Text Generation
Transformers
Safetensors
English
qwen3_5
image-text-to-text
kaiju-coder-7
coding
local-ai
business
opencode
tool-use
conversational
Instructions to use RMDWLLC/kaiju-coder-7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RMDWLLC/kaiju-coder-7 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RMDWLLC/kaiju-coder-7") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("RMDWLLC/kaiju-coder-7") model = AutoModelForImageTextToText.from_pretrained("RMDWLLC/kaiju-coder-7") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use RMDWLLC/kaiju-coder-7 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RMDWLLC/kaiju-coder-7" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RMDWLLC/kaiju-coder-7", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RMDWLLC/kaiju-coder-7
- SGLang
How to use RMDWLLC/kaiju-coder-7 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "RMDWLLC/kaiju-coder-7" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RMDWLLC/kaiju-coder-7", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "RMDWLLC/kaiju-coder-7" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RMDWLLC/kaiju-coder-7", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use RMDWLLC/kaiju-coder-7 with Docker Model Runner:
docker model run hf.co/RMDWLLC/kaiju-coder-7
Refresh Kaiju Coder 7 final readiness docs
Browse files- FINAL_RELEASE_REPORT.md +15 -23
- GOAL_COMPLETION_AUDIT.md +7 -7
- HF_UPLOAD_EVIDENCE.md +3 -3
- PAID_API_READINESS.md +35 -33
FINAL_RELEASE_REPORT.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
# Kaiju Coder 7 Final Release Report
|
| 2 |
|
| 3 |
-
Generated: `2026-06-03T21:
|
| 4 |
|
| 5 |
Product name: `Kaiju Coder 7`
|
| 6 |
Public model id: `kaiju-coder-7`
|
|
@@ -15,10 +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
|
| 19 |
-
|
| 20 |
-
charging still requires a
|
| 21 |
-
|
| 22 |
|
| 23 |
## Runtime
|
| 24 |
|
|
@@ -38,11 +38,11 @@ stability and speed.
|
|
| 38 |
|
| 39 |
| Area | Result |
|
| 40 |
|---|---|
|
| 41 |
-
| Local public-testing readiness | `ready=True pass=
|
| 42 |
-
| Hugging Face release readiness | `ready=True pass=
|
| 43 |
-
| Public launch readiness | `ready=
|
| 44 |
| Hugging Face staging integrity | `ready=True pass=6 fail=0 manual=0 rc=0` |
|
| 45 |
-
| Paid API launch readiness | `ready=
|
| 46 |
|
| 47 |
## Hugging Face Upload Evidence
|
| 48 |
|
|
@@ -52,30 +52,22 @@ stability and speed.
|
|
| 52 |
| Small helper repos uploaded | `True` |
|
| 53 |
| Merged model uploaded | `True` |
|
| 54 |
| Merged repo | `RMDWLLC/kaiju-coder-7` |
|
| 55 |
-
| Merged repo SHA | `
|
| 56 |
| Merged upload size | `39 files / 53.8G / 14 safetensors shards recorded` |
|
| 57 |
| Download status | `public downloads verified; no active private-storage blocker recorded` |
|
| 58 |
| Visibility decision | `PUBLIC`; `HF_VISIBILITY_DECISION: PUBLIC` recorded in human review |
|
| 59 |
|
| 60 |
## Hugging Face Release Blockers
|
| 61 |
|
| 62 |
-
|
| 63 |
-
|---|---|---|
|
| 64 |
-
| manual | paid API launch preflight | 24 pass, 0 fail, 3 manual |
|
| 65 |
|
| 66 |
## Public Launch Blockers
|
| 67 |
|
| 68 |
-
|
| 69 |
-
|---|---|---|
|
| 70 |
-
| fail | paid API launch preflight | 24 pass, 0 fail, 3 manual |
|
| 71 |
|
| 72 |
## Paid API Launch Blockers
|
| 73 |
|
| 74 |
-
|
| 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 |
|
|
@@ -272,9 +264,9 @@ human release review explicitly approves public paid API launch.
|
|
| 272 |
| git status | `git status --short` | 0 |
|
| 273 |
| local readiness | `/opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_kaiju_public_release_readiness.py --mode local --json --base-url http://100.109.109.14:18083/v1 --live-timeout 5 --staging-dir /tmp/kaiju-coder-7-hf-staging` | 0 |
|
| 274 |
| HF release readiness | `/opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_kaiju_public_release_readiness.py --mode hf-release --json --base-url http://100.109.109.14:18083/v1 --live-timeout 5 --staging-dir /tmp/kaiju-coder-7-hf-staging` | 0 |
|
| 275 |
-
| public readiness | `/opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_kaiju_public_release_readiness.py --mode public --json --base-url http://100.109.109.14:18083/v1 --live-timeout 5 --staging-dir /tmp/kaiju-coder-7-hf-staging` |
|
| 276 |
| HF staging integrity | `/opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_hf_staging_integrity.py --staging-dir /tmp/kaiju-coder-7-hf-staging --require-checksums --json` | 0 |
|
| 277 |
-
| paid API launch readiness | `/opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_paid_api_readiness.py --mode launch --json` |
|
| 278 |
|
| 279 |
## Report Safety
|
| 280 |
|
|
|
|
| 1 |
# Kaiju Coder 7 Final Release Report
|
| 2 |
|
| 3 |
+
Generated: `2026-06-03T21:12:14Z`
|
| 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, a custom API domain, live Cloudflare bindings,
|
| 19 |
+
Worker-to-Gojira proof, rollback proof, latency evidence, and Stripe test-mode
|
| 20 |
+
Checkout/webhook evidence. Real customer charging still requires a deliberate
|
| 21 |
+
Stripe live-mode switch and controlled live payment verification.
|
| 22 |
|
| 23 |
## Runtime
|
| 24 |
|
|
|
|
| 38 |
|
| 39 |
| Area | Result |
|
| 40 |
|---|---|
|
| 41 |
+
| Local public-testing readiness | `ready=True pass=24 fail=0 manual=0 rc=0` |
|
| 42 |
+
| Hugging Face release readiness | `ready=True pass=24 fail=0 manual=0 rc=0` |
|
| 43 |
+
| Public launch readiness | `ready=True pass=24 fail=0 manual=0 rc=0` |
|
| 44 |
| Hugging Face staging integrity | `ready=True pass=6 fail=0 manual=0 rc=0` |
|
| 45 |
+
| Paid API launch readiness | `ready=True pass=27 fail=0 manual=0 rc=0` |
|
| 46 |
|
| 47 |
## Hugging Face Upload Evidence
|
| 48 |
|
|
|
|
| 52 |
| Small helper repos uploaded | `True` |
|
| 53 |
| Merged model uploaded | `True` |
|
| 54 |
| Merged repo | `RMDWLLC/kaiju-coder-7` |
|
| 55 |
+
| Merged repo SHA | `736af44add9321f74e8603cd739245fc0853d62c` |
|
| 56 |
| Merged upload size | `39 files / 53.8G / 14 safetensors shards recorded` |
|
| 57 |
| Download status | `public downloads verified; no active private-storage blocker recorded` |
|
| 58 |
| Visibility decision | `PUBLIC`; `HF_VISIBILITY_DECISION: PUBLIC` recorded in human review |
|
| 59 |
|
| 60 |
## Hugging Face Release Blockers
|
| 61 |
|
| 62 |
+
- No matching checks.
|
|
|
|
|
|
|
| 63 |
|
| 64 |
## Public Launch Blockers
|
| 65 |
|
| 66 |
+
- No matching checks.
|
|
|
|
|
|
|
| 67 |
|
| 68 |
## Paid API Launch Blockers
|
| 69 |
|
| 70 |
+
- No matching checks.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
|
| 72 |
## Evidence Paths
|
| 73 |
|
|
|
|
| 264 |
| git status | `git status --short` | 0 |
|
| 265 |
| local readiness | `/opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_kaiju_public_release_readiness.py --mode local --json --base-url http://100.109.109.14:18083/v1 --live-timeout 5 --staging-dir /tmp/kaiju-coder-7-hf-staging` | 0 |
|
| 266 |
| HF release readiness | `/opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_kaiju_public_release_readiness.py --mode hf-release --json --base-url http://100.109.109.14:18083/v1 --live-timeout 5 --staging-dir /tmp/kaiju-coder-7-hf-staging` | 0 |
|
| 267 |
+
| public readiness | `/opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_kaiju_public_release_readiness.py --mode public --json --base-url http://100.109.109.14:18083/v1 --live-timeout 5 --staging-dir /tmp/kaiju-coder-7-hf-staging` | 0 |
|
| 268 |
| HF staging integrity | `/opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_hf_staging_integrity.py --staging-dir /tmp/kaiju-coder-7-hf-staging --require-checksums --json` | 0 |
|
| 269 |
+
| paid API launch readiness | `/opt/homebrew/opt/python@3.14/bin/python3.14 scripts/check_paid_api_readiness.py --mode launch --json` | 0 |
|
| 270 |
|
| 271 |
## Report Safety
|
| 272 |
|
GOAL_COMPLETION_AUDIT.md
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
# Kaiju Coder 7 Goal Completion Audit
|
| 2 |
|
| 3 |
-
Generated: `2026-06-03T21:
|
| 4 |
|
| 5 |
-
Overall: `
|
| 6 |
-
Summary: `
|
| 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 |
|
|
@@ -13,9 +13,9 @@ This audit maps the active Kaiju Coder 7 objective to current evidence. It is st
|
|
| 13 |
|---|---:|---:|
|
| 14 |
| Local public-testing readiness | `True` | `0` |
|
| 15 |
| Hugging Face release readiness | `True` | `0` |
|
| 16 |
-
| Public launch readiness | `
|
| 17 |
| Paid API scaffold | `True` | `0` |
|
| 18 |
-
| Paid API launch | `
|
| 19 |
| HF staging integrity | `True` | `0` |
|
| 20 |
| HF namespace permission evidence | `True` | `0` |
|
| 21 |
| Human public review | `True` | `0` |
|
|
@@ -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. | `
|
| 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 |
-
-
|
| 49 |
|
| 50 |
## Commands To Re-run
|
| 51 |
|
|
|
|
| 1 |
# Kaiju Coder 7 Goal Completion Audit
|
| 2 |
|
| 3 |
+
Generated: `2026-06-03T21:12:21Z`
|
| 4 |
|
| 5 |
+
Overall: `complete`
|
| 6 |
+
Summary: `18 passed / 0 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 |
|
|
|
|
| 13 |
|---|---:|---:|
|
| 14 |
| Local public-testing readiness | `True` | `0` |
|
| 15 |
| Hugging Face release readiness | `True` | `0` |
|
| 16 |
+
| Public launch readiness | `True` | `0` |
|
| 17 |
| Paid API scaffold | `True` | `0` |
|
| 18 |
+
| Paid API launch | `True` | `0` |
|
| 19 |
| HF staging integrity | `True` | `0` |
|
| 20 |
| HF namespace permission evidence | `True` | `0` |
|
| 21 |
| Human public review | `True` | `0` |
|
|
|
|
| 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. | `passed` | python3 scripts/check_paid_api_readiness.py --mode launch | |
|
| 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 |
+
- No blocking items.
|
| 49 |
|
| 50 |
## Commands To Re-run
|
| 51 |
|
HF_UPLOAD_EVIDENCE.md
CHANGED
|
@@ -6,10 +6,10 @@ Generated: `2026-06-03T20:36:26Z`
|
|
| 6 |
|
| 7 |
| Repo | Visibility | Evidence |
|
| 8 |
|---|---|---|
|
| 9 |
-
| `RMDWLLC/kaiju-coder-7-adapter` | public | Final visible SHA `
|
| 10 |
| `RMDWLLC/kaiju-coder-7-opencode` | public | Final visible SHA `3c9c75416ffb41645a1a959beb99baeff6972fb8`; public visibility and OpenCode installer dry-run verified. |
|
| 11 |
| `RMDWLLC/kaiju-coder-7-quantized-runtime` | public | Uploaded at commit `6d7449a3ffac68ed1d591c57b044ba599cee8b11`; public visibility verified. |
|
| 12 |
-
| `RMDWLLC/kaiju-coder-7` | public | `hf upload-large-folder` completed successfully, then metadata/evidence refreshed at final visible SHA `
|
| 13 |
|
| 14 |
These SHAs are a point-in-time release evidence snapshot. Uploading this
|
| 15 |
evidence file itself creates another metadata commit, so use `hf models info`
|
|
@@ -78,7 +78,7 @@ Result:
|
|
| 78 |
- The downloaded OpenCode helper installer dry-run passed and included the
|
| 79 |
loop guard.
|
| 80 |
- Merged model metadata reports `private: false`, SHA
|
| 81 |
-
`
|
| 82 |
safetensors shards.
|
| 83 |
|
| 84 |
The earlier private-storage limit blocked private file downloads after the
|
|
|
|
| 6 |
|
| 7 |
| Repo | Visibility | Evidence |
|
| 8 |
|---|---|---|
|
| 9 |
+
| `RMDWLLC/kaiju-coder-7-adapter` | public | Final visible SHA `67bb48b8115b820cd8b01d1778d2610d9ce63692`; public visibility verified after 2026-06-03 paid API evidence refresh. |
|
| 10 |
| `RMDWLLC/kaiju-coder-7-opencode` | public | Final visible SHA `3c9c75416ffb41645a1a959beb99baeff6972fb8`; public visibility and OpenCode installer dry-run verified. |
|
| 11 |
| `RMDWLLC/kaiju-coder-7-quantized-runtime` | public | Uploaded at commit `6d7449a3ffac68ed1d591c57b044ba599cee8b11`; public visibility verified. |
|
| 12 |
+
| `RMDWLLC/kaiju-coder-7` | public | `hf upload-large-folder` completed successfully, then metadata/evidence refreshed at final visible SHA `736af44add9321f74e8603cd739245fc0853d62c`; public metadata reports `private: false`. |
|
| 13 |
|
| 14 |
These SHAs are a point-in-time release evidence snapshot. Uploading this
|
| 15 |
evidence file itself creates another metadata commit, so use `hf models info`
|
|
|
|
| 78 |
- The downloaded OpenCode helper installer dry-run passed and included the
|
| 79 |
loop guard.
|
| 80 |
- Merged model metadata reports `private: false`, SHA
|
| 81 |
+
`736af44add9321f74e8603cd739245fc0853d62c`, and lists all `14`
|
| 82 |
safetensors shards.
|
| 83 |
|
| 84 |
The earlier private-storage limit blocked private file downloads after the
|
PAID_API_READINESS.md
CHANGED
|
@@ -68,41 +68,43 @@ 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
|
|
|
|
| 78 |
|
| 79 |
```text
|
| 80 |
-
|
| 81 |
```
|
| 82 |
|
| 83 |
Passed live launch evidence:
|
| 84 |
|
| 85 |
-
- `
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
- Worker-to-Gojira staging request passed through
|
|
|
|
| 90 |
`model=kaiju-coder-7`, HTTP `200`, and streaming enabled.
|
| 91 |
-
- Paid-route latency was measured over five staging
|
| 92 |
-
`
|
|
|
|
|
|
|
|
|
|
| 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 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 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 |
|
|
@@ -217,11 +219,10 @@ python3 scripts/apply_paid_api_cloudflare_bindings.py \
|
|
| 217 |
```
|
| 218 |
|
| 219 |
`--mode scaffold` verifies the local gateway implementation and should pass.
|
| 220 |
-
`--mode launch` is stricter
|
| 221 |
-
|
| 222 |
-
|
| 223 |
-
|
| 224 |
-
in `release/paid-api-launch-evidence.json`.
|
| 225 |
|
| 226 |
Launch evidence is attached through a sanitized JSON file:
|
| 227 |
|
|
@@ -289,8 +290,9 @@ Current quality evidence:
|
|
| 289 |
|
| 290 |
## Release Blockers
|
| 291 |
|
| 292 |
-
-
|
| 293 |
-
|
|
|
|
| 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
|
|
@@ -307,13 +309,13 @@ Current quality evidence:
|
|
| 307 |
smoke tests, passed a 16k business-document smoke in `53.44s`, and reduces
|
| 308 |
model memory to about `17.8 GiB`; its OpenCode one-file smoke now passes.
|
| 309 |
- Persisted quantized public weights are still pending.
|
| 310 |
-
- Hosted gateway
|
| 311 |
binding, live KV rate-limit binding, live R2 artifact binding, model
|
| 312 |
-
enforcement, secret-content rejection,
|
| 313 |
-
|
| 314 |
-
|
| 315 |
-
|
| 316 |
-
|
| 317 |
-
|
| 318 |
-
|
| 319 |
approval.
|
|
|
|
| 68 |
|
| 69 |
```text
|
| 70 |
https://kaiju-api-gateway.kiyomi-api.workers.dev
|
| 71 |
+
https://kaiju-api.kiyomikode.com
|
| 72 |
```
|
| 73 |
|
| 74 |
Gojira-B now advertises `kaiju-coder-7` from its public health endpoint. The
|
| 75 |
origin secret was rotated during launch verification and re-applied to
|
| 76 |
Cloudflare without writing the value to this repo.
|
| 77 |
|
| 78 |
+
Current launch preflight after custom-domain traffic, Stripe test webhook
|
| 79 |
+
staging, and rollback verification:
|
| 80 |
|
| 81 |
```text
|
| 82 |
+
27 pass / 0 fail / 0 manual
|
| 83 |
```
|
| 84 |
|
| 85 |
Passed live launch evidence:
|
| 86 |
|
| 87 |
+
- Custom domain `https://kaiju-api.kiyomikode.com` resolves to the intended
|
| 88 |
+
Kaiju Worker; `/health` returned `200` in the launch evidence probe.
|
| 89 |
+
- `KAIJU_ORIGIN_URL`, `KAIJU_ORIGIN_SECRET`, and
|
| 90 |
+
`KAIJU_STRIPE_WEBHOOK_SECRET` are present by Wrangler secret name.
|
| 91 |
+
- Worker-to-Gojira staging request passed through
|
| 92 |
+
`https://kaiju-api.kiyomikode.com/v1/chat/completions` with
|
| 93 |
`model=kaiju-coder-7`, HTTP `200`, and streaming enabled.
|
| 94 |
+
- Paid-route latency through the custom domain was measured over five staging
|
| 95 |
+
samples with p95 `14121.18ms`.
|
| 96 |
+
- Stripe test-mode `checkout.session.completed` credited the staging API key
|
| 97 |
+
using `metadata.kaiju_api_key_id`; duplicate signed delivery returned
|
| 98 |
+
`duplicate: true` and did not double-credit.
|
| 99 |
- Rollback drill succeeded by deploying same-code version
|
| 100 |
`e838e01d-2d72-4eb7-9814-b95b7e2cef14`, rolling traffic back to verified
|
| 101 |
version `d37d60d1-7bfc-4ac9-a69c-e9339b5e495f`, and rechecking `/health`.
|
| 102 |
|
| 103 |
+
Real-money public charging still needs an explicit Stripe live-mode switch:
|
| 104 |
+
create the live Checkout products/links or Sessions, create the live webhook
|
| 105 |
+
endpoint for the final API domain, replace `KAIJU_STRIPE_WEBHOOK_SECRET` with
|
| 106 |
+
the live webhook signing secret, and run a live-mode penny or controlled
|
| 107 |
+
internal payment before advertising paid API access.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
|
| 109 |
Covered locally:
|
| 110 |
|
|
|
|
| 219 |
```
|
| 220 |
|
| 221 |
`--mode scaffold` verifies the local gateway implementation and should pass.
|
| 222 |
+
`--mode launch` is stricter and now passes with the custom domain, live
|
| 223 |
+
Cloudflare bindings, Wrangler secret-name evidence, Stripe test-mode top-up
|
| 224 |
+
staging, Worker-to-Gojira traffic, paid-route latency evidence, and rollback
|
| 225 |
+
proof recorded in `release/paid-api-launch-evidence.json`.
|
|
|
|
| 226 |
|
| 227 |
Launch evidence is attached through a sanitized JSON file:
|
| 228 |
|
|
|
|
| 290 |
|
| 291 |
## Release Blockers
|
| 292 |
|
| 293 |
+
- Real-money paid API charging still needs a deliberate live-mode Stripe switch
|
| 294 |
+
and controlled live payment verification. The technical launch preflight is
|
| 295 |
+
green with test-mode Stripe staging evidence.
|
| 296 |
- Raw OpenCode customer-readiness task currently times out on multi-file work;
|
| 297 |
the harnessed business-owner route is the reliable first paid API product.
|
| 298 |
- Harnessed customer-readiness route passes; paid API must route through that
|
|
|
|
| 309 |
smoke tests, passed a 16k business-document smoke in `53.44s`, and reduces
|
| 310 |
model memory to about `17.8 GiB`; its OpenCode one-file smoke now passes.
|
| 311 |
- Persisted quantized public weights are still pending.
|
| 312 |
+
- Hosted gateway now has local-tested API key behavior, live D1 prepaid credits
|
| 313 |
binding, live KV rate-limit binding, live R2 artifact binding, model
|
| 314 |
+
enforcement, secret-content rejection, custom API domain, signed Stripe
|
| 315 |
+
test-mode webhook top-up behavior, rollback evidence, and custom-domain p95
|
| 316 |
+
latency evidence.
|
| 317 |
+
- `python3 scripts/check_paid_api_readiness.py --mode launch` currently passes
|
| 318 |
+
`27 pass / 0 fail / 0 manual`. This means the technical hosted API path is
|
| 319 |
+
launch-ready for controlled testing; real customer charging still needs the
|
| 320 |
+
live-mode Stripe switch above.
|
| 321 |
approval.
|