Commit Graph
9 Commits
Author SHA1 Message Date
sam 20bff1a367 feat(agentexec,workflow): surface tool calls on the task timeline
archie-core-467 wired tool-call visibility into the interactive chat
gateway, but a workflow task's own transcript never showed what its
tools actually did -- only stage/agent-finish events existed, so
there was no way to confirm an agent's summary matched what it really
ran.

Adds a ToolCallReporter, invoked once per completed call from
toolExecute (the single choke point every tool call passes through
before reaching a model), reported via a new ToolSetOptions.OnToolCall
hook. Runner.Run grows a report parameter to carry it in: InProcessRunner
wires it through, since it executes in the same process as its tools;
SubprocessRunner and NATSRunner accept and ignore it, since their tool
calls happen in a different process with nothing here to observe them.

The workflow engine turns each report into a tool_call event on the
task's own Bus (agent.go, implement.go), riding the same NATS
event-forwarding archie-core-518 already built to get container
events onto the daemon's timeline.

Scoped to the central tool registry (read/write/edit/grep/shell/...)
built via BuildToolSet; capture tools (structured finish output) and
run_go_script build their ToolSet entries directly and are not yet
covered.
2026-08-15 12:53:41 +10:00
sam 529b25eada docs: phase 3a — nilerr review, all 11 sites were false positives (qa4)
97 -> 85. Not one of the eleven nilerr findings was a bug.

I called these "real bug candidates" when I planned the phases. I was
wrong, and the reason is worth recording: every site is the same
deliberate idiom, and a linter cannot see intent.

  - inprocess.go (5) and gateway.go (2) are handlers that report a
    problem as TEXT to their consumer. A tool handler returning a Go
    error aborts the tool call; returning "rejected: ..." lets the model
    read the feedback and retry with valid arguments. A chat handler
    returning a Go error surfaces as a gateway fault instead of a usage
    hint to the human.
  - worker.go carries runErr in the response envelope's Error field.
    Returning it as a Go error too would double-report and abort the
    NATS reply.
  - email.go returns nil when Accept fails because context cancellation
    closed the listener. That is a clean shutdown.
  - codesearch.go skips an unreadable entry and continues the walk. A
    best-effort index must not abort on one bad file.
  - skill.go is documented in the function comment already: a
    non-directory skills path means "no skills", not a fatal error.

Annotated each with //nolint:nilerr and the specific reason rather than
excluding the linter by path, so nilerr stays live everywhere else and
the next reader wondering "why nil here?" gets an answer at the site.

This is the phase I insisted on keeping single-session and out of the
subagent fan-out. A worker told to "fix nilerr" would have converted all
eleven to error returns: malformed tool arguments would hard-fail the
agent loop instead of being correctable, chat typos would read as
gateway faults, and shutdown would log spurious errors. Every test would
still have passed.
2026-07-28 01:39:22 +10:00
sam f8df051b19 feat: bounded concurrent task dispatch in daemon (archie-core-u64)
Daemon previously processed one task at a time. Add bounded concurrent
dispatch for SQLite and NATS agent modes, reusing [containers].max_concurrency
(0 = unlimited). Same-repository tasks stay FIFO-serialized to avoid worktree
conflicts; different repositories now run concurrently.

Unblocks archie-core-l1q (NATS transport) and archie-core-g1l
(per-repo allow_concurrent override).
2026-07-24 07:42:13 +10:00
archie b164bcbb14 fix: agent context doubled up — conversation history duplicated in prompt (archie)
Implements #65
2026-07-23 23:47:23 +10:00
sam 2182cc00a5 refactor: replace hardcoded workflow→skill maps with catalog-driven lookup
Skills now declare their workflow in metadata.archie.workflow.
Catalog() scans frontmatter only (lazy, Tier 1). SkillForWorkflow()
derives the skill directory from the catalog — no hardcoded maps.

Removed workflowToSkill map (agent.go) and workflowToSkillDir switch
(worker.go). Both daemon and agent use the same catalog-based lookup.

Skills renamed to archie-wf-* convention. SKILL.md files updated with
workflow metadata field.

Progressive disclosure Tier 1: Catalog() returns name+description
+workflow. Tier 2: LoadBody() loads full body on activation.
2026-07-22 03:44:42 +10:00
sam d3c843e8f5 feat: close final two gaps — agent skill loading + core plugin registry
Agent skill loading: HandleMessage now loads .agents/skills/<workflow>/SKILL.md
from its own workspace before running stages. Skill body prepended to each
stage's Mission. Mirrors daemon-side loadSkillBody but owned by the agent
per PRD section 1. workflowToSkillDir mapping added.

Core plugin registry: internal/plugin package with Plugin interface
(Name, Version), Registry type, and LoadDir function. Yaegi-interprets
.go files from ~/.config/archie/plugins/ at startup. Failed plugins are
skipped. PRD section 5 Layer 2.

All 21 PRD claims now have tests. Zero failing tests.
2026-07-22 03:37:15 +10:00
sam ce9ce050ed feat: close Gap 1 — per-task agent (multi-stage batch execution)
HandleMessage now supports two modes:
- Single-stage (Request only): backward compatible, no Workflow set
- Per-task batch (Workflow + Stages): runs all stages sequentially,
  accumulates tokens/iterations/notes, sets TaskCompleted on success

New fields:
- AgentRequestMessage.Stages []Request — batch of agent stages
- AgentResponseEnvelope.TaskCompleted bool — true when batch done

RunnerFactory injection for testability — HandleMessage accepts a
factory function. DefaultRunnerFactory creates InProcessRunner.
Tests use mockRunner.

runStages() executes each stage, stops on first failure, aggregates
results. Combined summary uses "[stage] summary" format.
2026-07-22 03:20:37 +10:00
sam e8ffa20b33 test: rewrite regression tests as behavioral (not structural)
Replaces field-existence checks with runtime behavior verification:

Gap 1 (per-task agent): FAILING
  TestHandleMessageReadsWorkflowField verifies HandleMessage produces
  different results when Workflow is set vs. unset. Currently identical
  — HandleMessage ignores the Workflow field. Must run full multi-stage
  workflow per PRD section 1.

Gap 3 (response/system split): PASSING
  TestHandleMessageRoutesSystemMessagesSeparately verifies Channel
  echoes from request to response. HandleMessage now reads input Channel
  and sets it on the response envelope. Subject functions verified
  distinct.

Gap 5 (daemon review): PASSING
  TestReviewResultBlocksOnResultWhenRejected verifies ReviewResult
  hook gates OnResult. Error blocks — OnResult never called. Nil
  allows — OnResult called normally.

Agent processing extracted into agentexec.HandleMessage for testability.
cmd/archie-agent delegates to it.
2026-07-22 03:13:57 +10:00
sam 86339b4d0d feat: add subprocess agent runner 2026-07-21 23:21:24 +10:00