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 6154686
Browse filesBrowse the repository at this point in the historyBrowse files
fix(settings): stop a resolved default being writable; sync roadmap/spec/docs
A 5-lens audit of the branch produced 14 confirmed findings (9 more were
refuted and dropped). This lands the ones that belong in this PR; the four
live-verification findings that are pre-existing and unrelated are filed as
issues #1083 and #1084 rather than widened into this change.
THE REAL BUG — a resolved default WAS writable, which falsifies the claim
this PR made:
SettingsSection keeps a component-local `dirty` ref, and dirtyKeys is the
UNION of that ref and the working/original comparison. Nothing keyed the
section, so Reload replaced both snapshots while leaving the ref populated:
pick Compact -> Reload -> Save PATCHed `tool_response_mode: "full"` into a
config that never had the key. Every section is now keyed on a form epoch
bumped per hydration, so it remounts with an empty ref. Verified live: after
Reload the abandoned edit is gone, Save is disabled, and the key is still
absent from the config file on disk.
This also fixes the general case — the stale ref could strand ANY field.
TESTS THAT COULD NOT FAIL. Cross-model review caught the vacuous
"both copies normalized" assertion in the tray test; the same audit found I
had left the identical tautology in the Web UI twin, plus a Raw-tab test that
matched source text and so could not see whether `cfg` was still the untouched
response by the time it was serialized. Both are now real assertions against
an extracted `hydrateConfigState` helper (the Vue counterpart of the Swift
`hydrate(from:)` seam). Mutation-checked in both directions: normalizing one
snapshot fails them, and stripping the section keys fails the regression test.
SYNC:
- roadmap.yaml: the schema-deferred epic still said `in_progress` with a note
ending "plan in progress" — spec 102 shipped in #1063. Now `done` with a
`pr:` ref, and the note's "~88% smaller listing" projection is corrected with
the measured 29.7%/34.8% and the 38.9% ceiling. ROADMAP.md is GENERATED, so
the edit is in the YAML and the file regenerated via scripts/gen-roadmap.py.
- spec.md/plan.md asserted SC-001's >=70% as fact in four more places, and
plan.md claimed "Backend-only; no frontend, tray, or Swift changes" plus
"no tray state" — both contradicted by the UI work. SC-001 is now marked
NOT MET with the measurement, the ceiling, and the two options open to the
maintainer. tasks.md was already honest; only two drift notes corrected
(T083 said four new goldens, git shows three; T073 named the wrong file).
- docs: "routing_mode sits directly above it" was wrong — tool_response_mode
is between them. The settings-page restart list named `data_dir`, which is
not a field at all, and omitted routing_mode.
classDef todo fill:#6e7781,stroke:#3d4248,color:#ffffff;
70
-
class sandbox_isolation,scanner_v2,scanner_simplification done;
71
-
class analytics_dashboard,schema_deferred,telemetry_identity,telemetry_v7_churn in_progress;
70
+
class sandbox_isolation,scanner_v2,scanner_simplification,schema_deferred done;
71
+
class analytics_dashboard,telemetry_identity,telemetry_v7_churn in_progress;
72
72
class tpa_db in_review;
73
73
class ux_audit,action_log_transparency,remote_access_tunnel,token_bench,tool_graph,discovery_eval_harness todo;
74
74
```
@@ -154,15 +154,6 @@ graph LR
154
154
155
155
</details>
156
156
157
-
<details>
158
-
<summary>🔵 Deferred-schema serialization for the direct tools/list surface (spec 102) — In progress · P1</summary>
159
-
160
-
> Direct mode enumerates every upstream tool but always ships full inputSchema (~30K tokens for a 100-tool fleet; Spec 083 profiling put ~77% of the payload in schemas agents rarely read). Deferred serialization keeps every tool name, description and annotation and appends the Spec 085 compact signature instead of the schema (~88% smaller listing), with describe_tool on the direct surface to recover it and the shipped pre-dispatch validation turning a wrong guess into one self-healing retry. Not a new routing_mode — a serialization mode of the direct surface, on the same tool_response_mode axis that already governs retrieve_tools. Spec merged in #1035 (issue #971, maintainer-accepted direction); plan in progress.
<summary>🔵 Telemetry identity & data quality (machine_id + CI-filter hardening) — In progress · P1</summary>
168
159
@@ -711,6 +702,15 @@ graph LR
711
702
712
703
</details>
713
704
705
+
<details>
706
+
<summary>🟢 Deferred-schema serialization for the direct tools/list surface (spec 102) — Done · P1</summary>
707
+
708
+
> Direct mode enumerates every upstream tool but always ships full inputSchema (~30K tokens for a 100-tool fleet; Spec 083 profiling put ~77% of the payload in schemas agents rarely read). Deferred serialization keeps every tool name, description and annotation and appends the Spec 085 compact signature instead of the schema (~88% smaller listing), with describe_tool on the direct surface to recover it and the shipped pre-dispatch validation turning a wrong guess into one self-healing retry. Not a new routing_mode — a serialization mode of the direct surface, on the same tool_response_mode axis that already governs retrieve_tools. Spec merged in #1035 (issue #971, maintainer-accepted direction). COMPLETE: all 89 tasks shipped in #1063; the settings UI for both serialization axes followed in #1082. MEASURED SAVINGS FELL WELL SHORT OF THE ~88% PROJECTION ABOVE: 29.7% on the frozen reference corpus and 34.8% on a 527-tool snapshot, against SC-001's >=70% target, with 38.9% the arithmetic ceiling even if both the schema and the signature were deleted. The projection assumed schemas dominate the payload; names, descriptions and annotations turn out to carry most of it. SC-001 is knowingly unmet and awaits a maintainer decision (restate per corpus shape, or re-target at a schema-heavy corpus) — see specs/102-schema-deferred/tasks.md T035a.
<summary>🟢 Tray↔core decoupling: socket/REST API only, no config-file reads — Done · P2</summary>
716
716
@@ -740,7 +740,6 @@ graph LR
740
740
| --- | --- | --- | --- | --- | --- |
741
741
| Release qualification gate (auto-QA matrix blocks the tag) | In progress | P0 | — |[081-release-qa-gate](./specs/081-release-qa-gate/)||
742
742
| Analytics dashboard as default page | In progress | P1 | 25/26 (96%) |[069-observability-usage-graphs](./specs/069-observability-usage-graphs/)||
743
-
| Deferred-schema serialization for the direct tools/list surface (spec 102) | In progress | P1 | 89/89 (100%) |[102-schema-deferred](./specs/102-schema-deferred/)||
744
743
| Telemetry identity & data quality (machine_id + CI-filter hardening) | In progress | P1 | — |||
0 commit comments