profit/lakehouse
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

agent.ts: route generateCloud through /v1/chat (Phase 44 migration)

Browse Source 
Phase 44 PRD (docs/CONTROL_PLANE_PRD.md:204) explicitly lists
`tests/multi-agent/agent.ts::generate()` as a migration target:
every internal LLM caller must flow through /v1/chat so usage
accounting + audit trail see all traffic.

generateCloud() was bypassing the gateway entirely — direct POST to
OLLAMA_CLOUD_URL/api/generate with the bearer key. This meant:
  - /v1/usage missed every agent.ts cloud call
  - No gateway-side caching, rate-limiting, or cost gating
  - Callers needed OLLAMA_CLOUD_KEY in env (leak risk; gateway
    already owns the key)

Migration:
  - Endpoint: OLLAMA_CLOUD_URL/api/generate → GATEWAY/v1/chat
  - Body shape: {prompt,options.num_predict,options.temperature} →
    OpenAI-compatible {messages[],temperature,max_tokens}
  - provider: "ollama_cloud" explicit in the request
  - Response extraction: data.response → data.choices[0].message.content
  - OLLAMA_CLOUD_KEY no longer required in agent.ts env

Phase 44 gate verified: `grep localhost:3200/generate|/api/generate`
now only hits (a) the ollama_cloud.rs adapter itself (legit — it's
the gateway-side direct caller) and (b) this comment explaining the
migration history. Zero non-adapter code paths to /api/generate.

generate() (local Ollama) still goes direct to :3200 — that's the
t1_hot path. Phase 44 PRD focuses on cloud callers; hot-path local
generation deliberately stays direct for latency.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
root 2026-04-24 13:27:54 -05:00
parent 049a4b69fb
commit 021c1b557f
1 changed files with 21 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
tests/multi-agent/agent.ts
View File

@ -394,11 +394,15 @@ export async function generate(model: string, prompt: string, opts: {
return text; return text;
} }
// Cloud generate — hits Ollama Cloud directly with the bearer key. Same // Cloud generate — routes through the lakehouse gateway's /v1/chat
// /api/generate shape as local Ollama; `thinking` field (for gpt-oss:Nb) // with provider="ollama_cloud". Phase 44 migration (2026-04-24): was
// is discarded, only `response` is returned. Caller should budget // hitting OLLAMA_CLOUD_URL/api/generate directly with a bearer key,
// num_predict ≥ 400 so thinking-model reasoning has room before the // bypassing the gateway's usage tracking + audit path. Now every call
// visible response starts. // flows through /v1/chat so /v1/usage accounts for it. Gateway holds
// the OLLAMA_CLOUD_KEY; caller no longer needs it in env.
//
// Thinking-model budget note: num_predict ≥ 400 still matters, just
// expressed via max_tokens on the /v1/chat request.
export async function generateCloud(model: string, prompt: string, opts: { export async function generateCloud(model: string, prompt: string, opts: {
max_tokens?: number; max_tokens?: number;
temperature?: number; temperature?: number;
@ -406,41 +410,35 @@ export async function generateCloud(model: string, prompt: string, opts: {
bypass_budget?: boolean; bypass_budget?: boolean;
think?: boolean; think?: boolean;
} = {}): Promise<string> { } = {}): Promise<string> {
if (!OLLAMA_CLOUD_KEY) {
throw new Error("OLLAMA_CLOUD_KEY not set; cannot reach Ollama Cloud");
}
assertContextBudget(model, prompt, { assertContextBudget(model, prompt, {
system: opts.system, system: opts.system,
max_tokens: opts.max_tokens, max_tokens: opts.max_tokens,
bypass: opts.bypass_budget, bypass: opts.bypass_budget,
}); });
const messages: Array<{ role: string; content: string }> = [];
if (opts.system) messages.push({ role: "system", content: opts.system });
messages.push({ role: "user", content: prompt });
const body: Record<string, any> = { const body: Record<string, any> = {
model, model,
prompt, messages,
stream: false, provider: "ollama_cloud",
options: { temperature: opts.temperature ?? 0.3,
temperature: opts.temperature ?? 0.3, max_tokens: Math.max(opts.max_tokens ?? 800, 400),
num_predict: Math.max(opts.max_tokens ?? 800, 400),
},
}; };
if (opts.system) body.system = opts.system;
if (opts.think !== undefined) body.think = opts.think; if (opts.think !== undefined) body.think = opts.think;
const resp = await fetch(`${OLLAMA_CLOUD_URL}/api/generate`, { const resp = await fetch(`${GATEWAY}/v1/chat`, {
method: "POST", method: "POST",
headers: { headers: { "Content-Type": "application/json" },
"Authorization": `Bearer ${OLLAMA_CLOUD_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify(body), body: JSON.stringify(body),
}); });
if (!resp.ok) { if (!resp.ok) {
throw new Error(`Ollama Cloud ${resp.status}: ${await resp.text().catch(() => "?")}`); throw new Error(`gateway /v1/chat ${resp.status}: ${await resp.text().catch(() => "?")}`);
} }
const data: any = await resp.json(); const data: any = await resp.json();
const text = typeof data.response === "string" ? data.response : ""; const text = data?.choices?.[0]?.message?.content ?? "";
// Same non-throw policy as local generate() — empty text is a valid // Same non-throw policy as local generate() — empty text is a valid
// signal that thinking ate the budget. Let generateContinuable retry. // signal that thinking ate the budget. Let generateContinuable retry.
return text; return typeof text === "string" ? text : "";
} }
// --- Prompt construction --- // --- Prompt construction ---