restokes92 commited on
Commit
8d8d6ea
·
verified ·
1 Parent(s): 5c7ac60

Refresh Kaiju Coder 7 paid API readiness evidence

Browse files
FINAL_RELEASE_REPORT.md CHANGED
@@ -1,6 +1,6 @@
1
  # Kaiju Coder 7 Final Release Report
2
 
3
- Generated: `2026-06-03T20:41:56Z`
4
 
5
  Product name: `Kaiju Coder 7`
6
  Public model id: `kaiju-coder-7`
@@ -15,9 +15,10 @@ commercial API launch yet. The local model path, OpenCode profile, harnessed
15
  business-owner evals, staged helper repos, runtime-quantized recipe, and paid
16
  API scaffold are in place. The adapter, OpenCode helper, runtime helper, and
17
  merged 53.8GB model are uploaded under `RMDWLLC` with public visibility. The
18
- paid API has human approval, but operational launch still requires live
19
- Cloudflare bindings, secrets, Stripe staging evidence, Worker-to-Gojira proof,
20
- rollback proof, and latency evidence.
 
21
 
22
  ## Runtime
23
 
@@ -41,7 +42,7 @@ stability and speed.
41
  | Hugging Face release readiness | `ready=True pass=23 fail=0 manual=1 rc=0` |
42
  | Public launch readiness | `ready=False pass=23 fail=1 manual=0 rc=1` |
43
  | Hugging Face staging integrity | `ready=True pass=6 fail=0 manual=0 rc=0` |
44
- | Paid API launch readiness | `ready=False pass=21 fail=0 manual=6 rc=1` |
45
 
46
  ## Hugging Face Upload Evidence
47
 
@@ -60,24 +61,21 @@ stability and speed.
60
 
61
  | Status | Check | Detail |
62
  |---|---|---|
63
- | manual | paid API launch preflight | 21 pass, 0 fail, 6 manual |
64
 
65
  ## Public Launch Blockers
66
 
67
  | Status | Check | Detail |
68
  |---|---|---|
69
- | fail | paid API launch preflight | 21 pass, 0 fail, 6 manual |
70
 
71
  ## Paid API Launch Blockers
72
 
73
  | Status | Check | Detail |
74
  |---|---|---|
75
- | manual | public route mode | attach sanitized evidence in /Users/richardecholsai7/Apps/kaiju-coder/release/paid-api-launch-evidence.json key `public_route_mode` |
76
- | manual | wrangler secret list confirms KAIJU_ORIGIN_URL, KAIJU_ORIGIN_SECRET, and KAIJU_STRIPE_WEBHOOK_SECRET | attach sanitized evidence in /Users/richardecholsai7/Apps/kaiju-coder/release/paid-api-launch-evidence.json key `wrangler_secrets_verified` |
77
  | manual | Stripe Checkout top-up products and webhook endpoint tested with metadata.kaiju_api_key_id | attach sanitized evidence in /Users/richardecholsai7/Apps/kaiju-coder/release/paid-api-launch-evidence.json key `stripe_checkout_topup_staging` |
78
- | manual | staging request passed through Worker to Gojira-B origin with model=kaiju-coder-7 | attach sanitized evidence in /Users/richardecholsai7/Apps/kaiju-coder/release/paid-api-launch-evidence.json key `worker_to_gojira_staging_request` |
79
- | manual | rollback command or route switch was exercised and recorded | attach sanitized evidence in /Users/richardecholsai7/Apps/kaiju-coder/release/paid-api-launch-evidence.json key `rollback_exercised` |
80
- | manual | p95 latency for paid routes is recorded after staging traffic | attach sanitized evidence in /Users/richardecholsai7/Apps/kaiju-coder/release/paid-api-launch-evidence.json key `paid_route_latency` |
81
 
82
  ## Evidence Paths
83
 
 
1
  # Kaiju Coder 7 Final Release Report
2
 
3
+ Generated: `2026-06-03T21:00:45Z`
4
 
5
  Product name: `Kaiju Coder 7`
6
  Public model id: `kaiju-coder-7`
 
15
  business-owner evals, staged helper repos, runtime-quantized recipe, and paid
16
  API scaffold are in place. The adapter, OpenCode helper, runtime helper, and
17
  merged 53.8GB model are uploaded under `RMDWLLC` with public visibility. The
18
+ paid API has human approval and a live Worker staging route with Cloudflare
19
+ bindings, Worker-to-Gojira proof, rollback proof, and latency evidence. Public
20
+ charging still requires a custom API domain plus real Stripe webhook and
21
+ Checkout top-up evidence.
22
 
23
  ## Runtime
24
 
 
42
  | Hugging Face release readiness | `ready=True pass=23 fail=0 manual=1 rc=0` |
43
  | Public launch readiness | `ready=False pass=23 fail=1 manual=0 rc=1` |
44
  | Hugging Face staging integrity | `ready=True pass=6 fail=0 manual=0 rc=0` |
45
+ | Paid API launch readiness | `ready=False pass=24 fail=0 manual=3 rc=1` |
46
 
47
  ## Hugging Face Upload Evidence
48
 
 
61
 
62
  | Status | Check | Detail |
63
  |---|---|---|
64
+ | manual | paid API launch preflight | 24 pass, 0 fail, 3 manual |
65
 
66
  ## Public Launch Blockers
67
 
68
  | Status | Check | Detail |
69
  |---|---|---|
70
+ | fail | paid API launch preflight | 24 pass, 0 fail, 3 manual |
71
 
72
  ## Paid API Launch Blockers
73
 
74
  | Status | Check | Detail |
75
  |---|---|---|
76
+ | manual | public route mode | public route evidence must use exposure_mode=custom_domain before paid launch |
77
+ | manual | wrangler secret list confirms KAIJU_ORIGIN_URL, KAIJU_ORIGIN_SECRET, and KAIJU_STRIPE_WEBHOOK_SECRET | secret-name evidence missing: KAIJU_STRIPE_WEBHOOK_SECRET |
78
  | manual | Stripe Checkout top-up products and webhook endpoint tested with metadata.kaiju_api_key_id | attach sanitized evidence in /Users/richardecholsai7/Apps/kaiju-coder/release/paid-api-launch-evidence.json key `stripe_checkout_topup_staging` |
 
 
 
79
 
80
  ## Evidence Paths
81
 
GOAL_COMPLETION_AUDIT.md CHANGED
@@ -1,11 +1,11 @@
1
  # Kaiju Coder 7 Goal Completion Audit
2
 
3
- Generated: `2026-06-03T20:42:32Z`
4
 
5
  Overall: `not complete`
6
  Summary: `17 passed / 1 blocked / 0 manual`
7
 
8
- This audit maps the active Kaiju Coder 7 objective to current evidence. It is stricter than local readiness: local public testing can pass while Hugging Face upload, human review, and paid API launch remain blocked.
9
 
10
  ## Readiness Commands
11
 
@@ -40,12 +40,12 @@ This audit maps the active Kaiju Coder 7 objective to current evidence. It is st
40
  | Quality | Model/harness prompts produce file-oriented business-owner artifacts rather than vague advice. | `passed` | kaiju_harness/business_suite.py; release/EVAL_SCOREBOARD.md | |
41
  | Provenance | Training/eval provenance is preserved and public docs avoid internal checkpoint naming except license/provenance attribution. | `passed` | release/SOURCE_INVENTORY.md; release/DATA_PROVENANCE_DRAFT.md; release/PUBLIC_TESTING_QUICKSTART.md | |
42
  | Paid API | Paid API scaffold covers API keys, Stripe billing, rate limits, logging controls, abuse controls, rollback plan, and pricing assumptions. | `passed` | python3 scripts/check_paid_api_readiness.py --mode scaffold; gateway/cloudflare-worker tests | |
43
- | Paid API | Paid API is ready for public charging. | `blocked` | python3 scripts/check_paid_api_readiness.py --mode launch | Requires Wrangler secret-name evidence, Stripe staging evidence, Worker-to-Gojira staging request, rollback proof, and paid-route latency evidence. |
44
  | Final Report | Final report includes exact commands run, eval results, changed files, remaining risks, and what Richard should test first. | `passed` | release/FINAL_RELEASE_REPORT.md | |
45
 
46
  ## Blocking Items
47
 
48
- - Paid API: Paid API is ready for public charging.: Requires Wrangler secret-name evidence, Stripe staging evidence, Worker-to-Gojira staging request, rollback proof, and paid-route latency evidence.
49
 
50
  ## Commands To Re-run
51
 
 
1
  # Kaiju Coder 7 Goal Completion Audit
2
 
3
+ Generated: `2026-06-03T21:00:45Z`
4
 
5
  Overall: `not complete`
6
  Summary: `17 passed / 1 blocked / 0 manual`
7
 
8
+ This audit maps the active Kaiju Coder 7 objective to current evidence. It is stricter than local readiness: local public testing and Hugging Face release checks can pass while paid API launch remains blocked.
9
 
10
  ## Readiness Commands
11
 
 
40
  | Quality | Model/harness prompts produce file-oriented business-owner artifacts rather than vague advice. | `passed` | kaiju_harness/business_suite.py; release/EVAL_SCOREBOARD.md | |
41
  | Provenance | Training/eval provenance is preserved and public docs avoid internal checkpoint naming except license/provenance attribution. | `passed` | release/SOURCE_INVENTORY.md; release/DATA_PROVENANCE_DRAFT.md; release/PUBLIC_TESTING_QUICKSTART.md | |
42
  | Paid API | Paid API scaffold covers API keys, Stripe billing, rate limits, logging controls, abuse controls, rollback plan, and pricing assumptions. | `passed` | python3 scripts/check_paid_api_readiness.py --mode scaffold; gateway/cloudflare-worker tests | |
43
+ | Paid API | Paid API is ready for public charging. | `blocked` | python3 scripts/check_paid_api_readiness.py --mode launch | Requires a custom API domain, KAIJU_STRIPE_WEBHOOK_SECRET, and real Stripe Checkout top-up staging evidence. |
44
  | Final Report | Final report includes exact commands run, eval results, changed files, remaining risks, and what Richard should test first. | `passed` | release/FINAL_RELEASE_REPORT.md | |
45
 
46
  ## Blocking Items
47
 
48
+ - Paid API: Paid API is ready for public charging.: Requires a custom API domain, KAIJU_STRIPE_WEBHOOK_SECRET, and real Stripe Checkout top-up staging evidence.
49
 
50
  ## Commands To Re-run
51
 
PAID_API_READINESS.md CHANGED
@@ -64,15 +64,45 @@ Live Cloudflare resources were created on 2026-06-03 after Wrangler login:
64
  - R2 `kaiju-api-artifacts` bound as `KAIJU_ARTIFACT_BUCKET`
65
  - D1 migration `0001_paid_api.sql` applied successfully
66
 
67
- Current launch preflight after those resources:
68
 
69
  ```text
70
- 21 pass / 0 fail / 6 manual
71
  ```
72
 
73
- The remaining manual items are public route mode, required Wrangler secret-name
74
- verification, Stripe Checkout/webhook staging, Worker-to-Gojira staging request,
75
- rollback exercise, and paid-route p95 latency evidence.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
 
77
  Covered locally:
78
 
@@ -187,9 +217,11 @@ python3 scripts/apply_paid_api_cloudflare_bindings.py \
187
  ```
188
 
189
  `--mode scaffold` verifies the local gateway implementation and should pass.
190
- `--mode launch` is stricter and should fail until real Cloudflare bindings,
191
- Wrangler secrets, Stripe webhook evidence, staging traffic, latency evidence,
192
- and rollback proof are attached.
 
 
193
 
194
  Launch evidence is attached through a sanitized JSON file:
195
 
@@ -257,7 +289,10 @@ Current quality evidence:
257
 
258
  ## Release Blockers
259
 
260
- - Raw OpenCode customer-readiness task currently times out on multi-file work.
 
 
 
261
  - Harnessed customer-readiness route passes; paid API must route through that
262
  deterministic product path until a faster raw/quantized path passes.
263
  - Context-size benchmarks passed at 12k, 16k, 24k, and 32k, but the current
 
64
  - R2 `kaiju-api-artifacts` bound as `KAIJU_ARTIFACT_BUCKET`
65
  - D1 migration `0001_paid_api.sql` applied successfully
66
 
67
+ The Worker was deployed on 2026-06-03 at:
68
 
69
  ```text
70
+ https://kaiju-api-gateway.kiyomi-api.workers.dev
71
  ```
72
 
73
+ Gojira-B now advertises `kaiju-coder-7` from its public health endpoint. The
74
+ origin secret was rotated during launch verification and re-applied to
75
+ Cloudflare without writing the value to this repo.
76
+
77
+ Current launch preflight after live staging traffic and rollback verification:
78
+
79
+ ```text
80
+ 24 pass / 0 fail / 3 manual
81
+ ```
82
+
83
+ Passed live launch evidence:
84
+
85
+ - `workers.dev` public staging route resolves to the Kaiju Worker.
86
+ - `KAIJU_ORIGIN_URL` and `KAIJU_ORIGIN_SECRET` are present by Wrangler secret
87
+ name; `KAIJU_STRIPE_WEBHOOK_SECRET` is intentionally not marked present until
88
+ a real Stripe webhook signing secret is configured.
89
+ - Worker-to-Gojira staging request passed through `/v1/chat/completions` with
90
+ `model=kaiju-coder-7`, HTTP `200`, and streaming enabled.
91
+ - Paid-route latency was measured over five staging samples with p95
92
+ `17686.74ms`.
93
+ - Rollback drill succeeded by deploying same-code version
94
+ `e838e01d-2d72-4eb7-9814-b95b7e2cef14`, rolling traffic back to verified
95
+ version `d37d60d1-7bfc-4ac9-a69c-e9339b5e495f`, and rechecking `/health`.
96
+
97
+ Remaining paid-launch manual items:
98
+
99
+ - Attach a real custom API domain. The current route is public and usable for
100
+ staging, but the launch checker requires `exposure_mode=custom_domain`.
101
+ `rmdw.ai` currently uses Vercel DNS, so a Cloudflare custom domain requires a
102
+ Cloudflare-managed zone, partial/CNAME setup, or a separate API domain.
103
+ - Configure `KAIJU_STRIPE_WEBHOOK_SECRET` from a real Stripe webhook endpoint.
104
+ - Test a real Stripe Checkout top-up that sends `checkout.session.completed`
105
+ with `metadata.kaiju_api_key_id`, including duplicate webhook idempotency.
106
 
107
  Covered locally:
108
 
 
217
  ```
218
 
219
  `--mode scaffold` verifies the local gateway implementation and should pass.
220
+ `--mode launch` is stricter. It should remain red until a real custom API
221
+ domain, Stripe webhook signing secret, and Stripe Checkout top-up staging
222
+ evidence are attached. Live Cloudflare bindings, Worker-to-Gojira staging
223
+ traffic, paid-route latency evidence, and rollback proof are already recorded
224
+ in `release/paid-api-launch-evidence.json`.
225
 
226
  Launch evidence is attached through a sanitized JSON file:
227
 
 
289
 
290
  ## Release Blockers
291
 
292
+ - Paid API launch still needs a custom API domain and real Stripe
293
+ Checkout/webhook evidence before public charging.
294
+ - Raw OpenCode customer-readiness task currently times out on multi-file work;
295
+ the harnessed business-owner route is the reliable first paid API product.
296
  - Harnessed customer-readiness route passes; paid API must route through that
297
  deterministic product path until a faster raw/quantized path passes.
298
  - Context-size benchmarks passed at 12k, 16k, 24k, and 32k, but the current