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 c903fe6
Browse filesBrowse the repository at this point in the historyBrowse files
The shared bearer token is appropriate for this small trusted v1 deployment. The protocol deliberately leaves room for later per-worker credentials or mTLS, but neither is part of this version. The worker never logs the token.
43
43
44
-
Use [`.env.example`](.env.example) for all timeout, Dappmanager, cleanup, and optional Nexus settings. `MCP_TIMEOUT_MS` bounds read-only Dappmanager calls at 30 seconds by default, while `MCP_MUTATION_TIMEOUT_MS` gives each install, update, or removal attempt 30 minutes by default (up to one hour). Transient transport and package-download failures are retried three times with bounded exponential backoff; tune this with `MCP_MUTATION_ATTEMPTS` and `MCP_MUTATION_RETRY_DELAY_MS`. `NEXUS_TIMEOUT_MS` gives advisory Nexus analysis five minutes by default. `RETAIN_BASELINE_PACKAGES` is a comma-separated allowlist for packages with expensive downloads: after the first successful baseline install, the harness records its expected version and immutable release reference, restores it after candidate testing, and reuses it on later runs instead of removing and downloading it again. `TROPIBOT_TIMEOUT_MS` bounds each coordinator request. The Dappmanager MCP token and Nexus key remain local and are never sent to Tropibot or persisted in a job record.
44
+
Use [`.env.example`](.env.example) for all timeout, Dappmanager, cleanup, and optional Nexus settings. `MCP_TIMEOUT_MS` bounds read-only Dappmanager calls at 30 seconds by default, while `MCP_MUTATION_TIMEOUT_MS` gives each install, update, or removal attempt 30 minutes by default (up to one hour). Transient transport and package-download failures are retried three times with bounded exponential backoff; tune this with `MCP_MUTATION_ATTEMPTS` and `MCP_MUTATION_RETRY_DELAY_MS`. `NEXUS_TIMEOUT_MS` gives advisory Nexus analysis five minutes by default. If the target package was installed before a run, cleanup restores the exact baseline resolved for that run; otherwise cleanup removes the target. The pre-run package version never replaces the requested baseline. `TROPIBOT_TIMEOUT_MS` bounds each coordinator request. The Dappmanager MCP token and Nexus key remain local and are never sent to Tropibot or persisted in a job record.
Copy file name to clipboardExpand all lines: docs/architecture.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -20,11 +20,11 @@ Planned restart control is an in-process `accepting → draining → drained` st
20
20
21
21
`RunRecord.worker` holds the opaque claim token, mutation/cleanup flag, final worker error when no normal result exists, exact pending completion JSON, acknowledgement status, and a manual-recovery reason. The atomic file store writes a temporary file in `/data` and persists it atomically. Only one unacknowledged claimed record is allowed to proceed. Pending completion bytes take precedence over legacy delivery-related recovery markers during restart. Compatibility rejections retry automatically with capped backoff, and an acknowledgement clears any stale marker.
22
22
23
-
On startup the worker finds an unresolved record before it polls. It retries a pending completion first. If an active job might have changed Dappmanager, it checks the target, refuses the harness and core packages, and executes the persisted recovery plan: restore the exact pre-test or intentionally retained baseline, or remove a target that was absent before the run. It verifies the final inventory, then sends an `interrupted` worker error. It never reruns the interrupted test. Successfully reconciled claim loss releases the obsolete local claim and lets Tropibot decide whether another claim is allowed. Cleanup and completion-conflict holds keep the worker task alive but not ready. `POST /operator/recovery/continue` remains the compatible cleanup-only endpoint; the dashboard uses `POST /operator/recovery/action` to record verified cleanup, retry exact persisted completion bytes, or explicitly accept the coordinator's existing result and release local delivery state. Every action is scoped to an exact run, and conflict release is rejected until cleanup is confirmed. The claim loop also remains paused, rather than exiting, when Tropibot reports an unresolved lost job. The UI separately proxies Tropibot's worker-authenticated lost-job lookup and exact-job ready command through `GET /api/coordinator/lost-job` and `POST /operator/coordinator/ready`; the browser never receives the coordinator token. The latter always injects `cleanupConfirmed: true`, lets the operator choose whether Tropibot should requeue the package, and wakes polling only after Tropibot accepts the recovery. Ordinary delivery compatibility failures self-heal when Tropibot becomes compatible.
23
+
On startup the worker finds an unresolved record before it polls. It retries a pending completion first. If an active job might have changed Dappmanager, it checks the target, refuses the harness and core packages, and executes the persisted recovery plan: restore the exact test baseline when the target existed before the run, or remove a target that was absent before the run. It verifies the final inventory, then sends an `interrupted` worker error. It never reruns the interrupted test. Successfully reconciled claim loss releases the obsolete local claim and lets Tropibot decide whether another claim is allowed. Cleanup and completion-conflict holds keep the worker task alive but not ready. `POST /operator/recovery/continue` remains the compatible cleanup-only endpoint; the dashboard uses `POST /operator/recovery/action` to record verified cleanup, retry exact persisted completion bytes, or explicitly accept the coordinator's existing result and release local delivery state. Every action is scoped to an exact run, and conflict release is rejected until cleanup is confirmed. The claim loop also remains paused, rather than exiting, when Tropibot reports an unresolved lost job. The UI separately proxies Tropibot's worker-authenticated lost-job lookup and exact-job ready command through `GET /api/coordinator/lost-job` and `POST /operator/coordinator/ready`; the browser never receives the coordinator token. The latter always injects `cleanupConfirmed: true`, lets the operator choose whether Tropibot should requeue the package, and wakes polling only after Tropibot accepts the recovery. Ordinary delivery compatibility failures self-heal when Tropibot becomes compatible.
24
24
25
-
The controller’s baseline and candidate paths share stabilization and capture. It always resolves the requested baseline first; an omitted `baselineRef` means the latest published release and never means “whatever is installed.” An existing target is reused only when its observed version matches the resolved baseline. Outside the retained-baseline allowlist, an original installed version remains the restoration target. For retained packages, the resolved published baseline becomes the restoration target so an unpublished candidate left on the node cannot be mistaken for a baseline. Stabilization requires a non-empty, all-running container list with the same sorted names across consecutive samples. Failed detail calls, empty lists, non-running states, and container-set changes reset the streak. Evidence history, log collection, redaction, and analysis input are bounded.
25
+
The controller’s baseline and candidate paths share stabilization and capture. It always resolves the requested baseline first; an omitted `baselineRef` means the latest published release and never means “whatever is installed.” An existing target is reused only when its observed version matches the resolved baseline, and cleanup restores that resolved baseline after candidate testing regardless of the pre-run version. If the target was absent before the run, cleanup removes it. Stabilization requires a non-empty, all-running container list with the same sorted names across consecutive samples. Failed detail calls, empty lists, non-running states, and container-set changes reset the streak. Evidence history, log collection, redaction, and analysis input are bounded.
26
26
27
-
The Dappmanager adapter uses separate read and mutation timeouts. Install, update, and removal calls retry only failures classified as transient transport or package-download errors, with bounded exponential backoff. Before reissuing a timed-out operation, it reconciles observable state so an installed package, reached version, or completed removal is accepted without a duplicate mutation. Authentication, validation, required-setup, and malformed-response failures are terminal. Packages in `RETAIN_BASELINE_PACKAGES` receive an exact restore plan for the resolved published baseline; that makes expensive baselines reusable across jobs and replaces any stale unpublished candidate left by an interrupted run. Cleanup verifies the final package inventory; failed verification or unexpected packages introduced by the run make cleanup fail rather than producing a clean result.
27
+
The Dappmanager adapter uses separate read and mutation timeouts. Install, update, and removal calls retry only failures classified as transient transport or package-download errors, with bounded exponential backoff. Before reissuing a timed-out operation, it reconciles observable state so an installed package, reached version, or completed removal is accepted without a duplicate mutation. Authentication, validation, required-setup, and malformed-response failures are terminal. The baseline preview alone determines the version used for testing and recovery; the pre-run installed version is ignored. Cleanup verifies the final package inventory; failed verification or unexpected packages introduced by the run make cleanup fail rather than producing a clean result.
28
28
29
29
Nexus receives only a single redacted, bounded request with no tools or conversation history. Its typed result is advisory; a failure falls back to the heuristic analyzer and no Nexus result can turn a deterministic failure into a pass.
0 commit comments