CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-15 09:25:28 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: sync every doc surface with the v1.63 release

Browse Source 
/document-release audit (4-lane, all claims verified against branch code):

- README: gstack-egress + gstack-context-bill rows in the standalone-binaries
  table; Privacy & Telemetry gains the receipted-egress bullet (attempted-
  egress framing per the shipped threat model).
- ARCHITECTURE: /health is liveness-only, POST /extension-token endpoint row
  + bootstrap mechanics paragraph; new Egress receipt ledger subsection under
  Security model; eval persistence covers the sharded runner, GSTACK_EVAL_DIR,
  and the finalized-run baseline rule.
- CLAUDE.md: sharded test scripts in Commands; sharded semantics in the
  detached-evals section; PTY skill seeding in the hermetic section; egress
  invariant block beside the other server-egress invariants; catalog-budget
  ceiling beside the 160KB token ceiling; project-tree entries for
  lib/egress-receipt.ts, lib/context-bill.ts, scripts/test-paid-shards.ts.
- CONTRIBUTING: seedSkills + live-tree seeding in the hermetic paragraph;
  sharded runner in detached runs; catalog-budget in the Tier 1 list.
- BROWSER: extension token bootstrap section, tunnel egress receipts section,
  identity-pin migration note in manual install.
- REMOTE_BROWSER_ACCESS: tunnel-start receipt bullet in the security model.
- gbrain docs: /sync-gbrain + brain-sync egress-receipt behavior documented;
  dead consumer-token instructions removed (consumer machinery deleted this
  release); new fail-closed refusal added to the error catalog.
- CHANGELOG: measured-vs-ceiling catalog numbers, contributor notes for the
  external-service tier move and the PTY single-line AskUserQuestion parser,
  release date.
- TODOS: /health token-distribution TODO resolved by this release, removed;
  port-wave follow-up sections re-labeled to the shipped version.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-08-13 18:28:36 -07:00
co-authored by Claude Fable 5
parent 562273d793
commit e7110aac93
11 changed files with 169 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -1
View File
@@ -235,7 +235,7 @@ Each skill feeds into the next. `/office-hours` writes a design doc that `/plan-
| `/ios-qa` | **iOS Live-Device QA (v1.43.0.0+)** — drive a real iPhone over USB CoreDevice via an embedded `StateServer` in the app. Read Swift source, codegen typed `@Observable` accessors, run the agent loop. Optional `--tailnet` flag exposes the device to OpenClaw or any HTTP-capable agent on your Tailscale tailnet so remote agents can run iOS QA without ever touching the hardware. Capability-tier allowlist (observe/interact/mutate/restore), per-device session lock, audit log. |
| `/ios-fix`, `/ios-design-review`, `/ios-clean`, `/ios-sync` | iOS bug-fix loop, designer's-eye HIG audit, debug-bridge cleanup, and accessor resync. See `docs/skills.md`. End-to-end walkthrough: [docs/howto-ios-testing-with-gstack.md](docs/howto-ios-testing-with-gstack.md). |
### New binaries (v0.19)
### Standalone binaries
Beyond the slash-command skills, gstack ships standalone CLIs for workflows that don't belong inside a session:
@@ -243,6 +243,8 @@ Beyond the slash-command skills, gstack ships standalone CLIs for workflows that
|---------|-------------|
| `gstack-model-benchmark` | **Cross-model benchmark** — run the same prompt through Claude, GPT (via Codex CLI), and Gemini; compare latency, tokens, cost, and (optionally) LLM-judge quality score. Auth detected per provider, unavailable providers skip cleanly. Output as table, JSON, or markdown. `--dry-run` validates flags + auth without spending API calls. |
| `gstack-taste-update` | **Design taste learning** — writes approvals and rejections from `/design-shotgun` into a persistent per-project taste profile. Decays 5%/week. Feeds back into future variant generation so the system learns what you actually pick. |
| `gstack-egress` | **Egress receipt auditor** — every gstack-initiated off-machine send writes a tamper-evident, hash-chained receipt to `~/.gstack/security/egress.jsonl` before the send. `list` shows what gstack attempted to send and to which host, `grants` shows every consent grant in force plus the exact command that revokes it, `verify` recomputes the hash chain and exits 3 on tamper. |
| `gstack-context-bill` | **Token bill-of-materials** — read-only, offline audit of what an installed skills tree costs in tokens: always-on frontmatter every session pays vs per-invocation SKILL.md + forced references. `--diff` compares two trees, `--budget` enforces a ceiling, `--exact` opts into Anthropic `count_tokens` (sends file text off-machine; writes an egress receipt first, degrades to the offline estimate if the receipt can't be written). |
| `gstack-ios-qa-daemon` | **iOS QA daemon** — Mac-side broker between an agent and a connected iPhone over USB CoreDevice. Loopback by default; `--tailnet` opens a Tailscale-facing listener with identity-gated capability tiers. Single-instance via flock on `~/.gstack/ios-qa-daemon.pid`. See [docs/howto-ios-testing-with-gstack.md](docs/howto-ios-testing-with-gstack.md). |
| `gstack-ios-qa-mint` | **iOS allowlist manager** — owner-grant CLI for the tailnet allowlist. `grant`/`revoke`/`list` against `~/.gstack/ios-qa-allowlist.json` (mode 0600). Remote agents never auto-allowlist; this is the explicit-intent path. |
| `gstack-ios-qa-regen` | **iOS bridge regenerator** — deterministically installs the canonical DebugBridge package, generates typed state accessors, and records the installed gstack version. Safe to rerun after source changes or upgrades. |
@@ -450,6 +452,7 @@ gstack includes **opt-in** usage telemetry to help improve the project. Here's e
- **What's sent (if you opt in):** skill name, duration, success/fail, gstack version, OS. That's it.
- **What's never sent:** code, file paths, repo names, branch names, prompts, or any user-generated content.
- **Change anytime:** `gstack-config set telemetry off` disables everything instantly.
- **Every off-machine send is receipted.** Any gstack-initiated network send — telemetry included — writes a hash-chained, tamper-evident receipt to `~/.gstack/security/egress.jsonl` before the send. Audit with `gstack-egress list`, verify the chain with `gstack-egress verify` (exit 3 on tamper), see every consent in force with `gstack-egress grants`. The ledger records attempted sends so accidents are auditable — it's an audit trail, not a network firewall.
Data is stored in [Supabase](https://supabase.com) (open source Firebase alternative). The schema is in [`supabase/migrations/`](supabase/migrations/) — you can verify exactly what's collected. The Supabase publishable key in the repo is a public key (like a Firebase API key) — row-level security policies deny all direct access. Telemetry flows through validated edge functions that enforce schema checks, event type allowlists, and field length limits.