The chat agent read only its local checkout, so an unfetched workspace made it report that no task branch or PR existed and that shipped UI code did not exist. Add a core rule: refresh from the remote or check the forge before describing branches, commits, pull requests or the default branch, and say the answer is local-only when it cannot.
An approval, ask or park can be resolved by an operator, a rule, a
classifier or automatically, so the vocabulary stops naming a person:
- step type human.approve -> workflow.approve
- park class needs_human -> needs_decision (ParkNeedsDecision)
- event kinds human_* -> operator_*
- alert kind task.needs_human -> task.needs_decision
- status grouping "needs you" -> "needs attention"
0061 rewrites the stored values, including the approval step type in the
workflow-definitions resource and each task's pinned definition, with the
digest recomputed so resumed tasks still match.
Each workflow has its own persisted conversation, rendered like the chat panel.
The canvas and YAML go read-only while Archie works instead of inert. The code
block highlighter loads Go and TOML and drops jsx, tsx and vue.
The Access area mixed organisation, instance and personal settings under
one name. Split them: /org is the organisation's own area (members,
identities, connections, models, schedules, playbooks), /settings is
instance administration only, and personal security stays in the account
menu. Setup checklist steps now link to the page that fixes them.
Personal API tokens are the signed-in operator's, and the instance URL and
OIDC providers are the instance's, so neither belongs under the organisation
Access area. Tokens render in the account page and Authentication moves to
Settings; the old paths redirect.
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.
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.
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.
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.
Persona/SOUL text was interpolated raw at the top of archie.md.tpl,
so a hostile SOUL could inject its own <core_rules> or
<instruction_precedence> tags ahead of the real ones. Render it
through the existing xml-escaping helper into a labeled
trust="data" <soul> block, and tell instruction_precedence
explicitly that the block is reference data, not an authority.
Closes archie-core-1786637490097-12-bf415ffb
Funcs() was passed a *strings.Replacer value instead of its Replace
method, panicking gateway's init(). Fixing that surfaced a second bug:
the template still referenced .Operator, removed from promptData by
5a92fc1, which made every render fail and silently fall back to a
generic hardcoded prompt.
Also replaces a real Telegram chat ID hardcoded across several test
fixtures with a placeholder value.
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.
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.
The communication rules were entirely prohibitions, with nothing
licensing warmth. On a social turn there is no answer to lead with, so
"lead with the answer, keep it short" collapsed into a demand that the
user justify getting in touch: "are you there?" drew "I'm here. What do
you need?"
Three defects found from a real Telegram transcript.
1. The operator's name was compiled into the prompt.
internal/gateway/persona.go and prompt.go both hardcoded "Sam's" into the
default persona and the fallback prompt. The persona renders first into
every system prompt, so a personal name was sent to the model provider on
every turn, and any other deployment got an assistant that believed it
worked for someone else. There was nowhere to put it: Repo.Owner is a repo
owner and config.Config had no operator concept.
ChatConfig.Operator now carries it, rendered in the prompt's <env> block as
runtime metadata and omitted entirely when unset. config.example.toml
documents that setting it sends the name to the model provider.
2. /new claimed to clear history that it had not cleared.
The chat responder keyed history by channel id through a local sessionKey
helper, while the session commands operate on tracked session ids.
sessionTracker.resolve mints deterministic ids so the two agree -- until
/new, /branch or /resume assigns a generated id, after which they address
different histories permanently. /new reported "Conversation history has
been cleared" while the next turn still saw everything, and /undo,
/compress, /resume and /sessions acted on a namespace the conversation
never read.
gateway.Router.ResolveSessionKey already existed for this, and
session_commands.go:104 said outright that main.go should call it instead of
its inline helper. It never got wired. The responder now resolves through
the router and the dead helper is deleted so it cannot come back.
buildTelegramRouter constructs the router before the responder so the
dependency is visible rather than captured by reference.
3. Prompt rules for two behaviours the transcript showed.
The agent offered to accept shell access it has no tool to use, which is
both unhonourable and a request for the user's secrets. It also opened
mid-conversation replies with a greeting, and described its own manner
("no fluff") in stock phrasing. Added core rule 7 and three communication
rules covering greetings, self-description and register.
Note the memory claim in that transcript was NOT a fabrication: the
memory_edit tool's own description names MEMORY.md and USER.md, and tool
descriptions are part of the prompt.
Also added chat-turn logging (session id, channel, thread, history depth).
Chat turns were entirely unlogged, so a report of lost context had no
evidence to check: 76 log lines covered two days and none of them was a
conversation. A separate report of mid-conversation amnesia remains
undiagnosed -- single process, 43h uptime, compression untriggered at three
messages -- and this is what makes it diagnosable next time.
Regression tests: prompt renders/omits the operator and carries no personal
name; the responder resolves via ResolveSessionKey and defines no local
session key helper.
Verified: go build, go vet, gofmt clean; full suite passes.
The chat agent's entire system prompt was the four-sentence static string
in gateway.DefaultPersonas(). It carried no tool inventory, no environment
block and no instruction precedence, so the model invented its own
capabilities: asked to set something up it announced it "only has the
memory editing tool", then offered to walk through installing software it
has no tool to install.
Renders a template modelled on tau's agent.md.tpl + tau.agent.md:
instruction precedence, core rules, communication rules, a <tools> block
and an <env> block. The persona stays the style layer on top; the rules
and the tool inventory live in the template so switching persona cannot
remove them.
The tool list is derived from the same core.ToolSet handed to the model,
so the prompt cannot drift from what the agent can actually call, and an
empty toolset renders an explicit "no tools are available" rather than
silence the model fills in for itself.
Tool metadata is third-party data from MCP servers, so it is markup-escaped
(<, >, & only — not xml.EscapeText, which mangles prose into 
/')
and whitespace-flattened, so a description cannot forge a closing tag or a
second "- tool: ..." list entry.