actions for every non-terminal state (queued,
  running, waiting_human, parked, pr_open) so both the dashboard and the chat
  tool surface it; terminal states still only expose archive
- make rejectTask transition from the task's actual status to closed_wont_do
  and interrupt running execution first, so nothing keeps working against a
  task being closed out
- keep the distinct stop (recoverable → parked) semantics; reject is the
  terminal escape hatch
- update the lifecycle contract tests to the new intent
2026-08-28 00:19:27 +00:00
sam 48133e68fe feat(logging): cursor pagination and filtering for task_logs
task_logs could only read the newest N entries with no way to walk the
rest, so a task's log beyond the page cap was unreachable and the agent
had no honest way to say what was missing. Add logging.Page -- a
byte-offset cursor over the tail-most 8 MiB scan window -- plus
Query.Since/Until time bounds, and wire the gateway's task_logs tool to
expose level/since/until/after_id with cursor and more_available in the
result.

The reader now reads the scan window into a single in-memory buffer and
walks it by exact slice offsets. Offsets into a contiguous buffer are
trivially correct, which an incremental reader over the file is not:
bufio.Reader buffers ahead, so its underlying file position runs one
buffer past its logical position and cannot be used as a cursor. The
same rewrite removes f.Read in favour of f.ReadAt (full-or-error), since
a silent short read would drop the newest entries and still report
success.

The scan window is a documented hard ceiling: for a log over 8 MiB the
oldest bytes are unreachable by any cursor -- that is what Truncated
reports, and send_file remains the path for a complete archive. The
tool description teaches the model the difference between more_available
(more this call did not return) and truncated (older entries the scan
cap hides).

Closes archie-core-vq92 (#625).
2026-08-26 02:02:36 +10:00
sam 4b340d2b56 fix: harden task and chat execution
Task runs now preserve real model context limits, provider usage, baseline-repair spend, commit identity, durable agent-finish telemetry, and useful timeline details without imposing a token cap. Dashboard forge links are canonical per owning GitHub or Gitea identity. Chat turn claims acquire SQLite writer intent before reading, eliminating the concurrent SQLITE_BUSY snapshot race.
2026-08-25 05:48:17 +10:00
sam 9d2c1e661d fix(gateway): make UUIDv7 session references unambiguous 2026-08-25 03:28:38 +10:00
sam bb8cd3f687 fix(chat): restore transcript and update replay 2026-08-25 03:05:28 +10:00
sam 901864a9df merge: task_action chat tool (crew/taskact) 2026-08-25 02:05:25 +10:00
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 64da3952aa feat(gateway): add task_action chat tool for operator task management
Adds the task_action tool to internal/gateway/task_tools.go and wires it via
chatTaskActorAdapter in cmd/archied. This enables operators in chat to execute
lifecycle actions (abandon, archive, retry, stop, cancel, approve, reject) on
tasks using the same action path and state machine as the dashboard.

Enforces identity scoping so an instance cannot mutate another identity's
tasks, verifies status permissions via internal/taskstate, and classifies the
tool as mutating with required human approval.
2026-08-25 01:19:21 +10:00
sam ef75feb9b4 chore(gateway): apply go fix rewrites in stream.go
Pre-existing code `task fmt` rewrites on every run: a manual clamp to
`max`, and a `strings.Split` range to `strings.SplitSeq`. Both are
semantically identical; committing them keeps the gate from reporting a
dirty tree on unrelated work.
2026-08-24 13:28:51 +10:00
sam 3421be48a4 fix(telegram): corrected tool outputs to keep context of tool calls (#609) 2026-08-24 07:46:42 +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 2ff09193cd fix(update): install only approved components
Carry the revalidated update snapshot through the installer contract so the shell adapter receives an explicit per-component plan. Build, back up, install, and roll back only selected components, and pass the runtime release version into agent image builds.\n\nCovers gateway-only, runtime-only, combined, and no-op updates.\n\nRefs #606\nBead: archie-core-462t
2026-08-23 16:18:30 +00:00
sam fe7246be33 fix(telegram): render tool progress as bounded code blocks 2026-08-23 15:34:38 +00:00
sam 67d77edb01 fix(gateway): back off ClaimTurn race retries
The concurrent regression retried SQLITE_BUSY immediately, allowing the losing goroutine to exhaust all attempts before the winning transaction was scheduled to commit on GitHub Actions. Yield for one millisecond between bounded busy retries; non-busy errors still fail immediately and exhausted contention still fails the test.
2026-08-23 04:08:49 +10:00
sam 06d1922f38 fix(gateway): isolate ClaimTurn race trials
The regression used to start all 100 two-store races at once, so it measured global SQLite writer saturation as well as the same-turn insert race. GitHub Actions exhausted the immediate busy retries before competing transactions could finish. Each trial now still releases both independent stores together, but joins them before starting the next turn ID, preserving the intended race without unrelated cross-trial lock contention.
2026-08-23 04:01:21 +10:00
sam 7bbc31be15 fix(gateway): restore media result after adapter removal
BasePlatformAdapter used to own SendResult even though no live channel implemented that adapter contract. The adapter is now gone, but launch-scoped MediaSender values still need the delivery result to classify Telegram failures. Keep SendResult with the media capability contract and make the tests describe senders instead of reviving the dead lifecycle abstraction.
2026-08-23 03:27:44 +10:00
sam 485b55b95b Merge pull request #561 from samcharles93/worktree-federated-wiggling-milner
feat: video generation via MiniMax, with a channel media-delivery pipeline
2026-08-23 02:54:19 +10:00
sam 242ae53fdf feat(gateway): add MediaSender/CapabilityReporter and TurnStream.Media
Channels had no shared contract for delivering non-text tool output --
MessageEvent/MediaAttachment/MsgVideo existed but nothing produced or
consumed them. MediaSender and CapabilityReporter give a channel an
optional, capability-queryable way to deliver an attachment; TurnStream
gains Media(event) alongside Delta/ToolCall so a tool's media reaches
the channel in the same ordered pass as its text.

CapabilitiesOf takes any deliberately: it must not depend on the
soon-to-be-removed BasePlatformAdapter (archie-core-azbo), since the
live channels implement channels.Channel, not that interface.
2026-08-23 02:47:53 +10:00
sam 00c5e06152 refactor: remove dead BasePlatformAdapter code 2026-08-22 23:23:51 +10:00
sam 068a1f493a fix(gateway): replay completed-duplicate turns with their tool activity
A NATS redelivery or restart RecoverTurns redelivery hit the
TurnClaimCompleted branch in TurnRunner.Run and replayed only
turn.ResponseText, never the tool calls that produced it -- neither the
ledger nor the session store persisted them. The transcript showed the
original answer beside a tool-less duplicate, disagreeing about what ran.

TurnRecord now carries ToolCalls, saved in the same call as ResponseText via
a toolCallRecorder that tees Generate's TurnStream. The completed-duplicate
replay walks turn.ToolCalls into stream.ToolCall before replaying the text,
so a redelivered turn narrates the same activity as the original.

The other replay path (prior-reply, matched by conversation history rather
than turn ID) stays deliberately text-only: it exists for the crash race
where the assistant message was saved but the turn record was never
completed, so there is no persisted tool record for it to replay either.
Documented on Run's doc comment rather than left implicit.

Closes archie-core-ippu.
2026-08-22 20:43:29 +10:00
sam 311f5f71f9 fix(gateway): stop ClaimTurn's insert-race branch losing its own retry read
Found while investigating an `ineffassign` finding, not a stylistic report:
the branch handling "another connection inserted the same turn between our
read and insert" was discarding its own result.

`result, err := tx.ExecContext(ctx, ...)` for the INSERT sits inside
`if errors.Is(err, sql.ErrNoRows) { ... }`, a new block scope, with `result`
new to that scope -- so Go's `:=` declares a fresh, block-scoped `err`
shadowing the function's own `err` for the rest of the block, including the
retry read a few lines later (`err = tx.QueryRowContext(...).Scan(...)`).
That assignment landed in the shadow, which goes out of scope at the block's
closing brace. The `if err != nil` check afterward was therefore still
looking at the *original* err -- sql.ErrNoRows from the very first read --
regardless of whether the retry read succeeded. The loser of a genuine
insert race would always return `sessionstore: read turn: %w` wrapping
`sql.ErrNoRows`, contradicting the branch's own comment: "apply the normal
claim state machine instead of surfacing a uniqueness error."

Fix: the insert-path errors are now insertErr, not err, so the retry read's
plain assignment reaches the outer err the later check actually inspects.
Confirmed via careful trace of Go's block-scoping rules that this closes the
gap for the affected!=1 (loser) path without touching the affected==1
(winner) path, which returns from its own separately-scoped err before ever
reaching this one.

Commit the honest limitation along with the fix: a genuine two-connection
concurrent regression test could not be made to hit the exact branch. A
temporary, reverted-before-commit diagnostic (real concurrent race,
artificially widened with a sleep) showed the losing connection instead
fails its own INSERT outright with SQLITE_BUSY_SNAPSHOT under WAL mode with
this driver, before ON CONFLICT DO NOTHING can ever report 0 rows affected
-- meaning the specific branch this bug lived in may be effectively
unreachable via this driver/journal-mode combination today. The shipped
test verifies the weaker, still real property that matters operationally:
many genuinely concurrent same-turn-ID claims across separate connections
never produce the bug's error signature ("sessionstore: read turn:"),
distinct from unrelated SQLITE_BUSY/SQLITE_BUSY_SNAPSHOT lock contention,
which is retried rather than treated as a failure. The fix stands
regardless of provable live reachability -- the shadowing was unambiguous
and wrong on its own terms.

Adversarially reviewed by a fresh subagent, which independently reverted
just the fix (keeping the test) and confirmed empirically -- 20 runs, plus
1000 trials with a debug probe on the affected!=1 branch -- that the branch
is never reached under this driver, corroborating the test's own stated
limitation rather than contradicting it. gocognit/nestif findings on
ClaimTurn are pre-existing on the prior committed baseline, unchanged by
this fix (only variable names moved).
2026-08-22 02:03:27 +10:00
sam 7a40cc8636 fix(gateway): stop persona from asserting unverified claims as fact (#528)
The chat agent labelled unchecked figures "Verified details" and
fabricated an entire "Hermes gateway" subsystem with invented file
paths, stating both as confirmed fact until directly challenged.

Reword core rule 1 to separate static tool-capability claims (fixed
by the tool list) from dynamic file/memory/action/result claims,
which now must be verified this turn rather than merely "in this
conversation" -- the looser wording let a stale claim be treated as
still verified. Add rules 8 and 9: never label something
verified/confirmed without a this-turn tool check, and never state a
specific system detail (path, subsystem, count, config value) with
confidence unless just retrieved.

Fixes archie-core-3jag / GH#524.
2026-08-20 23:19:34 +10:00
sam 7c409aadb5 feat(update): stream live progress and roll back failed updates automatically
The /update command went silent between "starting" and one final message,
gave no version summary, and required manual intervention on failure.

CommandInstaller now streams the installer script's stdout live instead of
buffering it, and parses a structured result (previous/installed versions,
per-component status) from a sentinel line. Because the reference install
script hands the daemon restart off to a detached systemd unit specifically
so restarting archied.service doesn't kill the process that requested the
update, the outcome is reported in two phases: the synchronous build/install
result comes back through Install() itself, and the post-restart health
check/rollback outcome is written by a new watchdog script and relayed by
whichever archied process boots next, via a small JSON handoff file cleared
once relayed.

Also fixes three defects an adversarial review pass found in the first
draft: the caller's request/handler context was passed straight into the
install child process, so a concurrent /restart or a browser disconnect
could SIGKILL it mid binary-copy; Telegram and the web dashboard each
tracked "install in progress" with their own private flag despite sharing
one Service, allowing two installs to race the same .prev backups; and the
watchdog reported rolled_back:true even when no backup existed to restore,
which would have told an operator to stand down while the daemon was still
broken.

internal/webui gains an unauthenticated /healthz the watchdog polls after
restarting archied.
2026-08-19 01:47:29 +10:00
sam 8239e8e935 style: apply gofumpt formatting 2026-08-17 00:02:31 +10:00
sam 2c6a4f9adc fix(tests): check type assertions in overlay and gateway tests 2026-08-16 01:24:31 +10:00
sam 0dfdd72f83 feat(gateway): polish /status command response format
Format /status response with clear heading, visual task status icons, canonical lifecycle ordering, and separated runtime details with graceful fallbacks.
2026-08-15 22:43:41 +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
sam 1f71489f0a fix(gateway): harden session recovery paths
Repair future-dated conversation history on SQLite open and cap newly supplied timestamps so one bad platform clock cannot pin a session indefinitely.

Make message and turn identifiers injective while preserving legacy redelivery and crash-recovery compatibility, retire idle turn lanes safely, and pin the existing compression and partial-undo behavior with focused regressions.
2026-08-09 23:18:55 +10:00
sam 61b4b7b0cf refactor(store): replace legacy persistence with SQLite
Task and event persistence now uses a dedicated SQLite sidecar derived from the configured state prefix, matching the independently persisted conversation store. The configured path now means a state-path prefix rather than a database file so fresh SQLite state never attempts to interpret the previous storage format.

Remove the retired implementation and dependency completely, strengthen SQLite migrations and concurrency behavior, restore backend-neutral coverage, and align configuration, operational guidance, UI labels, and deployment documentation with the new storage and host-daemon topology.
2026-08-09 22:27:25 +10:00
sam e4385ef266 feat(webui,gateway): add /api/tasks/{id}/logs endpoint and task_logs chat tool
Adds two read surfaces for per-task persisted log history so an operator
can answer "why did task N park?" without needing to watch docker ps in
real time — the deployment model documented in CLAUDE.md.

/api/tasks/{id}/logs — built on logging.Tail the same way /api/logs
already is, defaults attempt to the tasks current Attempt from the store.

task_logs chat tool — lets Archie read task logs from Telegram or webui
chat. Identity enforcement matches chatTaskListerAdapter: a model bound
to one identity cannot read another identitys logs, and forge tasks
(empty identity) are denied.

internal/logging: add TaskRegistry.Path() for read-side access without
threading baseDir separately through every caller.

Fixes from adversarial review: strict identity check (no empty-identity
bypass), non-null Entries when disabled, component doc accuracy, and
adapter tests covering the security boundary.

Ref: #455
2026-08-09 19:14:35 +10:00
sam 4131f05036 feat(webui,gateway): wire config, channel, log-feed, and work-intake seams
Composition root work tying the config resolver, channel manager, log
feed, and executable workflow registry into the running daemon and
dashboard server: web.Channels/LogFeed/Workflows/ConfigProvenance,
channel-reload wiring, TaskStopper for the Stop action, and
SpawnRequest.Body/WorkRequests threading dashboard "Start work" requests
through the same admission path chat uses. Touches all three features at
once because this is where they're composed, not owned by any single one.

Refs #53, #54, #55
2026-08-09 01:26:58 +10:00
sam 92280f4039 fix(store,gateway): taskstate constants and mobile jump-to search
Follow-up pieces of the task-controls work: store.InsertEvent factors out
an execer-generic insertEvent so SQLite gets the same zero-time defaulting
ArchiveTask's audit path relies on; gateway tests assert against
taskstate constants instead of magic status strings; the navigation
command bar gets an accessible mobile search toggle.

Refs #53
2026-08-09 01:26:40 +10:00
sam b876fc80cc feat(gateway): make chat turns durable and idempotent 2026-08-09 01:15:41 +10:00
sam 6aa3772ce9 feat(gateway): tool-approval gate, session tools for chat, and /delete command
Adds a human-consent gate for tools marked RequiresApproval, exposes
session management as LLM-invokable chat tools, and gives the operator
/delete to retire conversations permanently.

**Tool-approval gate (internal/tools, internal/agentexec)**

- ApprovalRequester contract lives in internal/tools (not gateway) so
  agentexec can import it without pulling in the chat-adapter stack.
- ToolSetOptions.Approval wires the approver through to toolExecute.
- BuildToolSetFrom omits RequiresApproval tools when no approver is
  configured; dispatch paths (invokeTool, tool_call bridge) refuse
  them too, so the invariant holds at every indirection.
- The gate fails closed: only Approved/PermanentlyApproved pass;
  an unknown decision value from a faulty approver does not execute.
- Tool-level timeout (2 min) returns a plain error, not a context
  cancellation, so the model can report "approval timed out" instead
  of the turn aborting.
- BuildApprovalDescription callback lets a tool surface the specific
  resource being acted on ("Delete session \"abc123\"") rather than
  showing a static tool description.

**Session tools (internal/gateware/session_tools.go)**

- session_list (idempotent), session_resume (mutating), session_title
  (mutating), session_delete (mutating + RequiresApproval).
- Scoped to the current platform + channel: GetByChannel replaces
  List() so a model in chat A cannot list or manipulate chat B.
- session_title validates the session belongs to this channel before
  writing; session_resume/session_delete resolve refs against the
  channel-scoped list.
- Shared limit helper extracted to tools.ListLimit.

**Telegram approval adapter (internal/channels/telegram/approval.go)**

- telegramApprover implements ApprovalRequester via the three-button
  inline keyboard (Approve/Permanent/Deny). 2-min token expiry.
- Own map + mutex + "approval:" callback prefix — separate from the
  dangerous-command system.
- Permanent approval uses exact-match (not prefix) lookup keyed by
  action + resource description, so permanently approving "delete
  session abc123" only covers that one session, not every call to
  session_delete for 24h.

**Session lifecycle**

- /delete <session-id>: removes a session and its history. Refuses
  prefixes shorter than 4 chars even when unique. Exact ID wins over
  an ambiguous prefix. sessionTracker.forget sweeps every channel+
  thread pointing at the deleted session.
- Extracted resolveSessionRef and shortSessionID for /resume and
  /delete to share.

**Wiring**

- submitTurn builds the approver onto ctx before the LLM turn.
- chatGenerateOptions reads approver from ctx, passes it through
  ToolSetOptions.
- SessionTools built per turn on the current message, combined with
  taskTools into a single toolset.
2026-08-08 16:42:59 +10:00
sam 1081a6c3ed feat(daemon): identity-scoped isolation + gateway session titles and /delete
Multi-identity daemon isolation:
- Split runIdentities into per-identity poll loops plus one shared
  maintenance-and-drain loop, so reconcilePRs and storage cleanup run in
  multi-identity mode and the global max_concurrency / per-repo
  serialization holds across identities.
- Make the poll path identity-aware: each identity polls with its own
  forge client, bot user, label, trigger, and ack reaction.
- Make allowConcurrentFor task-based and identity-aware via repoFor.
- Roll back storage mounts when container acquisition fails; log
  Store.Update failures after branch set.

Container-mode RPC identity routing:
- forgerpc/worktreerpc gain identity-scoped subjects (SubjectFor,
  RegisterFor) and identity-carrying clients.
- registerTaskRPCServers registers one server pair per identity (plus
  root), so a container-mode task owned by a non-root identity is served
  by its own forge client and worktree manager.

Gateway/Telegram:
- LLM-proposed session titles generated in the background after turns
  (TitleGenerator + chatTitleGenerator), persisted by the gateway.
- /delete session command with prefix guard and tracker forget.
- Shared session display helpers (shortSessionID, sessionDisplayTitle,
  resolveSessionRef).
2026-08-08 01:32:35 +10:00
sam 308666b410 chore: remove legacy terminology and dead code
- Reword docs and comments to drop vague "legacy" qualifiers where they no longer describe deprecation status
- Remove unused code: RecentEvents, MessageEvent.ToLegacy, index setState, stderr redaction tool, telegramOnlyCommands
- Delete or comment out tests covering removed or superseded behavior
2026-08-06 22:55:26 +10:00
sam e10cbbc92c refactor: pre-cleanup. 2026-08-06 01:40:15 +10:00
sam 68ba3456ee feat(webui): chat from the dashboard
Brings the chat surface to the Web UI: /api/chat with its own handlers
and tests, a self-contained ui/src/chat feature folder, and the shared
plumbing to reach the same router Telegram uses.

Includes a dangerous-command approval path (internal/gateway/dangerous.go,
internal/webui/dangerous.go, and the Telegram counterpart) so /rollback
and /stop are gated the same way on both surfaces, persona handling for
web sessions, and release-update formatting split out of the Telegram
service so both can render it.

web_parity_test.go pins that the two surfaces expose the same commands.

Authored in a parallel session; committed here so it lands with the rest
rather than sitting uncommitted while other work builds on top of it.
task check passes with it in place.

Screenshots used while building are gitignored (*.png) rather than
committed, matching the call made on the earlier design reference.
2026-08-05 10:48:51 +10:00
sam fa6f4aef5f fix(gateway,daemon): repair regressions found by the adversarial review
Six defects, four of them introduced by the fixes in dbacb96, 44d43ef,
d5e016e, de1a899 and 4d44ef7. This is the third round in this codebase
where a round of fixes broke something the next round caught.

SANDBOX SILENTLY DROPPED. startContainers degrades a failed container
pool to nil, and the daemon's only test was `if ContainerPool != nil`.
So `containers.enabled = true` plus a missing agent image ran every
task's agent loop in-process, with the daemon's own authority and the
host filesystem -- the one thing [containers] exists to prevent -- while
logging only that containers were disabled. Nil now means two things and
they are distinguished: SandboxRequired parks the task instead. The
daemon still stays up; chat and the dashboard are unaffected.

SUMMARY AT THE WRONG END OF HISTORY. compressedHistory returns [head,
summary, tail], but ordering is by timestamp, not slice position. The
retained messages keep their original timestamps -- that is what
preserves their identity -- so the summary, being new, was clamped to
now and sorted after the tail it was meant to precede. The model read
the recent conversation and was only then told earlier context had been
summarised. Confirmed on both backends: index 23 of 24.

The monotonic clamp belongs to the append path, where an inbound message
must not sort ahead of the one that provoked it. ReplaceMessages is a
rewrite primitive and now honours explicit placement, and the summary
takes a timestamp inside the span it replaces.

A COMPRESSION SUMMARY ANSWERED A QUESTION. Following from the above,
PriorReply saw a bot-attributed record immediately after an unanswered
message and replayed it as the answer: a redelivered question was
"answered" with the compression banner and the model never ran. The
user's question was silently swallowed.

RECENCY STILL DIVERGED. sessionRecency preferred LastActiveAt whenever
set; SQLite used MAX(last_active_at, created_at). Those agree only when
LastActiveAt is the later of the two, so a clock step or an older record
made the caller and the store order the same sessions differently.

LASTACTIVEAT WAS NEVER UPDATED. Touch had no caller, so "resolve the
most recently active session" meant the most recently created one -- an
operator who moved to an older session with /topic and worked there was
dropped back into the newer, abandoned one on restart, which is the bug
d5e016e claimed to fix, with the direction reversed.

/branch WITH NO ACTIVE SESSION PANICKED, slicing an empty parent ID for
its default title. Pre-existing, but reachable: email and webhook call
Route directly without resolving first, and the email path runs in a
goroutine with no recover, so one message took the daemon down.

The sandbox guard has no test. The honest reason is that exercising it
needs a daemon with a forge and worktree the current harness does not
build, and a test that re-states the condition proves nothing -- which
is the same false confidence that let these regressions through.
2026-08-05 04:24:16 +10:00
sam 1f2e7a42eb refactor: one definition of what approving or declining a task means
The dashboard and chat both let an operator approve or refuse work, and
they had drifted. Declining from the dashboard left the task
closed_wont_do; cancelling the same task from chat left it rejected. Two
operators looking at one queue saw different states for the same
decision, and "rejected" -- which reconcilePRs also uses for a pull
request closed without merging -- stopped meaning one thing.

internal/gateway deliberately does not import internal/store, so it kept
a hand-synced copy of the status strings with a comment asking future
editors to keep them aligned. That is the same defect one level down,
and it is how the drift happened.

internal/taskstate is a leaf package with no dependencies holding the
lifecycle vocabulary and the rules for operator actions. gateway, store
and the dashboard all import it, so gateway stays decoupled from store
without a copy, and CheckApprove/CheckRetry/CheckDecline have one
implementation. Declined is named for what it is -- a human said no --
and stays distinct from Rejected, which is something archie observed.

Chat cancel now records Declined. That is the behaviour change: same
decision, same state, whichever surface the operator used.

Rules were preserved rather than tidied while unifying. A parked task
still cannot be declined, which both surfaces already refused, even
though "not terminal" would have allowed it -- widening a rule under
cover of a refactor is how you ship a change nobody reviewed. The
comment says where to change it if that is ever wanted.

TestDashboardAndChatAgreeOnTerminalStates drives both real surfaces
against one store, so this cannot drift apart again without a red test.

Also removes a second rule for the dash-top-standalone class: renderSetup
already reconciles it from the data at the top of every call, and a later
branch cleared it again. Harmless, but it reads as two sources of truth
for one bit of layout state.
2026-08-05 04:15:39 +10:00
sam de1a899072 fix(gateway): make both backends agree on newest-first
SQLite ordered List and GetByChannel by created_at while NellDB reversed
document order, i.e. by session ID. Both documented "newest first", both
passed the shared suite, and neither meant recency -- so a cutover
between backends could change which session a restart resumes, and
Touch, the live path that makes a session the newest one, changed
nothing on either.

Recency is now LastActiveAt when set and CreatedAt otherwise, on both
sides, with an index matching the SQLite expression.

The conformance suite gains the case that would have caught this: three
sessions whose creation order, ID order and use order all disagree, plus
a Touch, asserted against List and GetByChannel on both backends.

Refs archie-core-8u8.2
2026-08-04 22:47:48 +10:00
sam a1a111ff35 fix(gateway): give branch-inherited messages their own identity
/branch copies the parent's history into the child. Because the store
honours an incoming MessageID -- which is what lets a read-modify-write
preserve identities -- the copies kept the parent's canonical IDs, so
two sessions claimed one identity and branch-point correlation was
ambiguous. Two branches from one parent made it three. It also broke
dedup in the child: an inherited message carried an ID derived from the
parent's session, so redelivering it appended (confirmed on both
backends: 3 messages became 4).

newMessageID's doc already claimed the opposite behaviour, and the
Message.MessageID doc said it was "ignored on write" -- which is exactly
the misreading that produced this. Both now describe what the code does,
including the obligation on a caller copying messages between sessions.

Also removes a doc comment describing msgID and its disambiguating
counter, deleted in 0814f7b, which had come to sit above
messageIDNamespace describing the opposite of the current design; and
corrects the Telegram comment still claiming a redelivered update
"updates the stored turn", the behaviour the immutability fix removed.

Refs archie-core-la1
2026-08-04 22:25:20 +10:00
sam f64353f0b5 fix(gateway): do not answer a redelivered message twice
Making the store idempotent stopped redelivery duplicating the inbound
record, but nothing consulted that result: respond() saved the message,
ignored the fact that nothing had changed, and called the model anyway.
The cost was a second billed turn, any tool side effects run a second
time, and a second assistant reply appended -- replies carry no upstream
reference, so they always get a fresh identity and always append. The
stated problem, "a re-delivered update appends a duplicate turn", was
only half fixed.

PriorReply answers "have I already replied to this?" from the history
the caller has already loaded, and the chat path replays that answer
instead of regenerating it. A message with nothing after it was never
answered -- the turn may have died partway -- so that still runs, since
the user is owed a reply.

CanonicalMessageID exposes the store's own derivation rather than
letting the caller reimplement it, since a lookup that silently never
matches is indistinguishable from a message never seen.

Refs archie-core-i6q
2026-08-04 22:23:17 +10:00
sam 0fd3398cf8 fix(gateway): stop /compress destroying a message that arrives midway
applyCompress reads the history, computes a summary, then replaces it.
ReplaceMessages removed everything outside the replacement set, so a
chat turn saved in that window was deleted without ever having been
read, let alone summarised. Confirmed on both backends. It is
unrecoverable loss, and it sits outside the write-then-delete guarantee
because the window is in the caller, not the store.

ReplaceMessages now takes the messages the caller is superseding instead
of inferring them from the complement of the replacement. A caller
computes a replacement from a history it read; anything that arrives
afterwards is not part of that, and is now left alone. IDs in both lists
are still kept, so read-modify-write callers are unaffected.

The test fake's ReplaceMessages was a slice assignment, which could not
observe ordering or identity at all -- it now mirrors the real stores.

Refs archie-core-6e0
2026-08-04 22:21:15 +10:00
sam 44d43ef286 fix(gateway): claim the session slot before writing it, not after
resolve saved a newly created session to the store and only then asked
the cache who had won a concurrent race. The loser had already persisted
a session that nothing pointed at: unreachable, but still listed by
/topic and /sessions as "(untitled)", and -- now that resolution goes by
recency -- resurrectable on a later restart. Confirmed by forcing the
interleaving: the store held 2 sessions where it should hold 1.

The claim now happens under the same double-check, ahead of the store
write, so only the winner writes. A failed Save releases the claim, or
the cache would point every later message in that chat at a session that
was never stored.

Refs archie-core-x35
2026-08-04 22:17:39 +10:00