toki/iop
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

sync: agent-ops from agentic-framework v1.1.201

Browse source
This commit is contained in:
toki 2026-08-13 22:57:19 +09:00
parent e6a820d03c
commit 8497bc0ebc
6 changed files with 58 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
agent-ops/.version
View file

@ -1 +1 @@
1.1.200
1.1.201

1
agent-ops/skills/common/code-review/SKILL.md
View file

@ -164,6 +164,7 @@ The diff is the starting point, not the boundary. Follow behavior and API connec
Review scope control:
- Use the plan's commands and checkpoints as the primary evidence. Add one focused, possibly table-driven reproducer only when needed to prove a suspected blocking defect; do not build speculative exhaustive probe matrices.
- Exclude unrequested generalization, future-proofing, cleanup, and architectural expansion from Required/Suggested findings unless an explicit acceptance criterion or concrete failing case makes them necessary.
- Execute the applicable plan verification commands and any focused reproducer needed for the verdict. Treat implementation-owned output as a handoff and comparison source, not as a substitute for fresh reviewer verification. If recorded output is absent or insufficient but the command is available and safe in the current authorized environment, run it and repair `Verification Results` before classifying findings. If a check fails, collect enough source/runtime data to establish the root cause and one implementable fix; never emit a diagnostic-only finding that asks the next worker to investigate or choose among alternatives.
- In a follow-up review, keep Required findings within the current plan, inherited Required findings, direct regressions from the fix, and concrete violations of the original SDD or contract acceptance criteria. Exclude unrelated pre-existing work from the verdict and Required/Suggested/Nit counts; mention it only in the final report as an out-of-scope task candidate.
- Before adding a new Required that the current plan did not state, cite the exact original plan/SDD/contract criterion it violates or provide a concrete failing case. Do not require a preferred test shape when existing deterministic evidence proves the same behavior.

2
agent-ops/skills/common/orchestrate-agent-task-loop/SKILL.md
View file

@ -57,7 +57,7 @@ Command templates may use only `{agent}`, `{model}`, `{reasoning_effort}`, `{tar
Each route owns its ordered `candidates` plus optional `rule_id`, `policy_priority`, and `reason_codes`. A route may use catalog-owned `windows` instead of a fixed candidate list; every window supplies an IANA timezone, start/end time, and candidates. Exactly one window must match.
The bundled review routes vary model and reasoning effort by routed grade instead of fixing every review to one target: G01-G04 use Terra/high, G05-G08 use Sol/high, and G09-G10 use Sol/xhigh. Runtime or project catalog overrides may replace this default tiering.
The bundled review routes vary model and reasoning effort by routed grade instead of fixing every review to one target: G01-G04 use Terra/high, G05-G08 use Sol/medium, and G09-G10 use Sol/high. Sol/xhigh remains cataloged for explicit runtime or project overrides but is not selected by a bundled default route. Runtime or project catalog overrides may replace this default tiering.
Before work starts, the dispatcher:

60
agent-ops/skills/common/orchestrate-agent-task-loop/assets/default-execution-catalog.json
View file

@ -161,6 +161,30 @@
"terminal_success": "turn_completed"
}
},
"codex-sol-medium": {
"agent": "codex",
"model": "gpt-5.6-sol",
"reasoning_effort": "medium",
"execution_class": "cloud_model",
"selfcheck_required": false,
"runtime": {
"command": [
"codex",
"exec",
"--json",
"-C",
"{workspace}",
"-m",
"{model}",
"-c",
"model_reasoning_effort=\"{reasoning_effort}\"",
"--dangerously-bypass-approvals-and-sandbox",
"{prompt}"
],
"output_format": "jsonl",
"terminal_success": "turn_completed"
}
},
"codex-sol-high": {
"agent": "codex",
"model": "gpt-5.6-sol",
@ -315,13 +339,13 @@
]
},
"local-G09": {
"candidates": ["codex-sol-xhigh", "codex-terra-high"],
"candidates": ["codex-sol-high", "codex-terra-high"],
"rule_id": "worker-local-g09-catalog",
"policy_priority": 30,
"reason_codes": ["worker_catalog_lane"]
},
"local-G10": {
"candidates": ["codex-sol-xhigh", "codex-terra-high"],
"candidates": ["codex-sol-high", "codex-terra-high"],
"rule_id": "worker-local-g10-catalog",
"policy_priority": 30,
"reason_codes": ["worker_catalog_lane"]
@ -363,25 +387,25 @@
"reason_codes": ["worker_catalog_lane"]
},
"cloud-G07": {
"candidates": ["codex-sol-high", "codex-terra-high"],
"candidates": ["codex-sol-medium", "codex-terra-high"],
"rule_id": "worker-cloud-g07-catalog",
"policy_priority": 30,
"reason_codes": ["worker_catalog_lane"]
},
"cloud-G08": {
"candidates": ["codex-sol-high", "codex-terra-high"],
"candidates": ["codex-sol-medium", "codex-terra-high"],
"rule_id": "worker-cloud-g08-catalog",
"policy_priority": 30,
"reason_codes": ["worker_catalog_lane"]
},
"cloud-G09": {
"candidates": ["codex-sol-xhigh"],
"candidates": ["codex-sol-high", "codex-terra-high"],
"rule_id": "worker-cloud-g09-catalog",
"policy_priority": 30,
"reason_codes": ["worker_catalog_lane"]
},
"cloud-G10": {
"candidates": ["codex-sol-xhigh"],
"candidates": ["codex-sol-high", "codex-terra-high"],
"rule_id": "worker-cloud-g10-catalog",
"policy_priority": 30,
"reason_codes": ["worker_catalog_lane"]
@ -392,22 +416,22 @@
"local-G02": {"candidates": ["codex-terra-high"], "rule_id": "review-local-g02-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G03": {"candidates": ["codex-terra-high"], "rule_id": "review-local-g03-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G04": {"candidates": ["codex-terra-high"], "rule_id": "review-local-g04-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G05": {"candidates": ["codex-sol-high"], "rule_id": "review-local-g05-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G06": {"candidates": ["codex-sol-high"], "rule_id": "review-local-g06-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G07": {"candidates": ["codex-sol-high"], "rule_id": "review-local-g07-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G08": {"candidates": ["codex-sol-high"], "rule_id": "review-local-g08-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G09": {"candidates": ["codex-sol-xhigh"], "rule_id": "review-local-g09-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G10": {"candidates": ["codex-sol-xhigh"], "rule_id": "review-local-g10-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G05": {"candidates": ["codex-sol-medium"], "rule_id": "review-local-g05-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G06": {"candidates": ["codex-sol-medium"], "rule_id": "review-local-g06-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G07": {"candidates": ["codex-sol-medium"], "rule_id": "review-local-g07-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G08": {"candidates": ["codex-sol-medium"], "rule_id": "review-local-g08-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G09": {"candidates": ["codex-sol-high"], "rule_id": "review-local-g09-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"local-G10": {"candidates": ["codex-sol-high"], "rule_id": "review-local-g10-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G01": {"candidates": ["codex-terra-high"], "rule_id": "review-cloud-g01-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G02": {"candidates": ["codex-terra-high"], "rule_id": "review-cloud-g02-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G03": {"candidates": ["codex-terra-high"], "rule_id": "review-cloud-g03-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G04": {"candidates": ["codex-terra-high"], "rule_id": "review-cloud-g04-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G05": {"candidates": ["codex-sol-high"], "rule_id": "review-cloud-g05-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G06": {"candidates": ["codex-sol-high"], "rule_id": "review-cloud-g06-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G07": {"candidates": ["codex-sol-high"], "rule_id": "review-cloud-g07-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G08": {"candidates": ["codex-sol-high"], "rule_id": "review-cloud-g08-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G09": {"candidates": ["codex-sol-xhigh"], "rule_id": "review-cloud-g09-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G10": {"candidates": ["codex-sol-xhigh"], "rule_id": "review-cloud-g10-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]}
"cloud-G05": {"candidates": ["codex-sol-medium"], "rule_id": "review-cloud-g05-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G06": {"candidates": ["codex-sol-medium"], "rule_id": "review-cloud-g06-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G07": {"candidates": ["codex-sol-medium"], "rule_id": "review-cloud-g07-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G08": {"candidates": ["codex-sol-medium"], "rule_id": "review-cloud-g08-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G09": {"candidates": ["codex-sol-high"], "rule_id": "review-cloud-g09-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]},
"cloud-G10": {"candidates": ["codex-sol-high"], "rule_id": "review-cloud-g10-catalog", "policy_priority": 10, "reason_codes": ["review_catalog_lane"]}
}
}
}

20
agent-ops/skills/common/orchestrate-agent-task-loop/tests/test_select_execution_target.py
View file

@ -92,18 +92,18 @@ class SelectorTests(unittest.TestCase):
},
"local-G07": ["opencode-glm-max", "codex-terra-high"],
"local-G08": ["opencode-glm-max", "codex-terra-high"],
"local-G09": ["codex-sol-xhigh", "codex-terra-high"],
"local-G10": ["codex-sol-xhigh", "codex-terra-high"],
"local-G09": ["codex-sol-high", "codex-terra-high"],
"local-G10": ["codex-sol-high", "codex-terra-high"],
"cloud-G01": ["codex-spark-xhigh", "opencode-glm-medium", "codex-terra-high"],
"cloud-G02": ["codex-spark-xhigh", "opencode-glm-medium", "codex-terra-high"],
"cloud-G03": ["opencode-glm-high", "codex-terra-high"],
"cloud-G04": ["opencode-glm-high", "codex-terra-high"],
"cloud-G05": ["opencode-glm-max", "codex-terra-high"],
"cloud-G06": ["opencode-glm-max", "codex-terra-high"],
"cloud-G07": ["codex-sol-high", "codex-terra-high"],
"cloud-G08": ["codex-sol-high", "codex-terra-high"],
"cloud-G09": ["codex-sol-xhigh"],
"cloud-G10": ["codex-sol-xhigh"],
"cloud-G07": ["codex-sol-medium", "codex-terra-high"],
"cloud-G08": ["codex-sol-medium", "codex-terra-high"],
"cloud-G09": ["codex-sol-high", "codex-terra-high"],
"cloud-G10": ["codex-sol-high", "codex-terra-high"],
}
expected_targets = {
"pi-ornith-high",
@ -111,6 +111,7 @@ class SelectorTests(unittest.TestCase):
"opencode-glm-high",
"opencode-glm-max",
"codex-spark-xhigh",
"codex-sol-medium",
"codex-sol-high",
"codex-sol-xhigh",
"codex-terra-high",
@ -137,9 +138,9 @@ class SelectorTests(unittest.TestCase):
expected = (
["codex-terra-high"]
if grade <= 4
else ["codex-sol-high"]
else ["codex-sol-medium"]
if grade <= 8
else ["codex-sol-xhigh"]
else ["codex-sol-high"]
)
decision = selector.policy.select_policy(
catalog=catalog,
@ -196,6 +197,9 @@ class SelectorTests(unittest.TestCase):
'model_reasoning_effort="{reasoning_effort}"',
terra.runtime["command"],
)
sol_medium = catalog.targets["codex-sol-medium"]
self.assertEqual(sol_medium.reasoning_effort, "medium")
self.assertEqual(sol_medium.runtime["terminal_success"], "turn_completed")
sol_high = catalog.targets["codex-sol-high"]
self.assertEqual(sol_high.reasoning_effort, "high")
self.assertEqual(sol_high.runtime["terminal_success"], "turn_completed")

1
agent-ops/skills/common/plan/SKILL.md
View file

@ -195,6 +195,7 @@ Before choosing plan files or task directory names, apply the split decision pol
Complete all items below before creating active plan/review files. Work through them in order; do not proceed to the next step until every checkbox is done. Keep the user request as the scope anchor and reconcile derived acceptance conditions before the split decision; do not create a separate routing summary. In `prepare-follow-up`, treat the reviewer's closed finding packet as the decision authority: repository reads validate its consistency and supply implementation mechanics, but do not reopen root cause or solution selection. If required evidence, root cause, or a selected fix is missing or contradicted, return `needs_evidence` to code-review so the reviewer corrects it in the same review pass; never pass investigation or alternatives to the worker. The only allowed file edits before writing plan/review files are local `agent-roadmap/current.md` creation or `.gitignore` block repair needed for roadmap routing.
- [ ] **Resolve verification context** — because implementation plans include verification, consume supplied `verification_context` when present and confirm its source paths, commands, expected results, preconditions, constraints, gaps, and confidence still apply. On first pass, derive missing facts from repository manifests, scripts, workflows, domain rules, related tests, user-provided environment facts, and safe read-only probes. In `prepare-follow-up`, require the reviewer to have collected every fact needed for diagnosis and fix selection; derive only mechanical command/path details, and return `needs_evidence` rather than performing missing review analysis. Record which facts came from the handoff and which came from repository-native validation. A missing optional first-pass handoff is not a user-review blocker.
- [ ] **Keep the plan minimal** — choose the smallest change that satisfies the stated goal and required acceptance criteria. Reuse existing structure; exclude unrequested generalization, future-proofing, cleanup, and architectural expansion.
- [ ] **Read all source files in full** — read every source file the change will touch, whole file. No partial reads.
- [ ] **Preflight external verification** — when any required verification leaves the current checkout, including remote runner, field/bootstrap, external provider, Docker/code-server, emulator/device, or shared long-running runtime, confirm or derive a read-only preflight before writing final verification commands. Record runner, repo root/workdir, branch/HEAD/dirty state, source sync status, binary/artifact paths, command help/version output needed by the verification, config path, runtime identity, ports/process state, external hosts, and OS/arch assumptions. If the preflight shows stale artifacts, dirty/divergent checkout, wrong identity, missing command, closed ports, host OS mismatch, or unsynced source, add an explicit setup/sync/rebuild step or report the blocker.
- [ ] **Read all test files in full** — read every test file that exercises the changed behavior, including files identified by the verification context and repository test layout.