workflow_list, workflow_get and workflow_step_types read the org's
definitions and step catalog; workflow_validate runs the editor's save
check on a proposed definition without saving it.
The State Store answers the calling principal's org aliases
(CallerModels) and bills chat usage to that org; usage records no longer
carry a caller-named org. Chat lists and resolves aliases for the
caller's org and fails rather than substitute one it may not use.
SOUL now owns the prompt identity slot via a per-turn source: a stored soul
resource wins once saved, otherwise the identity's SOUL file, then the
shipped default. The gateway watches the resource so a dashboard edit
reaches the next turn without a restart; a file read error degrades to the
default and logs once.
The persona prompt plumbing is replaced by the SOUL source; the persona
surface itself (registry, wire, page, commands) stays for archie-core-7ftt.
Remove PRD/doc paths, bead IDs, phase notes and deleted-test references
from comments; drop test-only hooks left by the test deletion. Includes
in-progress archied bootstrap, gateway and query changes.
prepareTurn now registers an ask_user tool only when the turn context
carries an interactive adapter (WithInteractive), so a contract with no
caller has a real one and a channel that cannot ask registers no tool
rather than one that always fails. A channel reporting Picker gets the
native single-choice request; one reporting only Clarify still carries a
choice, rendered as numbered text and matched from the typed reply through
the domain's FormatPickerText/ParsePickerReply rather than erroring.
Red-first: InteractiveTools returned nothing and
TestInteractiveToolsRegisteredWithCarrier / TestAskUserUsesPickerWhenChannelCanPick
/ TestAskUserFallsBackToTextWhenChannelCannotPick failed at the assertion
before the tool was implemented. TestTurnRegistersAskUserOnlyWithCarrier
proves reachability from a real TurnRunner turn.
The Messaging Service built the voice-transcription client in-process
from [models].transcription and [providers.*], which the messaging
boundary PRD reserves to the process that owns the model runtime and its
provider credentials. The deletion gate only measured linked packages,
so the PRD violation shipped green: config reads are not imports.
Move the capability across the boundary:
- archiemessaging no longer reads [models] or [providers], builds no
transcription client, and drops the ResolvedConfig.Transcriber field.
- telegram classifies a voice note as messaging.MediaTypeVoice and stops
transcribing; it carries the attachment bytes and its note to the turn,
which is all a frontend without the credential can do.
- archied builds the transcriber beside the chat runtime from its own
model-role configuration (setupTranscriber) and gives it to every
gateway TurnRunner.
- the turn runner transcribes a speech attachment before recording the
inbound message, so stored history and the model context carry the
transcript; a nil/failed/empty transcription keeps the frontend note.
- messaging.TranscribedMessageText renders the transcript into the text a
frontend built from its media note, preserving the sender's caption.
Red first: TestTurnRunnerTranscribesSpeechOnTheModelOwningSide failed at
'Transcribe calls = 0, want 1' with the transcription call disabled.
The OpenAI chat-completions provider in the pinned ai-sdk serialises a
non-zero output-token bound as `max_tokens`, which reasoning-class models
reject with HTTP 400 ("Use 'max_completion_tokens' instead"). Send no bound
at all for a model the catalog marks reasoning; classic models keep their
bound. Covers the chat turn path and MCP sampling, the two call sites that
set one today.
The reasoning flag rides TurnPrepareContext from the catalog details the
gateway already resolves, so archie-core keeps one notion of "reasoning
model": messaging.ModelDetails.Reasoning. A max_completion_tokens path in
ai-sdk is still needed to ever bound these models; that is filed separately.
Telegram dropped every incoming photo, document, video and audio
message: the default handler required message text, and nothing on the
turn path knew media existed. The receiving path now closes the gap
end to end.
- telegram: extract the attachment from the update (largest photo, plus
document, video, video-note, audio and voice kinds), download its
bytes on the turn lane through getFile + the Bot API file link with a
20 MB gate, submit the turn with the attachment, and answer
unsupported content kinds (sticker, location, contact, poll) with a
clear notice instead of silence
- messaging: Inbound carries turn-scoped transport media and
MediaAttachment a Data field for in-process bytes; Message gains
Media attachment metadata which stores persist (Postgres jsonb via
migration 0020, memory store) with Data stripped at the persist
boundary, and pb.Message carries the metadata on the gateway wire
- gateway: TurnModelRequest threads the turn's media to the model seam
- archied: the chat turn model merges the attachments into the final
user message as ai-sdk image/file part entries, so vision-capable
models see the file for the turn it arrived in; stored history keeps
the placeholder note plus caption
Session log: messages carry what was sent as data (the attachment
metadata), not just prose. Transcript rendering of attachments and a
re-look capability are tracked as archie-core-jaba.
review_pr self-omitted since d73e0748 deleted the synchronous reviewer it
called. It is rebuilt on the task enqueue path everything else uses: the
tool resolves the identity's configured repo, then queues a pr-review task
naming the pull request through the workflow's declared pr_number input,
which is the same generic input mechanism a watched-repos binding uses.
That input has to reach the store with the task, so
EnqueueChatTaskRequest gains inputs_json and the tasks insert writes the
inputs column directly. StampTaskBinding no longer writes it: the insert is
now the column's only writer, and a chat task must not acquire binding
provenance just to carry an input.
ChatPRReviewer, its result shape and the reviewer wiring are deleted with
the path they served.
One Router serves every channel and named itself "web", so Source.Platform -- the
FIRST component of the session natural key, and the platform GetByChannel filters
on -- was a constant, true of no channel but the dashboard. Two consequences
followed: the per-user identity policy was real code that no production call site
reached with a real channel name, and a curator pass's write to agent-user memory
could not be read back by the turn that wrote it, because that turn resolved no
UserID.
The channel now travels with the message. Frontends name the channel they carry
(pb.Message.platform: telegram, email, webhook, web), and the Gateway stamps the
session from it, falling back to its own name when a sender names none -- which is
what every existing row holds and what a frontend that does not participate keeps
doing.
Identity resolution reads the platform off the inbound rather than closing over a
channel name, so carriesPersonIdentity finally decides something in production:
telegram and email resolve a person, the dashboard and a webhook resolve nothing,
and an unknown platform fails closed.
Deliberately NOT changed, because it is where this could quietly widen scope:
TurnRunnerConfig.Channel still keys tool availability, so no channel gains or
loses a tool here. Only session lookup and identity follow the message's platform.
Consequence the maintainer accepted: a chat whose active session came from /new or
/branch re-resolves once, since GetByChannel now filters on the channel's name. A
chat with no /new re-resolves onto the same deterministic session id and heals
silently.
Verified: gateway, archied, gatewayrpc, messaging, webui, channels and cmd suites,
go vet ./..., go build ./..., golangci-lint run ./... (0 issues), docs:check.
New contracts: TestResolveSessionKeyStampsTheMessagesPlatform, the per-platform
identity table, and the transport-context wire round trip.
Build a per-turn memory tool set (memory_create/update/delete/list) onto
the turn's resolved Subject, matching slice 3's read-side scope model.
The model picks a scope KIND from an enum built off Subject.WritableScopes()
(never global); the agent and user ids a scope resolves to come from the
turn's Subject, with no schema field either could ever land in. A subject
with no writable scope, or a nil write store, gets no memory tools at all.
TurnRunnerConfig gains MemoryWriter (MemoryWriteStore: Create/Update/
Forget/List), wired alongside the existing MemoryEngine read surface
through the same active engine (boot.activeMemoryEngine, narrowed by
memoryStore/memoryWriter).
Wires the durable-memory engine into the chat turn: prepareTurn resolves a
per-channel Subject (BotUser as AgentID, TurnRunnerConfig.UserIdentity for
the user), runs a scope-only Query over Subject.Scopes(), and renders the
result into a new <memory purpose="durable_context" trust="data"> block
between <tools> and <env>, following the same untrusted-data framing as
those two blocks. The read is synchronous, total, and never surfaces an
error: a nil engine, a failing Query, or a panicking provider all degrade to
no memory block (recovered in gateway.renderMemory).
UserIdentity is supplied per channel by the composition
(userIdentityResolver in internal/app/archied): telegram and email resolve
their native SenderID, the dashboard ("web") and webhook resolve nothing, so
a webhook's route-path SenderID can never become a user identity and the
dashboard's shared bearer token can never impersonate a person.
Fixes the composition-ordering bug that left every turn runner holding a nil
memory engine: setupMemoryAll now runs before setupGateways in main.go, and
before setupGatewayChat in gateway.go's startGatewayRuntime, so
boot.memoryStore() has a live engine at every turn-runner construction site.
Named constants bound the read: memoryRecordsPerScope per scope, and
memoryBlockByteCap on the rendered block, which drops (and logs) trailing
records rather than truncating one mid-line.
Add a channel-neutral review_pr command that runs the adversarial reviewer
against an existing pull request and returns structured findings. The Web UI
chat and Telegram invoke the same command; the reviewer model is models.reviewer
(falling back to models.builder), configurable independently of planner/builder.
- forge: PullRequest + PullRequestReader.GetPullRequest (github, gitea)
- worktree: Manager.CheckoutPR materialises a PR head for Diff/Snapshot
- agentworker: NewOperatorReviewer + ReviewerModel (single model-resolution rule)
- gateway: review_pr tool, ChatPRReviewer, wired into TurnRunner for every channel
- archied: prReviewer adapter with identity-scoped repo allow-list and
per-PR single-flight, so duplicate/concurrent reviews are deterministic
Closes archie-core-h019.8.
Replaced gateway.Message as the currency at the channel-facing boundary
with the canonical internal/domain/messaging.Message. Channel adapters
now build the record directly (RoleUser, ConversationID, Sender) and the
Router hands it back unchanged, so nothing converts between two shapes in
process. gateway.Message is deleted; the dashboard route that had no home
in the record lives in a new Inbound envelope (Message + transport-only
Page), which reaches the system prompt and is never persisted.
Role is now set at construction instead of derived at the store boundary,
and the assistant reply is a direct messaging.Message (RoleAssistant,
Sender=botUser). The gRPC proto is unchanged: pb.Message still carries no
role, and both sides keep deriving it from the owning session's bot
identity via gateway.RoleForSender (ToStoredMessage/FromStoredMessage are
deleted).
Adds tests that the old shape could not express: Page reaches the system
prompt but not the persisted record, and a channel-built Inbound round-trips
with the Role the channel set.
Refs: archie-core-9g5e
SessionStore message history now stores/loads domain/messaging.Message:
sender attribution, derived role, and conversation address are canonical
record fields. SQLite gains a role column with open-time backfill for
pre-migration databases. gateway.Message remains the channel-facing
transport; conversion lives in one boundary module. ChatContract,
gatewayrpc proto, and dashboard JSON are unchanged; the RPC client
splits into ChatContract (Client) and SessionStore (StoreClient) views.
Sessions stay SessionContext: UUID keys and platform/bot/title/branch
metadata have no lossless home in Conversation; keyed migration tracked
separately once Agent/user/binding ownership settles.
Refs: archie-core-d9dv
The chat agent had no way to know where it lives without probing the
filesystem (pwd, find, git remote), wasting turns on every orientation.
Per docs/architecture/identity.md the <env> block is Layer 1 invariants,
so the daemon's own facts belong there, driven from live configuration.
Render into the prompt's <env> block:
- workspace path (chat.workspace)
- repositories under management with forge host and default branch
- operator identity (chat.operator, which was dead plumbing)
Unconfigured values render explicitly as unknown / none configured
rather than a plausible-looking default, and a repo with no forge
reports forge unknown, so the model never claims a fact the daemon
cannot confirm. Repos are resolved per active chat identity, mirroring
chatTaskProfiles.
gateway: add RepoEnv, SystemPromptConfig Workspace/Repos/Operator,
TurnRunnerConfig Workspace/Repos.
app: chatRepoEnv resolver wired through newChatTurnRunner.
tests: prompt rendering (incl. explicit-unknown + hostile-SOUL guard)
and chatRepoEnv identity resolution. go.sum gains module-graph
/go.mod checksum lines.
Compose the base registry with per-turn extras into a turn-local registry and
let ContextPressureGate decide full-vs-bridge disclosure per chat turn. The
three bridge tools (tool_search, tool_describe, tool_call) are now wired into
the chat toolset and only disclosed under context pressure, keeping the LLM's
schema footprint small while preserving full arsenal access on demand.
Per-turn extras are identity-bound per channel and cannot live in the
process-wide registry (agentexec.BuildToolSetFrom invariant), so the bridge is
composed turn-locally rather than registered globally. Thread the model's
context window through TurnModel.Prepare (TurnPrepareContext) so the gate
activates with a real window.
Refs #167
turn.go: extract checkConfigured, replayPriorReply, claimTurn,
recordInboundMessage, prepareTurn, generateAndComplete out of Run
(gocognit 53 -> under threshold, gocyclo brought under 20 then under
cyclop's 15 too).
gateway.go: split dispatchLocal's second half into dispatchLocalMisc
(cyclop 18 -> under 15, on top of the earlier gocyclo fix).
Behavior-preserving; internal/gateway lint clean.
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.
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.
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
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.
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
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.
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