Commit Graph
1604 Commits
Author SHA1 Message Date
samcharles93 f34c4076d6 Disk readiness probe watches only work_dir, so a full root filesystem goes unreported (archie)
Implements #835
2026-09-17 11:34:38 +00:00
sam c1ccf2f023 chore(telegram): resolve the state-store test conflict and drop dead clamp helper
Rebased onto main, which now carries an equivalent STATE_STORE_TOKEN isolation
guard in state_store_client_test.go from an independent baseline repair. The
two changes were the same fix expressed twice, so main's wording is kept and
this branch's duplicate is dropped -- the file is now identical to main and no
longer appears in the diff.

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

Removing clampToOneMessage, which this change orphaned: all three of its call
sites were replaced with clampToRunes directly, and `unused` flagged it. Dead
code left behind by a rewrite does not ship.
2026-09-17 11:31:05 +00:00
samcharles93 9faa1f14d7 Telegram tool-activity block is uncapped and crowds out the answer (archie)
Implements #839
2026-09-17 11:27:52 +00:00
sam 8ab86b86b3 Merge pull request #844 from samcharles93/fix/archied-watchdog-test-flake
fix(archied): stop the shutdown-watchdog test racing the scheduler
2026-09-17 21:24:29 +10:00
sam c4a27ccdc4 Update internal/gateway/stream.go 2026-09-17 21:19:53 +10:00
sam a8018ac06c fix(archied): stop the shutdown-watchdog test racing the scheduler
TestShutdownWatchdogHangingPastLeashForcesExit gave the watchdog two leash
lengths (60ms) to force an exit, but the 30ms leash only starts the timer --
the firing goroutine must then be scheduled before the injected exit is
observable. Measured margin is ~29.7ms, so the test is a wall-clock race
against the Go scheduler and fails intermittently on a loaded machine, where
it parks real work behind a gate failure unrelated to the change under test.

The assertion is now the contract that actually matters and that scheduling
jitter cannot falsify: the exit must not happen before the leash, and it must
happen. Waiting for it uses a generous ceiling, and the new elapsed >= leash
check catches an early fire strictly -- something the old test could not do,
because it only bounded lateness.

The inverse test asserts the ABSENCE of a forced exit, which load cannot
falsify (a slow runner only delays the exit being checked for), so it keeps a
tight bound and the suite stays fast.

Verified by mutation: removing the forced exit fails the first test, and
firing before the leash now fails it on the new elapsed check.
2026-09-17 11:17:19 +00:00
samcharles93 8c271801d1 fix: Repeated successful tool calls are never collapsed into a counted entry (archie)
Fixes #840
2026-09-17 11:13:11 +00:00
samcharles93 dae0fbe456 test: failing repro
Refs #840
2026-09-17 11:10:30 +00:00
samcharles93 53ed6d8d34 fix: baseline gate repair (go test ./... -count=1) 2026-09-17 11:03:29 +00:00
sam 2f67bd4335 fix(telegram): require the truncation wrapper before treating a count as metadata
Review found that a bare "showing 3/197 lines" inside ordinary output was
accepted as truncation metadata and replaced by a summary, hiding the real
result. Both built-in producers wrap the notice as "[truncated: …]"
(internal/tools/builtin/truncate.go), so the wrapper is now required rather
than tolerated: it is the only marker separating a notice the tool printed
from content that merely mentions a count.
2026-09-17 10:13:07 +00:00
sam b725e6137c fix(telegram): address greptile review on tool-result rendering
Four findings from review, all valid:

1. Search detection is now gated on the tool name rather than applied to every
   result. A compiler diagnostic ("file.go:42: message") has the same shape as
   a search hit, so counting it reported a build error as "N matches" and hid
   the diagnostic.

2. Only ripgrep match lines are counted. The hyphen context form
   ("path-N-text") and "--" group separators were being counted as matches, so
   a search with context requested reported the match count plus every
   surrounding context line.

3. The notice parser accepts shell's "showing last N/M lines" form as well as
   the plain "showing N/M lines" one. Shell emits the "last" form, which failed
   integer parsing and was not recognised as metadata -- so a truncated shell
   result quoted the raw truncation notice as its preview, the exact defect this
   change set out to remove. The summary now also states which end was kept
   ("97 lines total; showing last 66" for a tail truncation).

4. The renderer cases are consolidated into one table-driven test per the
   development protocol in AGENTS.md, covering all four defects above plus
   singular/plural, colons in paths, and module-cache noise.
2026-09-17 09:49:49 +00:00
sam 75403b3138 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 af3a8a2a61 refactor(config): delete the two decoded-but-unread policy fields
MemoryConfig.SessionTTL and ToolPolicy.ParallelExecution were decoded by
config loading and read nowhere, so setting either silently did nothing.
Removing them routes both keys into the unknown-key detector, which names
them in a boot warning instead. A live-looking knob wired to nothing is
the worse state, and the sibling memory.provider already earned a loud
load-time rejection for exactly this.

Also drops the config.example.toml line that shipped session_ttl into
every first-run config.toml via configtemplate.go, and the commented-out
dir_test.go assertions that would have re-created both fields under that
file's "make these pass without modifying them" header.
2026-09-17 00:32:02 +10:00
sam 0b3dc6c01f refactor(forge): delete the unwired RepliesAfter surface
DELETE: IssueForge.RepliesAfter and its Reply type had no production caller --
the waiting_human status exists and is reachable, but automatic detection of a
human reply never landed, so the intended poller was never built. Neither
implementation paginated either (both read one page of 50), so the method
would have been wrong if wired as-is.

The manual path is untouched: waiting_human remains reachable and an operator
requeues through the existing task-action flow. Removing the interface method
also removes seven test fakes that existed only to satisfy it.

No behavioural test accompanies this: a pure deletion has no assertion to
make fail, and the compiler enforces completeness across every implementation.
2026-09-15 16:54:16 +10:00
sam 51b0902926 merge: lane G (tools-builtin-3, tools-mcp-3, infra-misc-2, persistence-5) 2026-09-15 13:40:46 +10:00
sam 242d8322d5 refactor(store): use taskstate status constants in SQL
WIRE: internal/taskstate documents itself as the single source for the
persisted task status strings, but store.go re-declared them as bare SQL
literals. Reference the workflow status constants (aliases of taskstate)
so a rename of a status is a compile-time-visible migration instead of a
silent change in what ClaimNext/RecoverStale/OpenPRs/ClearTerminalTasks
match.
2026-09-15 13:39:15 +10:00
sam 7c5b81fd53 fix(container): enforce MaxUptime lifetime cap with a timer
WIRE: Config.MaxUptime and Acquire documented a hard container lifetime cap
(PRD section 4), but the code only wrapped ContainerCreate/ContainerStart in
a MaxUptime deadline that was cancelled when Acquire returned, so no running
container was ever killed. Wire the documented cap with a per-container
timer that stops and removes the container once the cap elapses.
2026-09-15 13:33:48 +10:00
sam a0dd21273b fix(mcp): cancel in-flight SSE reconnect on Stop
WIRE: the SSE transport's Stop contract already says it closes the
connection and waits for background readers, but the reconnect loop issued
its HTTP GET with the Start context, which Stop could not cancel, so Stop
blocked on readerWg.Wait() against an unreachable endpoint. Wire a
per-lifecycle cancel (mirroring the stdio transport's stopCh plus guarded
commit) so Stop interrupts the in-flight reconnect request.
2026-09-15 13:30:29 +10:00
sam f4e32ee6d4 docs(skill): drop comments that named the deleted skill.Discover
Lane F deleted skill.Discover/skill.DiscoverPlugins/skill.Skill (no
production caller) in 952bf4d, which left three comments in packages it did
not own describing or contrasting behaviour against a symbol that no longer
exists -- a dangling reference is the same drift class as an unreachable
code path, just cheaper to fix.

The behavioural statements are kept; only the dead names go. internal/skill's
Catalog skips a SKILL.md it cannot read, while this curator's store reports
the per-skill failure as an Action, so the test's rationale still holds
without naming the removed function.

Comment-only: no behaviour change, task check exit 0.
2026-09-15 13:17:54 +10:00
sam 280b744d8c merge: lane F (skill-2, workflow-engine-2, domain-records-2, forge-3) 2026-09-15 13:15:18 +10:00
sam a406c36f27 refactor(forge): delete dead CreateIssue surface
DELETE: no document in docs/architecture/ or docs/prds/ specifies a
production consumer for forge.IssueForge.CreateIssue. It has no
production caller -- the remaining repo matches are the GitHub
CreateIssueReaction and Gitea CreateIssueComment SDK methods. Removing
the interface method and the GitHub/Gitea/Noop implementations; the
other fakes that still define CreateIssue are test-only and out of lane
ownership, and an interface with one fewer method keeps them satisfying.
RepliesAfter and forge.Reply are untouched (a parallel FLAG record).
2026-09-15 13:13:55 +10:00
sam 1177012a3a refactor(binding): delete dead Matcher.Overlaps method
DELETE: no document in docs/architecture/ or docs/prds/ specifies a
consumer for binding.Matcher.Overlaps, and it has no caller or test
caller. The store enforces the overlap invariant with its own SQL
(internal/store/bindings.go InsertBinding/UpdateBinding), which is out
of this lane's ownership and left untouched. The doc comment's
empty-Source rule is already covered by Binding.validateCommon's
"matcher.source is required" check, so nothing needs moving.
2026-09-15 13:12:22 +10:00
sam bf7eb16bc4 fix(builtin): bound read/edit filesystem work by DefaultToolTimeout
WIRE: read and edit each declared a DefaultToolTimeout deadline and then
discarded it, so the documented contract (Tools that exceed this are
cancelled) was a no-op on the live tool-executor path. Wire the deadline
through runWithContext, the same helper write already uses, so a hung
filesystem cannot block the tool executor.
2026-09-15 13:12:21 +10:00
sam 0548a944b1 refactor(skillbuild): delete dead AugmentRegistry path
DELETE: no document in docs/architecture/ or docs/prds/ names
AugmentRegistry as a consumer. The live per-task registry construction is
skillbuild.BuildRegistry(workDir) at internal/app/agentworker/
task_execution.go; AugmentRegistry was an unwired alternate merge-over-
base path (with collision/override and nil-base semantics) that only
tests exercised. mergeSkillWorkflows remains reachable through
BuildCatalog/BuildRegistry.
2026-09-15 13:10:51 +10:00
sam 952bf4d5d6 refactor(skill): delete dead Discover/DiscoverPlugins/Skill path
DELETE: no document in docs/architecture/ or docs/prds/ specifies a
consumer for skill.Discover, skill.DiscoverPlugins, or the skill.Skill
type. Live per-skill loading is reimplemented inline in
internal/domain/workflow/agent.go loadSkillBody via
Catalog/SkillForWorkflow/Parse/LoadPlugins, and daemon startup and webui
use Catalog/CatalogRoots. The parallel fully-tested path had no caller
to keep it honest, so it is removed together with its now-dead tests.
2026-09-15 13:08:43 +10:00
sam ab2793e87f merge: lane B (forge-2 flagged, daemon-1, persistence-2) 2026-09-15 13:04:28 +10:00
sam 2b84ec2989 fix(daemon): forward configured MCP servers to task agents
WIRE: taskrun.Request.MCPServers is documented as the channel for MCP server
definitions the agent should construct, and the archie-agent worker consumes
it (task_execution.go startMCPProviders). The daemon's request constructor
dropped the field in a refactor, so configured MCP servers never reached a
task container. Restore it from d.configFor(task).Tools.MCPServers.
2026-09-15 13:01:53 +10:00
sam d0395cebd5 merge: lane C (tools-core-7, tools-core-6) 2026-09-15 13:01:26 +10:00
sam b5230941ec merge: lane A (gate-subsystem-2, gate-subsystem-1, infra-misc-3) 2026-09-15 12:59:30 +10:00
sam fbcfd68cd1 fix(taskactions): resolve max_retries from the task's owning identity
WIRE, not delete: per-repo max_retries is a configured field with a real
consumer (the retry gate), and it works for the legacy single-identity
[[repos]] list. In a multi-identity deployment repositories live under
[[identities.repos]] and there is no global [[repos]] at all, so the resolver
never saw the override and a parked task was killed at the global cap rather
than the configured one.

MaxRetries now consults the identity named on the task before the legacy list,
then falls back to the global cap. Identity name is the only thing that says
which repository list owns a persisted row.

Red-then-green: TestMaxRetriesResolvesFromTheOwningIdentity gained the
multi-identity cases; "identity repo override wins over the global cap" failed
with `MaxRetries = 3, want 7`. Two neighbouring cases keep the fix honest:
another identity's override must not leak, and the legacy path must still
resolve. Mutation-verified by deleting only the identity lookup, keeping the
extracted helper and the API intact.
2026-09-15 12:59:06 +10:00
sam 8ea45e836b refactor(tools/mcp): delete unreachable MCP adaptation path
DELETE: mcp.Client.RegisterTools and its handlerFor/writeMultimodalResult
chain, plus the WithMediaDir and WithParallelToolCalls options, had no
production caller -- the live adaptation path is provider/mcp.Provider,
which now owns binary media persistence itself. A repo-wide search finds
no remaining reference outside the composition contract test that asserts
RegisterTools must not appear, so the two paths can no longer diverge.
2026-09-15 12:58:10 +10:00
sam 16d331a16e refactor(daemon): remove unreachable SQLite poll/drain path
DELETE: NATS startup is mandatory (config.NATSConfig documents "there is no
broker-off execution mode"), so Daemon.Tasks is never nil in production and
pollSQLite/drainSQLite are unreachable. Remove them and their d.Tasks==nil
call sites, and correct the Tasks field comment.
2026-09-15 12:57:54 +10:00
sam 0e0611a6b3 refactor(gateway): share sensitive-key markers with webhookguard
Resolves infra-misc-3.

WIRE: webhookguard.SensitiveKeyMarkers is now the single exported marker
list, and gateway.sensitiveParameterKey consumes it instead of inlining an
identical copy. webhookguard/redact.go documented that the two lists must
match "exactly so the two redaction paths agree"; that agreement is now
structural (one slice, two consumers) rather than a comment nothing
enforces. A new test asserts both consumers observe the same set, so a
future edit cannot silently desynchronise chat-transcript redaction from
webhook-capture redaction.
2026-09-15 12:55:52 +10:00
sam 8b06d4192c merge: lane E (tools-media-1, transport-nats-2, release-1) 2026-09-15 12:55:07 +10:00
sam c9a5ae4aeb fix(tools/provider/mcp): preserve MCP binary tool results for delivery
WIRE: the live provider/mcp adaptation path is the only production MCP
consumer and its handlerFor detected image/audio/resource-blob blocks but
returned an empty MultimodalResult, so telegram_setup's multimodalMediaRefs
(which reads only result.URLs) had nothing to deliver. Decode each media
block into the provider's media root and populate Files, SubdirHint and
URLs with local-path refs the channel uploads.
2026-09-15 12:54:07 +10:00
sam cd775f8705 merge: lane D (curator-1, staterpc-2) 2026-09-15 12:53:32 +10:00
sam 72d80f1dfc fix(releaseupdate): don't treat empty available as deferred
Service.Check matched deferred[component.ID] == component.Available, and a
never-deferred recipient's absent entry is the empty string -- equal to an
empty Available emitted for a component with no update. Guard on a real
(non-empty) available version before applying the deferral, so an
up-to-date recipient is not told their update is deferred. No WIRE/DELETE
decision applies: this is a correctness fix on a live consumer, not
unreachable code.
2026-09-15 12:53:25 +10:00
sam bb780e63b4 fix(scheduling): record a completed run so a recurring job stops re-firing every tick
WIRE, not delete: cronstore.Store.MarkRun is the documented run-completion
step ("once the ticker has dispatched a job, the runner ... calls MarkRun to
keep next_run fresh") and the scheduling engine is now started at boot, but
nothing in production called it. Due returns every job whose NextRun is at or
before now, so with NextRun frozen in the past a job with a 1h interval was
handed to the runner on every tick.

The delivery Router is the single Runner the engine is given and, per this
package's own doc, the only place that knows a job store exists, so it is the
producer-side site. RouterStore (SpecLookup + RunRecorder) widens only what
the Router takes; the per-kind runners keep the narrow SpecLookup, and
NewRouter's signature is unchanged, so no call site moved.

Only a successful run records, matching the store's own contract that an
interval or cron schedule fires "after the last successful run". A one-shot
schedule reports ErrScheduleUnsupported -- it has no recurring next run by
definition -- which is swallowed rather than returned, because propagating it
would make the engine emit KindJobError for a job that actually succeeded.

Red-then-green: TestRouterAdvancesTheScheduleAfterASuccessfulRun asserts
LastRun is set and NextRun moved past now, and failed on both counts before
the change. TestRouterToleratesAOnceScheduleWithoutANextRun pins the
sentinel half. Mutation-verified by replacing only the record call with
`return nil`, keeping the API intact.
2026-09-15 12:53:02 +10:00
sam e93ad6353b fix(gate): validate finding level and share the blocking threshold
Resolves gate-subsystem-2 and gate-subsystem-1.

WIRE: gate.Finding.Level is now a typed gate.Level restricted to
LevelError/LevelWarn, and Finding.Validate rejects any other value so a
mis-typed or empty level fails the gate closed instead of silently
downgrading an intended blocker to a pass -- mirroring the fail-closed
standard ReviewFinding.Validate already sets in
internal/domain/workflow/review_findings.go.

WIRE: StageYaegiGate now delegates the blocking decision to
gate.Finding.Blocking instead of re-implementing the raw "error" literal,
so the script-facing gate.Blocking helper (exposed by gateextract to
interpreted .archie/gate.go scripts) and the rule the daemon actually
enforces share one source of truth and cannot drift.
2026-09-15 12:52:00 +10:00
sam 0a73394c23 fix(servicediscovery/nats): validate config after defaults
Root-cause fix: Connect validated the raw config before withDefaults, so
the Heartbeat<TTL guard was skipped whenever Heartbeat was unset and a
custom TTL below DefaultHeartbeat passed as a silently expiring registry.
Apply defaults first so the documented invariant is enforced. No
WIRE/DELETE decision applies: this is a producer-ordering bug, not
unreachable code.
2026-09-15 12:51:17 +10:00
sam 4268a25d30 fix(staterpc): preserve marshal_error marker in eventDataJSON
WIRE: docs/prds/state-store-contract.md §11 requires the remote wire and the
local adapter to behave identically. The local adapter (internal/store/events.go)
records a {"marshal_error":%q} marker when json.Marshal of event Data fails,
while eventDataJSON silently returned "" on the same failure, emptying the
event's Data on the wire. Carry the same marker so an unmarshalable Data
value survives the hop with the local adapter's fidelity.
2026-09-15 12:50:57 +10:00
sam 3300ac0a31 fix(memory): install the threat scanner the composition root never wired
WIRE, not delete: docs/architecture/configuration.md's behavioural-literals
inventory lists the "Memory safety scanner -- compiled prompt-injection and
sensitive-data patterns with fixed warn/block consequences" as current
behaviour, and internal/memory.Manager.HandleToolCall already refuses a write
whose content scans as ThreatBlock. The consumer existed; the producer never
called SetScanner, so Manager.ScanContent short-circuited to ThreatNone and
the gate was a permanent no-op.

setupMemory now installs memory.DefaultScanner. Consequences stay at the
documented defaults -- scanReject is false, so a prompt-injection match is
downgraded to a warn and logged rather than refusing the operator's write.

Red-then-green: TestSetupMemoryInstallsAThreatScanner asserts the composed
manager actually scans, not that a field was assigned; it failed with
"ScanContent = ThreatNone for a prompt-injection payload" before the change.
Mutation-verified by removing only the SetScanner call (API intact) and
watching the same assertion fail.
2026-09-15 12:49:13 +10:00
sam 0c5ea7b2a0 test(telegram): pin upload-ceiling agreement with send_file
Choice: cross-package test (pin). Both ceiling pairs are live producers
and currently agree, so the WIRE/DELETE rule does not apply. Deriving one
shared definition would either require a new package outside this lane's
ownership or bind the channel-free sendfile tool to the telegram package;
the cross-package test pins the documented 'the two must agree' contract
at the duplicate itself.
2026-09-15 12:48:51 +10:00
sam 8bef9605f3 fix(curator): populate PassInput.Since with the prior pass time
WIRE: docs/prds/session-memory-curator.md specifies that each pass finds
"sessions with activity since the last pass", and its effectiveSince rule
treats a zero Since as "the runtime declining to name a horizon" (24h
fallback for the first pass). The runtime is the only production constructor
of PassInput and already carries lastPass, so it must name the horizon at the
producer by setting Since to the prior pass time. Previously Since was never
set, so the session curator fell back to now-24h on every pass and re-read
the same window each chat turn.
2026-09-15 12:48:38 +10:00
sam b0050ff20a refactor(state): delete the dead IncrementRetryCount RPC (breaking change, accepted)
IncrementRetryCount had zero production callers -- only tests and the
staterpc plumbing referenced it. taskactions.Service.applyRetry already
uses the atomic RetryTask exclusively, which increments retry_count and
requeues in one transaction.

Unlike ListCaptures/ListUndispatchedCaptures (kept as declared-unconsumed
compatibility surfaces because a rolling deploy could have an old
client/server pairing mid-flight), this repo has one production consumer
(see AGENTS.md's solo-project note), so the breaking removal is accepted
outright rather than deprecated-and-kept. Deleted the Go method, the
storecontract interface entry, the staterpc server/client methods, and the
RPC/messages from state.proto, regenerating the .pb.go/_grpc.pb.go pair.

Test fixtures that used IncrementRetryCount as a setup helper now drive
retry_count through the real path instead: queries_test.go bumps it via
direct SQL (same package, no contract to route through), and
api_tasks_actions_test.go now loops RetryTask+Transition, which exercises
production code instead of a deleted one.
2026-09-15 11:24:57 +10:00
sam 7c68e1d436 feat(channels): wire ConfigSchema/ValidateConfig into a startup validation loop
Every chat gateway (Telegram, email, webhook) implemented channels.Channel's
ConfigSchema/ValidateConfig contract but nothing ever called it, so a
misconfigured gateway would only fail once it tried to start rather than at
boot. setupEmailGateway/setupWebhookGateway now call ValidateConfig before
registering a start function and return false (fatal boot error, matching
setupTelegramGateway's existing convention) on failure; telegram_setup.go
does the same for the already-constructed *telegram.Gateway.

Fixed telegram.Gateway.ValidateConfig/ConfigSchema along the way: it only
recognised token_env, but chat.telegram.token (a secret reference) is an
equally valid, already-precedent-ordered credential source per
resolveTelegramToken. Wiring the old validator unmodified would have
rejected every Token-only deployment. Also corrected ConfigSchema's stale
allowed_chat_ids property name to the real allowed_user_ids toml key.
2026-09-15 11:22:23 +10:00
sam 04d690322a Merge branch 'crew/cluster3' into crew-integration 2026-09-15 10:33:15 +10:00
sam d7ba77e1e9 Merge branch 'crew/cluster2' into crew-integration 2026-09-15 10:33:15 +10:00
sam 49da68fb25 Merge branch 'crew/cluster1' into crew-integration 2026-09-15 10:33:15 +10:00
sam abb23247c5 refactor(tools): delete unused plugin-tool registration API from builtin.Registry
RegisterPluginTool/SetPluginToolExecutor/UnregisterPluginTools and the
PluginToolDef/PluginToolExecutor types have no production caller.
Plugin/MCP tool registration flows through agentexec.pluginToolSet and
internal/tools.Registry, not this staging registry (tools-builtin-2,
duplicate of tools-core-8).
2026-09-15 10:25:59 +10:00