Commit Graph
73 Commits
Author SHA1 Message Date
sam 8d20456999 fix(deps): ai-sdk v0.3.1 so Gemini Interactions tool calls get valid arguments 2026-10-16 03:33:49 +11:00
sam d3e2a67222 feat(identity): add browser setup and user accounts 2026-10-16 02:41:24 +11:00
sam 168261c8be build(deps): bump ai-sdk v0.1.43 -> v0.3.0 and update dependencies
Gemini 3.x/4 chat now routes through the Interactions API transport, which
replays thought signatures on tool turns; long decode stays opt-in. Also
takes go get -u updates (x/*, genproto, goose, nats-server, modernc sqlite).
2026-10-14 23:10:34 +11:00
sam 531f3c13bd test(postgres): remove database-backed tests and the testcontainers harness 2026-10-12 01:17:02 +11:00
sam be31522e6a fix(kit): migrate runtime to sandbox kit m8 2026-10-09 18:31:56 +11:00
sam 7438c3211c fix(deps): pin sandbox-kit-spec to the API the code is written against
The dependency bump moved sandbox-kit-spec from v3.0.0-m.6 to m.8 without
adapting the code, so the tree no longer builds: CredentialCapability.Phase
is now spec.Phases, not a string (internal/infrastructure/egress), and
Client.Assemble became a package-level fetch.Assemble that takes a Loader
and a LayerValidator instead of spec.MergeOptions (internal/infrastructure/
kitrun).

Migrating to m.8 is not a version-string change: m.8 pushes kit integrity,
safe layer extraction and resource limits onto the caller, so it is
security-relevant work, not an unblock. Pin back to m.6, which the code is
written against, and leave the migration to a deliberate change.

Verified: go build ./..., go vet ./..., go test -short ./... all pass with
this pin. The gate's ui:check and lint steps fail for unrelated
toolchain reasons recorded separately.
2026-10-09 11:42:33 +11:00
sam 5991fc3ea2 chore: bump Go dependencies and toolchain 2026-10-09 11:23:04 +11:00
sam 3bbe7d1c72 fix(agentexec): enforce capture tool result schemas 2026-10-08 22:30:12 +11:00
sam ee5d6f78ff fix(deps): ai-sdk v0.1.43 sends gpt-6 tool calls through the Responses API 2026-10-08 01:41:44 +11:00
sam 6cce5ec907 fix(releaseupdate): read GitHub releases directly; drop go-selfupdate and its openpgp dependency 2026-10-07 23:18:03 +11:00
sam 0b9769dbf2 feat(releaseupdate): archied update check finds releases through go-selfupdate; archie-update-check is deleted 2026-10-07 01:12:11 +11:00
sam 172ba474b3 feat(storepkg): install packages from a signed default catalogue, listed on the Extensions page 2026-10-06 01:18:25 +11:00
sam d5eefcc512 chore(deps): bump ai-sdk to v0.1.42
Picks up the class-scoped request shaping fix: openai-compatible
transports keep max_tokens instead of receiving max_completion_tokens.
2026-10-06 00:24:55 +11:00
sam c660857a91 fix(archiegateway,agentexec,agentworker): rely on ai-sdk reasoning token selection
Bump github.com/samcharles93/ai-sdk v0.1.40 -> v0.1.41. ai-sdk now sends
max_completion_tokens for reasoning models and omits temperature when the
model rejects it, so the max_tokens workarounds are no longer needed: the
chat-turn bound is set directly and MCP sampling loses its reasoning
branch. Classic models keep their existing bounds.
2026-10-05 22:56:48 +11:00
sam ee2c9cda97 feat(releaseupdate): install from release artifacts with journaled rollback, topology check and channels 2026-10-05 17:02:29 +11:00
sam a76d51dee7 refactor(forge): github and gitea leave core; webhooks parse in the forge extension 2026-10-04 14:26:27 +11:00
sam c5558c43fb chore: remove Yaegi
yaegiutil, the go.mod dependency, the .yaegi host-code entry and the legacy
guard stages for .archie/gate.go and .archie/stages are gone.
2026-10-04 03:08:46 +11:00
sam b923708716 build(modelcatalog): read catalog metadata from ai-sdk/catalog
ai-sdk v0.1.40 moves the models.dev types into a dependency-free package, so
archied no longer links every provider client for catalog metadata.
2026-10-04 01:39:02 +10:00
sam 8b28857ff3 feat(secretengine): serve secret engines as go-plugin extensions
A secret engine is now a subprocess serving secretengine.v1, installed through
the package store's new extensions family and enabled by extension-settings.
bws leaves the binary, as do the Yaegi engine loader and its examples.
2026-10-04 00:40:23 +10:00
sam c6d880a8f8 feat(access): cedar-go engine for the policy chain, shipped roles and cross-org forbid (archie-core-qc8p) 2026-09-26 15:22:01 +10:00
sam cd368851d1 feat(access): policy schema, actions, request assembly and Authorizer contract (archie-core-qc8p) 2026-09-26 15:22:01 +10:00
sam 70df8d1131 feat(daemon): run a Kit profile's task in its Kit container on the egress path 2026-09-26 10:14:33 +10:00
sam 0b64130b6a feat(agentexec): serve capture tools to harnesses over MCP
archie-agent mcp is a stdio MCP server, on the official go-sdk, serving a
stage's capture tools and appending accepted calls to a captures file.
The harness runner writes the tool spec and a standard mcpServers config,
registers it through HarnessSpec.MCPConfig, and reads the captures back
into the stage result. The captures file is writable by the harness user,
so the worker validates every record again with the same acceptCapture
the built-in loop now shares, and forged, undeclared or over-cap records
are dropped. A stage with capture tools on a harness without MCP is
refused before it runs.
2026-09-26 03:28:58 +10:00
sam ad575879ee feat(kit): admit Kit v3 descriptors against archie's capability support
Decodes published descriptors from the manifest annotation, composes one
workload with its mixins through the Kit spec package, and applies the
runtime's support table: unsupported required capabilities refuse the
launch, optional ones are skipped and recorded, and forge or passthrough
credentials are refused. A composition must carry a headless prompt verb.
2026-09-26 02:23:11 +10:00
sam 2051ca94d2 chore(state-store): remove the one-time SQLite import and db_path
Every install serves from Postgres, so the legacyread/legacyimport packages,
the archie-state-store import command, the boot gate that refused to serve
over unimported SQLite files, and db_path (which only located those files)
go. Migration 0010 drops the import_completion table.
2026-09-25 00:40:48 +10:00
sam e425989574 chore: update deps and remediate GO-2026-6253 2026-09-24 22:27:08 +10:00
sam e3ee044c5e refactor(store)!: remove the SQLite task store, the PocketBase event store and the SQLite session store
The State Store, event capture and Gateway conversations already serve from
PostgreSQL. This deletes internal/store and internal/infrastructure/edastore,
the SQLite gateway session store and openProductionTaskStore, and the -db
recovery path on a legacy task file; backup, restore, validate and rollback
work on the database database_url names.

- The binding-secret cipher moves to internal/infrastructure/bindingcipher and
  ToolCall to internal/infrastructure/postgres.
- NewSessionStoreMemory is now a pure in-memory store that passes the shared
  SessionStore conformance suite.
- Tests run against PostgreSQL through internal/infrastructure/postgres/pgstore;
  legacyimport/legacyfixture writes the legacy files the import and the boot
  gate read.
- The cron dialect is owned in internal/domain/scheduling, so
  github.com/pocketbase/pocketbase and pocketbase/dbx leave go.mod.
  modernc.org/sqlite stays for the one-time import (legacyread).
- The UI and Messaging architecture gates ban the Postgres and legacy readers
  in place of internal/store.
2026-09-24 14:43:50 +10:00
sam 902cfbeb61 feat(postgres): pool that refuses servers before PG 18, goose migrations under an advisory lock, testcontainers harness
internal/infrastructure/postgres opens a pgx pool, checks server_version_num >= 180000, and applies goose migrations with a Postgres session advisory lock so processes starting together apply each migration once. internal/infrastructure/postgres/pgtest starts postgres:18 through testcontainers per test binary and gives each test its own database. Adds jackc/pgx/v5 v5.11.0, pressly/goose/v3 v3.28.0 and testcontainers-go v0.44.0. The database URL config, sqlc, the Compose service and the ownership lock move to archie-core-7r0x.2, where they have consumers.
2026-09-24 01:03:08 +10:00
sam 63be83e0cf refactor(playbooks): serve on go.lsp.dev/protocol instead of hand-written LSP types
Replaces sourcegraph/jsonrpc2 with the go.lsp.dev stack (protocol, jsonrpc2, uri). The exit notification now ends Serve; closing the connection from inside the exit handler deadlocked.
2026-09-23 22:34:33 +10:00
sam ee16b8a711 feat(playbooks): archie-playbooks serve, a language server publishing lint findings as diagnostics 2026-09-23 22:22:56 +10:00
sam 3ccc57d445 fix(stateadmin): drop the default users collection and pin the sqlite driver
PocketBase creates a "users" auth collection on first bootstrap whose
createRule is open, so an unauthenticated caller could POST a record and write
a row into the State Store's database file. This surface authenticates
superusers only and has no notion of end users, so the collection is deleted
rather than given a tighter rule: one that is absent cannot be loosened again
by a later PocketBase default.

Also re-applies the modernc pin. It was applied while developing the previous
commit but a concurrent go.mod resolution reverted it before that commit was
taken, so the tree has been running 1.59.0/1.77.1 against a PocketBase built
and tested on 1.57.0/1.74.4, printing the mismatch warning on every start.
Note for future dependency work: go get -u will undo this pin, and
modernc.org/libc does not follow semver, which is why PocketBase checks.

The claim in the previous commit message that the pin landed there is wrong.
2026-09-23 00:55:57 +10:00
sam 2a4e764718 refactor(indexing): delete the workspace codesearch indexer
The index built google/codesearch over the chat workspace on every daemon
start, for the process lifetime, through a child-process helper and a
SQLite metadata DB -- and grep consulted it only for searches confined to
the workspace root, which the analysed sessions showed was a small
fraction of searches. The compute was continuous; the benefit was not.

Removes internal/indexing, the workspace-codesearch helper subcommand,
the [indexing] config section, and the GrepIndex accelerator seam from
the grep tool, which returns to its direct walk. google/codesearch
leaves go.mod with it.
2026-09-23 00:36:38 +10:00
sam 5fa43b7e87 fix(messaging): render a tool call as one line with its own icon
A tool call rendered as a label line plus a ```text fence. Telegram draws a
fenced block as a full code widget (language header bar, copy button, panel),
and the block parser inserts a spacer paragraph before every block, so one
call cost four rendered elements. Three calls filled the screen to show three
word counts.

Every toolPreview path already summarises to a single line, so the fence was
never wrapping more than one. Drop it and put the preview on the header line.
Tool lines now join with a hard break rather than a bare newline: a soft
break would space-join them into one run-on paragraph, and a blank line would
put the spacer back. Three calls are now three consecutive blocks.

Two hardcoded values go with it. The status word is printed only when the
outcome is not success, since every line otherwise read "done" and
distinguished nothing. The icon is no longer a literal in the renderer: each
builtin declares its own on tools.Tool (not on Schema, which is the model's
contract), the provider carries it into ToolEntry, and the turn snapshots the
registry's icons alongside its tool set. A tool that declares none renders
without one rather than borrowing a generic wrench.

Carries a dependency upgrade (go.mod, go.sum, tools/go.mod, tools/go.sum).
2026-09-22 21:36:02 +10:00
sam 79f521b65b feat(webui): let a person sign in and act as themselves
The last gap in the identity boundary: enabling a provider used to lock browsers
out, because nothing could turn a sign-in into the credential the dashboard already
verifies. Now a browser completes the authorization code flow with PKCE and the
identity reaching the request context is the person who signed in.

The audience is requested AT THE AUTHORIZATION ENDPOINT, not only at the token
endpoint. Infra measured that a provider asked otherwise returns the audience empty,
and this dashboard then refuses a perfectly valid token -- a failure that reads as a
signing fault and is actually a missing query parameter. A test asserts the
parameter is present, so it cannot quietly go missing.

The flow is the libraries': discovery, the code exchange, PKCE generation and the
challenge transformation are go-oidc and x/oauth2, so archie writes no protocol. The
token returned by the exchange is verified through the SAME Verifier a presented
token goes through, and the identity is then resolved through the same rule -- one
Resolve now shared by Authenticate and the callback, so a browser sign-in cannot be
accepted on terms a presented token would be refused on.

Archie still issues no session. The callback stores the PROVIDER's token in an
HttpOnly cookie and every later request re-verifies it, so what archie holds cannot
outlive the provider's own decision. The callback checks the state it issued, and
expires the state and PKCE verifier cookies on use.

The sign-in routes mount on the bypass mux because they are how a caller becomes
authenticated; gating them behind the credential they obtain would make signing in
impossible. The client secret is never a flag: -oidc-client-secret-env names the
environment variable holding it, so it cannot reach a process listing or a log line.
No client id means no sign-in route and token verification is unaffected, which is
what an agent-only deployment wants.

Evidence, produced by driv·ng the flow rather than the seam:
internal/webui/api_tasks_actor_test.go's TestBrowserSignInRecordsTheSignedInPerson
walks sign-in -> callback -> cookie -> action and asserts the recorded actor is the
signed-in person with human_approved. TestCallbackRefusesAMismatchedState asserts a
replayed state is refused before any credential is verified.
internal/infrastructure/oidc/flow_test.go runs the real flow against a test
provider's own authorize and token endpoints, asserting the audience parameter, the
PKCE challenge, a successful exchange, and a refused wrong verifier.

Verified: task check exit 0 on this tree.
2026-09-22 14:59:03 +10:00
sam a7d6f71d5a feat(identity): verify provider tokens and attribute task actions to their actor
Two halves of one boundary: a credential resolves to an identity, and an action
records which identity acted and whose authority it used.

resource server. internal/infrastructure/oidc verifies a provider-issued bearer
token against the provider's published keys, using an OSS OIDC library: archie
compares no signature, validates no claim and rotates no key itself, holds no
client secret and issues no session, so a compromised archie cannot mint an
identity. Audience is required rather than optional -- a token minted for another
service must not authenticate here -- and discovery happens at construction, so an
unreachable provider is a startup failure rather than a request-time surprise.

identity.Authenticate is the single place a credential becomes an identity, and it
refuses in four distinguishable ways: no credential presented, a credential that
did not verify (wrong key, expired, wrong issuer, wrong audience, malformed), a
verified subject with no identity bound to it, and an identity that may not act.
The order is deliberate: verification happens before any field of the token is
used, so nothing an unverified token carries can select an identity. A suspended
identity is refused even though its credential verified, because suspension is
archie's decision and must not depend on the provider withdrawing a token.

The binding is the second bridge beside the legacy-name alias: identity_subjects
keys (issuer, subject) so the same subject string from another issuer is a
different caller, and rebinding moves a subject so two identities can never claim
one provider subject. The contract Authenticate needs is SubjectResolver, narrower
than Repository, so a consumer that only authenticates does not take the whole
identity CRUD surface -- and staterpc.Client, which asserts Repository, does not
need a new RPC to satisfy it.

attribution. taskactions now records two identities per action: the acting
identity and the authorising principal, both on the event row as new columns added
through the existing migration table. The rule that the bug turned on is enforced
by the event kind describing the actor: a person's approval is human_approved, an
agent's is agent_approved, and an action with no verified actor is task_approved,
a task-level event that credits nobody. An agent acting under a person's standing
approval records itself as the actor and that person as the principal, so
"approved by came from me" is answerable from the record rather than asserted.
Scope and actor are separated: scope decides which task a caller may touch and is
never promoted into an actor, because the dashboard's credential is a shared token
and possession of it is not evidence that a person was at the keyboard.

That last point is a deliberate fidelity trade, and the reason the transport is
not wired: the dashboard action path passes no actor yet, so dashboard approvals
are now recorded as task_approved rather than claimed as a human's. Recording
nothing false is the requirement; naming the human verifiably needs the dashboard
to authenticate a token and resolve it, which needs two new state-store RPCs
(ResolveIdentitySubject, BindIdentitySubject) -- the next piece, not a rewrite:
the verifier is a one-method interface, so introspection would be a second
implementation of it.

Verified: task check exit 0; focused runs recorded in the handoff. Opaque
authelia_at_ tokens were inspected rather than assumed and cannot be verified
against public keys; infra is configuring access_token_signed_response_alg RS256
on the archie client, with audience https://archie.catlow.cloud and issuer
https://auth.catlow.cloud.
2026-09-22 14:34:16 +10:00
sam 2504283414 fix(deps): bump grpc to patch GO-2026-6443
Server panic via missing :authority/Host header, reachable through
archied's gRPC gateway server. No stable google.golang.org/grpc release
carries the fix yet, so this pins the pre-release commit that does.
2026-09-19 16:29:49 +10:00
sam cd9399f705 chore(deps): refresh go modules and tidy the tools module
Direct bumps:
- github.com/nats-io/nats-server/v2    v2.14.6 -> v2.15.0
- github.com/nats-io/nats.go           v1.53.1 -> v1.54.0
- github.com/samcharles93/ai-sdk       v0.1.32 -> v0.1.39
- google.golang.org/grpc               v1.83.2 -> v1.84.0
- modernc.org/sqlite                   v1.58.0 -> v1.59.0
- golang.org/x/net                     v0.58.0 -> v0.59.0
- golang.org/x/term                    v0.45.0 -> v0.46.0

Indirect: go-humanize, x/crypto, x/exp, x/sync, x/sys, x/text, x/time,
genproto/googleapis{,/api,/rpc}, modernc.org/libc.

tools/ is a separate module and needs its own tidy to match the root's
ai-sdk and sqlite bumps. docs:check runs it with -mod=readonly, so a
stale tools/go.mod fails loudly there rather than being rewritten.
2026-09-19 10:56:22 +10:00
sam 72bc95cc00 fix(telegram): summarise tool results instead of quoting an arbitrary line
Operator report: tool output in the Telegram channel was unreadable during
search-heavy turns -- a wall of fenced blocks each showing one arbitrary
match line ("/path/config.json-322-          }") under a heading that said
only "grep -- done".

The renderer quoted the first non-module-cache line of a result and appended
a line count recomputed from its own truncated sample, which could not agree
with the total the tool had already reported: one search rendered the tool's
"194 more lines" beside our "… 3 more lines". Two different numbers for one
result set read as noise, and the quoted line carried no context at all.

- Describe, don't quote: a search is reported as "N matches", a truncated
  result as "<total> lines total; showing <n>", and every other tool falls
  back to its first informative line. Truncation notices are skipped, since
  they are metadata rather than content.
- Never invent a count: the tool's own reported total is the only
  trustworthy source, parsed from its truncation notice rather than
  recomputed from the visible sample.
- Remove the now-dead compactToolPreview and countNonEmptyOrContentLines.

Also bump go-telegram/bot v1.25.0 -> v1.27.0, which fixes a streaming bug
that lands squarely on this path: rawRequest sent the multipart body through
an io.Pipe, which net/http cannot replay, so sendMessage/editMessageText
failed until the connection was dropped.

Remaining work from the report (collapsing repeated calls into one counted
entry, and a ring of recent activity lines with a capped frame) is tracked
in #837.
2026-09-17 09:36:28 +00:00
sam 3d7666002c feat(contracts): add gateway service seams and protobuf toolchain 2026-09-05 22:57:45 +10:00
sam cf1d4057eb chore: update go modules
closes #shl7 / #673
2026-09-05 20:42:48 +10:00
sam 61ae078fa0 fix(deps): upgrade x/crypto to v0.56.0 (#708) 2026-09-03 15:23:04 +10:00
sam 7e34fcb598 feat(eda): CEL expression environment (compile/validate at load, evaluate at dispatch)
Sixth slice of docs/prds/eda-playbook-engine.md (t2db.14): the
internal/domain/eda/expr package implementing the resolved open question 1
(CEL decision), standalone -- no coordinator/dispatch yet, mirroring how
t2db.13 built ModuleRegistry before any consumer.

- NewEnv: CEL env declaring the two context roots (event + actions, both
  map(string, dyn)) with DefaultCostLimit (100,000, tunable per J5).
- Compile: parses/type-checks an expression string; syntax error, unknown
  root (anything other than event/actions), or type error is a returned
  error -- the reject-at-load entry point the playbook loader and lint
  tool will share.
- Eval: evaluates a compiled program against a dispatch-time Context;
  missing-field/wrong-type/cost-limit errors are returned, never panics.
  No recover() wrapper: CEL is panic-free by design, verified by the
  hostile-data tests (5000-deep map, no panic). CEL's ref.Val wrappers
  (types.Bool etc.) are unwrapped to native Go values.

Dependency: cel.dev/cel-go v0.32.0 (direct), the only new dependency,
already vetted in the resolved doc's vetting record -- no re-vet.

Tests (table-driven, verified against real CEL semantics, not guessed):
valid boolean against event fields; syntax error at compile; unknown root
rejected at compile naming the root; missing event field errors not
panics (== on a missing key evaluates false -- verified CEL semantics);
has() presence macro; actions context reads; deep-nested hostile data
error-free or false without panic; cost-limit enforcement proven by
aborting a macro expression under a tiny limit (CEL's cost model accrues
on map/filter iteration, not field reads -- verified by probing).

task check clean (113/113 UI, exit 0).
2026-09-03 04:01:21 +10:00
sam 31283f47bf chore: updated ai-sdk core lib 2026-09-02 22:37:59 +10:00
sam 8e4923991d chore: bump ai-sdk version. 2026-08-29 00:17:16 +10:00
sam 212f762021 fix: go.mod bumped to 1.27.0 and stupid tests removed 2026-08-28 23:44:41 +10:00
sam a84085c89e fix(telegram): drop retry_after bandaid, bump go-telegram/bot to v1.24.0
go-telegram/bot v1.24.0 fixes getUpdates to honour Telegram's retry_after
on a 429 instead of its own 100ms-doubling-to-5s backoff (release notes:
https://github.com/go-telegram/bot/releases/tag/v1.24.0). pipelineErrorHandler
was our workaround for that upstream gap -- it now just logs.
2026-08-28 22:28:43 +10:00
sam 2395254559 build(deps): upgrade github.com/samcharles93/ai-sdk to v0.1.29 2026-08-27 21:40:01 +00:00
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 aaa9e85dd4 fix(agentexec): recover omitted finish calls 2026-08-24 14:56:56 +10:00
sam 566beff1d6 chore(deps): bump ai-sdk to v0.1.21
ai-sdk v0.1.21 wraps the cancellation cause in aborted-stream errors
("%w: %w") instead of formatting it, so errors.Is(err, context.Canceled)
is reliable again. The Telegram channel was compensating with a comment
explaining why errors.Is could not be trusted.

The code was already correct; only the comment was obsolete. It now
states the real reason for context.WithoutCancel(turnCtx): turnCtx is
dead on both stop and fault paths, so the cursor-drop edit needs a live
context. The runtime effect of the bump is that a /stop landing inside
the step loop is now logged as "chat turn stopped" rather than
"route failed".

Refs ai-sdk-0pn
2026-08-15 00:24:33 +10:00