mirror of
https://github.com/Finesssee/ProxyPilot.git
synced 2026-11-20 20:34:36 +00:00
chore: record terminal operator scrutiny rerun
This commit is contained in:
+21
@@ -0,0 +1,21 @@
|
||||
{
|
||||
"featureId": "fix-runtime-account-count-semantics",
|
||||
"reviewedAt": "2026-04-05T11:36:06.651055Z",
|
||||
"commitId": "91fe6562",
|
||||
"transcriptSkeletonReviewed": true,
|
||||
"diffReviewed": true,
|
||||
"status": "pass",
|
||||
"codeReview": {
|
||||
"summary": "Reviewed the original runtime-stats feature (`1b3542d7`), the prior scrutiny finding, and the fix commit (`91fe6562`). The fix resolves the remaining non-blocking truthfulness issue: `/v0/runtime/stats.account_count` now counts only runtime-usable Codex accounts, mixed-provider and blank-key entries no longer inflate that value, and the TUI wording matches the runtime semantics.",
|
||||
"issues": []
|
||||
},
|
||||
"sharedStateObservations": [
|
||||
{
|
||||
"area": "skills",
|
||||
"observation": "The worker skipped the rust-operator-worker skill's required manual `tuistory` verification even though the feature touched TUI-visible runtime wording. For this fix the unit-level wording assertion was likely sufficient, but the skill currently leaves that lightweight label-only case undocumented.",
|
||||
"evidence": "Skill procedure step 6 requires manual verification with `tuistory` when the feature affects the TUI or runtime observability surface (`/home/fsos/code-lean/ai-tools/ProxyPilot/.factory/skills/rust-operator-worker/SKILL.md`). The handoff for session `38bb865f-5bfd-4b20-8a75-281170e69c06` records `followedProcedure: false` and says manual TUI verification was skipped in favor of unit tests because the change was only label alignment."
|
||||
}
|
||||
],
|
||||
"addressesFailureFrom": "/home/fsos/code-lean/ai-tools/ProxyPilot/.factory/validation/terminal-operator-console/scrutiny/reviews/proxy-runtime-stats-surface.json",
|
||||
"summary": "Pass. The follow-up fix closes the prior `account_count` truthfulness gap and I found no new code issues in the scoped change."
|
||||
}
|
||||
+28
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"featureId": "fix-tui-footer-and-passive-polling",
|
||||
"reviewedAt": "2026-04-05T11:36:55Z",
|
||||
"commitId": "67c79b9dc5755305448c33df5cb1d761f150bece",
|
||||
"transcriptSkeletonReviewed": true,
|
||||
"diffReviewed": true,
|
||||
"status": "fail",
|
||||
"codeReview": {
|
||||
"summary": "Reviewed the fix commit together with both prior failed reviews (`terminal-tui-operator-console` and `cli-state-runtime-truthfulness-and-docs`). The passive-polling blocker is resolved: idle polling now stays on `/healthz` + `/v0/runtime/stats`, and the new regression test proves it no longer calls `/v1/models`. However, the footer visibility blocker is only partially fixed: the panel now fits the four nominal footer lines, but realistic long feedback still wraps and pushes the help text back out of view.",
|
||||
"issues": [
|
||||
{
|
||||
"file": "rust/proxypilot-rs/src/tui.rs",
|
||||
"line": 396,
|
||||
"severity": "blocking",
|
||||
"description": "The footer still has a fixed height of `Constraint::Length(6)`, which leaves only four inner text rows once the bordered `Keys` block is rendered (`tui.rs:530-543`). That is enough only when the feedback line stays on a single row. But routine operator messages in this same file are much longer\u2014for example the `runtime_refresh_target` failure text at `tui.rs:701-708` is 131 characters before account-name variation, so in the worker's own 120-column verification geometry it wraps to two rows. When that happens, one of the status/help lines is clipped again, so the feature does not fully satisfy the prior blocker of keeping all footer/help guidance visible. The added snapshot test (`tui.rs:943-975`) only exercises a short `Feedback line`, so it misses this realistic wrapped-feedback path."
|
||||
}
|
||||
]
|
||||
},
|
||||
"sharedStateObservations": [
|
||||
{
|
||||
"area": "skills",
|
||||
"observation": "The shared Rust operator-worker guidance still does not tell workers to exercise long, wrapped operator feedback when validating fixed-height TUI regions. That omission helped this fix reintroduce a footer-visibility edge case even though the worker followed the documented procedure and added a snapshot test.",
|
||||
"evidence": "`rust-operator-worker` step 6/7 asks for manual TUI verification and truthful operator-visible wording review, but it does not call out wrap/line-budget checks for fixed-height panels (`/home/fsos/code-lean/ai-tools/ProxyPilot/.factory/skills/rust-operator-worker/SKILL.md`). In this fix, the new regression test in `rust/proxypilot-rs/src/tui.rs:943-975` only uses a one-line `Feedback line`, while the production footer can render much longer routine messages such as `runtime_refresh_target` at `tui.rs:701-708`."
|
||||
}
|
||||
],
|
||||
"addressesFailureFrom": "/home/fsos/code-lean/ai-tools/ProxyPilot/.factory/validation/terminal-operator-console/scrutiny/reviews/terminal-tui-operator-console.json; /home/fsos/code-lean/ai-tools/ProxyPilot/.factory/validation/terminal-operator-console/scrutiny/reviews/cli-state-runtime-truthfulness-and-docs.json",
|
||||
"summary": "Fail. The fix successfully stops passive idle polling from contaminating runtime telemetry, but the footer/help blocker is not fully resolved because long, routine feedback messages can still wrap and hide guidance in the fixed-height footer."
|
||||
}
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"milestone": "terminal-operator-console",
|
||||
"round": 1,
|
||||
"round": 2,
|
||||
"status": "fail",
|
||||
"validatorsRun": {
|
||||
"format": {
|
||||
@@ -25,70 +25,36 @@
|
||||
}
|
||||
},
|
||||
"reviewsSummary": {
|
||||
"total": 6,
|
||||
"passed": 4,
|
||||
"failed": 2,
|
||||
"total": 2,
|
||||
"passed": 1,
|
||||
"failed": 1,
|
||||
"failedFeatures": [
|
||||
"terminal-tui-operator-console",
|
||||
"cli-state-runtime-truthfulness-and-docs"
|
||||
"fix-tui-footer-and-passive-polling"
|
||||
]
|
||||
},
|
||||
"blockingIssues": [
|
||||
{
|
||||
"featureId": "terminal-tui-operator-console",
|
||||
"featureId": "fix-tui-footer-and-passive-polling",
|
||||
"severity": "blocking",
|
||||
"description": "The TUI footer/help block still uses Constraint::Length(3) while rendering four content lines inside a bordered block, so the selected-account/runtime divergence copy and key help are clipped off-screen. This makes the console fail both the TUI readability contract and the CLI/runtime-truthfulness feature's operator-facing explanation goals."
|
||||
},
|
||||
{
|
||||
"featureId": "terminal-tui-operator-console",
|
||||
"severity": "blocking",
|
||||
"description": "The TUI background polling path still calls GET /v1/models whenever /healthz succeeds, which goes through the proxy and mutates total_proxied_requests, successful_upstream_responses, and potentially last_refresh/auth state. Leaving the console open therefore contaminates the runtime stats it is supposed to observe."
|
||||
}
|
||||
],
|
||||
"nonBlockingIssues": [
|
||||
{
|
||||
"featureId": "proxy-runtime-stats-surface",
|
||||
"severity": "non_blocking",
|
||||
"description": "runtime_stats.account_count currently reports all saved state entries rather than only runtime-usable Codex accounts, so mixed-provider saved state can overstate runtime-usable account count."
|
||||
}
|
||||
],
|
||||
"appliedUpdates": [
|
||||
{
|
||||
"target": "services.yaml",
|
||||
"description": "Added `init`, `typecheck`, and `lint` commands so scrutiny/user-testing workers can bootstrap the Rust slice and run the full validator suite from shared service metadata.",
|
||||
"sourceFeature": "scrutiny-validator-terminal-operator-console"
|
||||
},
|
||||
{
|
||||
"target": "library",
|
||||
"description": "Documented in `.factory/library/environment.md` that `./.factory/init.sh` fetches Rust dependencies and creates `rust/proxypilot-rs.toml` when missing before smoke validation.",
|
||||
"sourceFeature": "shared-auth-runtime-domain"
|
||||
"description": "The TUI footer still has a fixed six-row outer height, which leaves only four inner text rows inside the bordered keys block. Long routine feedback such as the runtime-active-account failure copy wraps at the validated terminal width, so one of the footer status/help lines becomes clipped again and the operator console still fails the footer-visibility contract."
|
||||
}
|
||||
],
|
||||
"nonBlockingIssues": [],
|
||||
"appliedUpdates": [],
|
||||
"suggestedGuidanceUpdates": [
|
||||
{
|
||||
"target": "rust-operator-worker",
|
||||
"suggestion": "Clarify that mission artifacts may live under `/home/fsos/.factory/missions/<id>` even when repo-relative `.factory/missions/...` paths are absent, and instruct workers to fall back to the absolute mission directory before treating missing files as blockers.",
|
||||
"evidence": "Review reports for `shared-auth-runtime-domain` and `fix-tui-runtime-truthfulness` both recorded ENOENT attempts against repo-relative mission paths before successfully reading `/home/fsos/.factory/missions/7e6968f8-b3d3-4772-9518-ca3a93ea1374/...`.",
|
||||
"suggestion": "When validating fixed-height TUI regions, explicitly exercise long wrapped operator feedback (not just short placeholder strings) so layout-fit checks prove realistic messages remain visible.",
|
||||
"evidence": "The follow-up review for `fix-tui-footer-and-passive-polling` found the new snapshot test only covered a short `Feedback line`, while real footer messages in `rust/proxypilot-rs/src/tui.rs` are long enough to wrap and clip help text again within the fixed six-row footer.",
|
||||
"isSystemic": true
|
||||
},
|
||||
{
|
||||
"target": "rust-operator-worker",
|
||||
"suggestion": "For TUI features that change visible copy or layout, require a layout-fit visibility check (render/snapshot or terminal smoke) in addition to helper-string assertions so multi-line regions are proven visible.",
|
||||
"evidence": "Both `terminal-tui-operator-console` and `cli-state-runtime-truthfulness-and-docs` failed review because the footer stayed at `Constraint::Length(3)` while rendering four lines, yet the worker tests only asserted helper-string content.",
|
||||
"isSystemic": true
|
||||
},
|
||||
{
|
||||
"target": "rust-operator-worker",
|
||||
"suggestion": "Reinforce the mission boundary that only docs-scoped features may edit `docs/rust-replatform.md` or `README.md`, and direct workers to defer such changes to the explicit docs-alignment feature when possible.",
|
||||
"evidence": "Review reports for `proxy-runtime-stats-surface` and `terminal-tui-operator-console` both recorded edits to `docs/rust-replatform.md` despite mission AGENTS guidance reserving docs changes for docs-alignment work.",
|
||||
"isSystemic": true
|
||||
"suggestion": "Document when label-only TUI/runtime wording changes may use lightweight non-interactive verification instead of full `tuistory` validation, so narrow observability fixes can follow a clear exception path.",
|
||||
"evidence": "The pass review for `fix-runtime-account-count-semantics` noted the worker intentionally skipped manual `tuistory` verification because the change only aligned runtime/TUI labels, but the current skill does not describe that small-change exception.",
|
||||
"isSystemic": false
|
||||
}
|
||||
],
|
||||
"rejectedObservations": [
|
||||
{
|
||||
"observation": "Add a dedicated mock upstream/refresh service definition to `.factory/services.yaml` for runtime smoke validation.",
|
||||
"reason": "ambiguous: the reviewed mock servers were scenario-specific one-off fixtures with ad hoc ports and behavior, so a generic shared service entry would risk encoding the wrong workflow. The concrete bootstrap/config discovery gap was handled instead via additive command/library updates."
|
||||
}
|
||||
],
|
||||
"previousRound": null
|
||||
"rejectedObservations": [],
|
||||
"previousRound": "/home/fsos/code-lean/ai-tools/ProxyPilot/.factory/validation/terminal-operator-console/scrutiny/synthesis.round1.json"
|
||||
}
|
||||
|
||||
@@ -0,0 +1,94 @@
|
||||
{
|
||||
"milestone": "terminal-operator-console",
|
||||
"round": 1,
|
||||
"status": "fail",
|
||||
"validatorsRun": {
|
||||
"format": {
|
||||
"passed": true,
|
||||
"command": "cargo fmt --all --manifest-path rust/Cargo.toml -- --check",
|
||||
"exitCode": 0
|
||||
},
|
||||
"test": {
|
||||
"passed": true,
|
||||
"command": "cargo test --manifest-path rust/Cargo.toml",
|
||||
"exitCode": 0
|
||||
},
|
||||
"typecheck": {
|
||||
"passed": true,
|
||||
"command": "cargo check --manifest-path rust/Cargo.toml",
|
||||
"exitCode": 0
|
||||
},
|
||||
"lint": {
|
||||
"passed": true,
|
||||
"command": "cargo clippy --manifest-path rust/Cargo.toml --all-targets -- -D warnings",
|
||||
"exitCode": 0
|
||||
}
|
||||
},
|
||||
"reviewsSummary": {
|
||||
"total": 6,
|
||||
"passed": 4,
|
||||
"failed": 2,
|
||||
"failedFeatures": [
|
||||
"terminal-tui-operator-console",
|
||||
"cli-state-runtime-truthfulness-and-docs"
|
||||
]
|
||||
},
|
||||
"blockingIssues": [
|
||||
{
|
||||
"featureId": "terminal-tui-operator-console",
|
||||
"severity": "blocking",
|
||||
"description": "The TUI footer/help block still uses Constraint::Length(3) while rendering four content lines inside a bordered block, so the selected-account/runtime divergence copy and key help are clipped off-screen. This makes the console fail both the TUI readability contract and the CLI/runtime-truthfulness feature's operator-facing explanation goals."
|
||||
},
|
||||
{
|
||||
"featureId": "terminal-tui-operator-console",
|
||||
"severity": "blocking",
|
||||
"description": "The TUI background polling path still calls GET /v1/models whenever /healthz succeeds, which goes through the proxy and mutates total_proxied_requests, successful_upstream_responses, and potentially last_refresh/auth state. Leaving the console open therefore contaminates the runtime stats it is supposed to observe."
|
||||
}
|
||||
],
|
||||
"nonBlockingIssues": [
|
||||
{
|
||||
"featureId": "proxy-runtime-stats-surface",
|
||||
"severity": "non_blocking",
|
||||
"description": "runtime_stats.account_count currently reports all saved state entries rather than only runtime-usable Codex accounts, so mixed-provider saved state can overstate runtime-usable account count."
|
||||
}
|
||||
],
|
||||
"appliedUpdates": [
|
||||
{
|
||||
"target": "services.yaml",
|
||||
"description": "Added `init`, `typecheck`, and `lint` commands so scrutiny/user-testing workers can bootstrap the Rust slice and run the full validator suite from shared service metadata.",
|
||||
"sourceFeature": "scrutiny-validator-terminal-operator-console"
|
||||
},
|
||||
{
|
||||
"target": "library",
|
||||
"description": "Documented in `.factory/library/environment.md` that `./.factory/init.sh` fetches Rust dependencies and creates `rust/proxypilot-rs.toml` when missing before smoke validation.",
|
||||
"sourceFeature": "shared-auth-runtime-domain"
|
||||
}
|
||||
],
|
||||
"suggestedGuidanceUpdates": [
|
||||
{
|
||||
"target": "rust-operator-worker",
|
||||
"suggestion": "Clarify that mission artifacts may live under `/home/fsos/.factory/missions/<id>` even when repo-relative `.factory/missions/...` paths are absent, and instruct workers to fall back to the absolute mission directory before treating missing files as blockers.",
|
||||
"evidence": "Review reports for `shared-auth-runtime-domain` and `fix-tui-runtime-truthfulness` both recorded ENOENT attempts against repo-relative mission paths before successfully reading `/home/fsos/.factory/missions/7e6968f8-b3d3-4772-9518-ca3a93ea1374/...`.",
|
||||
"isSystemic": true
|
||||
},
|
||||
{
|
||||
"target": "rust-operator-worker",
|
||||
"suggestion": "For TUI features that change visible copy or layout, require a layout-fit visibility check (render/snapshot or terminal smoke) in addition to helper-string assertions so multi-line regions are proven visible.",
|
||||
"evidence": "Both `terminal-tui-operator-console` and `cli-state-runtime-truthfulness-and-docs` failed review because the footer stayed at `Constraint::Length(3)` while rendering four lines, yet the worker tests only asserted helper-string content.",
|
||||
"isSystemic": true
|
||||
},
|
||||
{
|
||||
"target": "rust-operator-worker",
|
||||
"suggestion": "Reinforce the mission boundary that only docs-scoped features may edit `docs/rust-replatform.md` or `README.md`, and direct workers to defer such changes to the explicit docs-alignment feature when possible.",
|
||||
"evidence": "Review reports for `proxy-runtime-stats-surface` and `terminal-tui-operator-console` both recorded edits to `docs/rust-replatform.md` despite mission AGENTS guidance reserving docs changes for docs-alignment work.",
|
||||
"isSystemic": true
|
||||
}
|
||||
],
|
||||
"rejectedObservations": [
|
||||
{
|
||||
"observation": "Add a dedicated mock upstream/refresh service definition to `.factory/services.yaml` for runtime smoke validation.",
|
||||
"reason": "ambiguous: the reviewed mock servers were scenario-specific one-off fixtures with ad hoc ports and behavior, so a generic shared service entry would risk encoding the wrong workflow. The concrete bootstrap/config discovery gap was handled instead via additive command/library updates."
|
||||
}
|
||||
],
|
||||
"previousRound": null
|
||||
}
|
||||
Reference in New Issue
Block a user