restokes92 commited on
Commit
b5dcda3
·
verified ·
1 Parent(s): 032872d

Upload Kaiju Coder 7 OpenCode helper package

Browse files
PUBLIC_TESTING_QUICKSTART.md CHANGED
@@ -129,7 +129,8 @@ Expected result:
129
  - Raw multi-file OpenCode generation: still too slow for broad paid claims;
130
  useful for testing, but paid API claims should favor harnessed product
131
  workflows until broader latency gates pass
132
- - Paid API: not public until launch preflight passes
 
133
 
134
  ## What Not To Claim Yet
135
 
@@ -153,14 +154,15 @@ Do claim:
153
  - a GGUF Q8_0 candidate exists, but is not public quantized-weights release
154
  evidence until runtime smoke passes
155
 
156
- ## Current Blockers Before Public Release
157
 
158
- - Hugging Face repo creation still requires a write-capable token or namespace.
159
- - Full merged model upload has not completed; the merged folder must first have
160
- the metadata packet synced by `prepare_hf_merged_model_metadata.sh`.
161
  - The GGUF Q8_0 candidate still needs a runtime smoke before public
162
  quantized-weights upload.
163
- - Public paid API launch needs real Cloudflare D1/KV/R2 bindings, Wrangler
164
- secret verification, Stripe webhook staging evidence, staging traffic, latency
165
- evidence, and rollback proof.
166
- - Human review is still required before public upload.
 
 
 
 
129
  - Raw multi-file OpenCode generation: still too slow for broad paid claims;
130
  useful for testing, but paid API claims should favor harnessed product
131
  workflows until broader latency gates pass
132
+ - Paid API: not public until launch preflight passes and the Stripe live-mode
133
+ switch is deliberately completed
134
 
135
  ## What Not To Claim Yet
136
 
 
154
  - a GGUF Q8_0 candidate exists, but is not public quantized-weights release
155
  evidence until runtime smoke passes
156
 
157
+ ## Remaining Caveats Before Broader Claims
158
 
159
+ - Hugging Face public release repos are uploaded and public under `RMDWLLC`.
 
 
160
  - The GGUF Q8_0 candidate still needs a runtime smoke before public
161
  quantized-weights upload.
162
+ - Raw multi-file OpenCode generation is still not the public speed story; use
163
+ the deterministic router/harness for websites and business-owner packs.
164
+ - Public paid API launch has approval and preflight evidence, but real customer
165
+ charging still needs a deliberate Stripe live-mode switch and controlled live
166
+ payment verification.
167
+ - Do not claim 32k context as the live default until it is freshly restarted
168
+ and re-confirmed.
scripts/prepare_hf_merged_model_metadata.sh CHANGED
@@ -58,7 +58,7 @@ cat > "${STAGING}/MERGED_MODEL_RELEASE_MANIFEST.json" <<EOF
58
  "notes": [
59
  "Local metadata sync only; no Hugging Face upload performed.",
60
  "Qwen attribution belongs in README/provenance/license notes, not the product model id.",
61
- "Public paid API launch remains blocked until live launch preflight and human review pass."
62
  ]
63
  }
64
  EOF
 
58
  "notes": [
59
  "Local metadata sync only; no Hugging Face upload performed.",
60
  "Qwen attribution belongs in README/provenance/license notes, not the product model id.",
61
+ "Public paid API preflight evidence has passed; real customer charging still requires the deliberate Stripe live-mode switch."
62
  ]
63
  }
64
  EOF