mirror of
https://github.com/boshu2/agentops.git
synced 2026-09-14 15:08:13 +08:00
Bo
e1fae0dae6
RPI now owns the authorized outcome through finish, with Plan and Memory
loaded only when useful. Known defects get direct repair, and evidence
can change the approach under unchanged acceptance. Fresh exact-content
validation remains required. Memory provides optional recall, mining and
curation of reviewed topic pages; specialists and the fixed-dispatch
adapter remain optional.
The change reconciles current documentation and generated skill
projections. It preserves native budget and permission authority, BD
work ownership, protected external evidence storage and the distinction
between a supported lesson and demonstrated later benefit. It adds no
scheduler, work store, Go command or evidence schema.
Validation: required local Go/build/vet/race checks, aggregate suite,
generated-output check and 72 gates pass. The complete 44-test executor
suite passes; its shared-deadline fixture now tolerates CI scheduling
jitter while still requiring deadline exhaustion and preventing a third
launch. Fresh author-distinct review passed all 112 changed paths with
no findings; all seven exact-head CI checks passed at bfce33cce. Native
restricted-source enforcement and reduced token use are not established
by this change.
37 lines
2.3 KiB
Markdown
37 lines
2.3 KiB
Markdown
# Agent workflow reference
|
|
|
|
[AGENTS.md](../AGENTS.md) and the [RPI charter](../skills/rpi/SKILL.md) direct the
|
|
agent to own the authorized outcome through finish. Use the native agent and
|
|
shell; the tracker, Git and runtime keep their existing authority.
|
|
|
|
1. Use the existing intent. Invoke Plan only for missing intent or consequential
|
|
uncertainty. A trivial change needs no Plan, Recall or Learn worksheet.
|
|
2. Implement the smallest useful change, repair known defects directly, and
|
|
revise an approach when evidence disproves its assumption within unchanged
|
|
outcome and scope. Changing acceptance needs caller authority.
|
|
3. Run cheap discriminating checks while editing, then required integration
|
|
checks. Reserve capacity for finishing, final judgment and needed repairs.
|
|
4. Obtain fresh author-distinct final Validate over the exact subject. Same-family
|
|
is default; cross-model is opt-in, with no fixed ten-minute cap. PASS requires
|
|
all acceptance and empty `not_checked`; evidence gaps remain visible.
|
|
5. Repair known findings within real bounds and revalidate the changed subject.
|
|
A genuine causal stall admits at most one bounded helper, never a chain.
|
|
Report the outcome and evidence truthfully when complete or actually stopped.
|
|
|
|
[Memory](../skills/memory/SKILL.md) supplies on-demand recall and separately
|
|
budgeted mining/curation over caller-selected reviewed external topic pages.
|
|
BD owns work/status/handoffs, Git content, and native/CASS sources episodes.
|
|
Learning can update, qualify or remove a rule; no-change is valid. Only later
|
|
work establishes benefit. This lean route uses public or already-cleared inputs
|
|
and claims no native restricted-source enforcement.
|
|
|
|
Specialists, anti-ceremony audits, factories and outer-goal guidance are optional.
|
|
No new scheduler, command or process ledger is needed. The grandfathered pure
|
|
fixed-dispatch adapter is separately described in its own reference.
|
|
|
|
For exact intent snapshots, subject manifests, evidence storage, scope and
|
|
freshness, use [RPI traversal](architecture/rpi-traversal.md) and
|
|
[Validate mechanics](../skills/validate/references/mechanics.md). New proof goes
|
|
to caller-selected protected external non-Git storage; missing routing does not
|
|
permit a workspace fallback. Legacy `.agents/` evidence remains preserved.
|