Wire scripts/lib/agent-proximity/ and the #3028 coordination inventory into
the control pane as one read-only live view, ecc.control-plane.view.v1,
shaped as tasks, lanes and events.
- agent-proximity/projection.js: rolling z-score per channel, tails clipped
at the 2.5th and 97.5th percentile, mapped back to [0, 1], static channel
weights, PCA (Jacobi on the 3x3 covariance) over x_tree, x_overlap, x_dep.
Raw mode until the window holds 8 samples. No runtime dependencies.
- agent-proximity/index.js: airspace links now carry the per-channel values.
- agent-proximity/distance.js: rightOfWay(a, b) extracted from advise().
- control-pane/proximity.js: snapshot includes agent summaries (files,
progress, startedAt) so the view can join sessions to working sets.
- control-pane/control-plane-view.js: builds the view from the snapshot;
advisory events derived from every pair link against the view's static
thresholds (ta 0.35, ra 0.7), deterministic ids, steer/hold from
rightOfWay; lease conflicts from the inventory as events; inventory
manifest built from live sessions with sanitized ids, declared-only.
- control-pane/server.js: GET /control-plane (self-contained page with the
2D canvas), GET /api/control-plane, GET /api/control-plane/events; one
projection window per server so z-scores roll across polls.
- docs/control-plane/VIEW-CONTRACT.md: the task/lane/event contract for
reuse by the Ito ops control plane.
- docs/control-plane/TCAS-HOOK.md: design for slice (b), not implemented.
The view does not acquire leases, steer or pause agents, and claims no
conflict-reduction number.
* feat: bundle standalone taste distillation and application workflows
* docs: fix imported taste skill markdown lint
* docs: align Turkish agent catalog with taste skills
* refactor: make ECC the canonical reusable video engine
* fix: preserve video duration when applying image overlays
* fix: preserve background colors in image compositing
* fix: report best-effort duration targets and shortfalls
* feat: ship verified Fusion presets with compatibility provenance
* feat(tasteforge): preserve native edits in application bundles
* feat(tasteforge): compile local preservation without hosted input
* fix: update js-yaml to patched 4.3.2
* test: report bounded Stop wrapper failure diagnostics
* fix(tasteforge): fail closed on unsafe output names, missing overlays and cadence
- cli: default report and spec paths are derived from pack name and profile
genre; require the manifest's name pattern before using either as a
filename part so a traversal string cannot write outside cwd/out.
- apply_local: a pack without cadence.json, or with no measured shots and
no explicit mean_shot, raises instead of silently planning 1.0s shots and
reporting a measured cadence.
- legacy apply: a missing overlay aborts before any paid upload; forge()
would have rejected it after every take was generated.
- requirements-live: pin fal-client>=0.13.0, the first release whose
subscribe() accepts client_timeout.
Addresses the five P1 findings from the independent review of #3033.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015fxHRsydPqEcYngGbqkgt1
---------
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
Keep the contributor's corrected Haiku and Fable/Mythos tiers, update the live Sonnet and Opus rows against the current official pricing contract, and mirror the same numeric changes in the Japanese and Chinese tables.
Keep the duplicate estimator and its tests deleted as landed through #2866, while carrying the contributor's pricing-table correction forward and refreshing the documented live model rows against the current official pricing contract.
Nine command files spell the key with an underscore while six other files in
this repository already use `allowed-tools`. Claude Code reads the hyphenated
form, so the underscored key is unrecognized and the tool pre-approval it is
meant to grant never applies.
The design rationale cited "Opus 4.6+" as the class of models capable of
holistic checklist judgment. That reference predates the Claude 5 families
(Opus 5, Sonnet 5, Fable 5), so readers on current models can't tell whether
the guidance still applies to them.
Widens the parenthetical to name the Claude 5 families explicitly. Applied
across all four locale copies (en, ja-JP, tr, zh-CN) to keep translations in
sync. Documentation wording only; no behavioral change.
Curated skill delegating to the canonical tasteforge package in
Ito-Markets/ito-video: taste interviews, style-pack validation, offline
distillation with measured grounding, deterministic cadence application to
local footage, EDL/FCPXML export, and generated-media provenance audits.
Provider (Fal) generation requires explicit separately authorized execution
and fails closed in ECC; local references never mean a saved provider
workflow. Registered in the opt-in media-generation install module, npm
files, and catalog counts via scripts/ci/catalog.js. Contract tests cover
frontmatter/triggers, the fail-closed boundary, manifest and npm-packed
discoverability (real tarball check opt-in via ECC_TEST_NPM_PACK=1).