You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 3bdd6e7
Browse filesBrowse the repository at this point in the historyBrowse files
Copy file name to clipboardExpand all lines: .agents/skills/launch-openshell-gator/SKILL.md
+12-18Lines changed: 12 additions & 18 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -13,7 +13,7 @@ For gator's PR/issue validation policy, load `gator-gate` inside the launched sa
13
13
14
14
## Non-Negotiable Rules
15
15
16
-
- Keep normal gator launches supervised: use `--watch --background` and let the in-sandbox supervisor own sleeping and relaunching bounded cycles.
16
+
- Keep normal gator launches supervised: use `--watch` and let the in-sandbox supervisor own sleeping and relaunching bounded cycles.
17
17
- Do not add passive `sleep` loops in the operator session to watch gator. Check logs or status once, then report the current state or launch a proper watcher outside the model session only when explicitly asked.
18
18
- Do not change the default gator model in `scripts/agents/gator/agent.yaml` for experiments. Use `CODEX_MODEL=...` and, if needed, a temporary `--from` Docker context or `--codex-bin` override.
19
19
- Do not push to contributor branches, approve, merge, post `/ok to test`, or broaden gator scope unless the operator explicitly authorized that action.
@@ -34,7 +34,6 @@ For gator's PR/issue validation policy, load `gator-gate` inside the launched sa
34
34
|`scripts/agents/gator/bin/validate-review-findings`| Enforces the blocker evidence schema and downgrades unsupported hypotheses. |
35
35
|`scripts/agents/gator/prompts/gator.md`| Rendered top-level prompt template baked into the payload. |
"Review and monitor PR #${pr_number} through the gator-gate workflow. Scope this invocation only to PR #${pr_number}."
161
159
```
162
160
163
-
The launcher queries gateway's selected compute driver, builds gator image in matching Docker or Podman image store, stages immutable payload, imports provider profiles, configures provider credentials and refresh, creates and uploads sandbox payload, then starts agent supervisor with `sandbox exec`. It writes a background log under `scripts/agents/gator/logs/`. `CONTAINER_ENGINE`, when set, must match gateway driver.
161
+
The launcher queries the gateway's selected compute driver, builds the gator image in the matching Docker or Podman image store, stages the immutable payload, imports provider profiles, configures provider credentials and refresh, and starts the agent supervisor as the sandbox's canonical main process. The detached main process survives loss of the host CLI connection and reconnects to a restarted gateway. Unless `--keep` is set, the sandbox is marked ephemeral so the gateway deletes it after the supervisor exits. `CONTAINER_ENGINE`, when set, must match the gateway driver.
162
+
163
+
The launcher streams image-build and provisioning output until the detached workload is ready, then exits. Use `openshell logs <sandbox-name>` or the TUI for runtime output.
"Review and monitor PR #${pr_number} with linked issue #${issue_number} through the gator-gate workflow. Scope this invocation only to PR #${pr_number} and issue #${issue_number}."
"Review and monitor PR #${pr_number} through the gator-gate workflow. Scope this invocation only to PR #${pr_number}. The operator explicitly authorizes applying the test:e2e label, posting /ok to test for the current head SHA, and rerunning the relevant current-head workflow when the E2E Label Help bot says that is required."
224
221
```
225
222
@@ -241,7 +238,6 @@ CODEX_MODEL=gpt-5.6-sol \
241
238
--gateway "$gateway_name" \
242
239
--name "$sandbox_name" \
243
240
--watch \
244
-
--background \
245
241
"Review and monitor PR #${pr_number} through the gator-gate workflow. Scope this invocation only to PR #${pr_number}. This launch is intentionally testing Codex model gpt-5.6-sol via the CLI launcher."
246
242
```
247
243
@@ -266,27 +262,22 @@ CODEX_MODEL=gpt-5.6-sol \
266
262
--name "$sandbox_name" \
267
263
--from "$tmp_context" \
268
264
--watch \
269
-
--background \
270
265
"Review and monitor PR #${pr_number} through the gator-gate workflow. Scope this invocation only to PR #${pr_number}."
271
266
```
272
267
273
268
## Monitoring
274
269
275
270
### Read The Launch Result
276
271
277
-
The launcher prints the log path when `--background` is used:
278
-
279
-
```text
280
-
Started in background. Log: scripts/agents/gator/logs/<sandbox-name>.log
281
-
```
282
-
283
-
Read that file directly. Important markers:
272
+
The launcher streams image-build and provisioning output to the terminal. Important markers:
284
273
285
274
-`Built image ...` means the local image build completed.
286
275
-`Created sandbox: <name>` means OpenShell accepted the sandbox.
287
276
-`openshell-agent: starting watch cycle` means the in-sandbox supervisor began a bounded cycle.
288
277
-`OpenAI Codex v...` plus `model: ...` confirms the Codex CLI and model actually used.
289
278
-`OPENSHELL_AGENT_RESULT {...}` is the bounded-cycle sentinel. In watch mode, the supervisor sleeps and relaunches after this line.
279
+
-`/sandbox/.openshell-agent/status.json` is the atomic current state snapshot. Its `result.notes` field is Gator's plain-language diagnosis and next action for that cycle.
280
+
-`/sandbox/.openshell-agent/history.jsonl` contains the latest 100 supervisor transitions, including active-cycle starts and completed cycle results.
290
281
-`openshell-agent: still running watch cycle ...` is a heartbeat during long active model cycles.
291
282
-`review_feedback_lookup_failed` means Gator could not build the required cross-SHA feedback ledger and deliberately skipped a context-free review.
292
283
@@ -314,6 +305,11 @@ If `sandbox get` is not supported by the local CLI shape, use `openshell sandbox
314
305
|`status=terminal_failure`| Unrecoverable or stale immutable payload. | Inspect the reason; rebuild/relaunch for `stale_gator_payload`. |
315
306
|`status=complete`| Target closed, merged, or one-shot complete. | Delete sandbox if no longer needed. |
316
307
308
+
Prefer the state snapshot over scraping transient `/tmp` cycle output. Use the
309
+
history file to tell whether a failure is repeating or whether the supervisor
310
+
has begun a fresh cycle. Runtime logs remain useful for full command output and
311
+
transport diagnostics.
312
+
317
313
## Restarting A Gator
318
314
319
315
Restart when the payload must change, the sandbox is wedged without a sentinel, the model/tooling version changed, or a transient failure repeats past the useful retry point.
Copy file name to clipboardExpand all lines: .agents/skills/sbom/SKILL.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -15,7 +15,7 @@ The OpenShell SBOM tooling produces source-tree CycloneDX JSON SBOMs using Syft,
15
15
16
16
SBOMs are **release artifacts only** -- they are generated on demand and not committed to the repository. Output lands in `deploy/sbom/output/` (gitignored).
17
17
18
-
Pushed gateway and supervisor images carry an SPDX SBOM and minimal SLSA provenance as OCI attestations. Branch E2E, Release Dev, and Release Tag image binaries embed cargo-auditable metadata, so their image SBOMs include linked Rust crates.
18
+
Pushed gateway, sandbox, and supervisor images carry an SPDX SBOM and minimal SLSA provenance as OCI attestations. Branch E2E, Release Dev, and Release Tag image binaries embed cargo-auditable metadata, so their image SBOMs include linked Rust crates.
0 commit comments