mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-17 20:52:15 +03:00
* feat(responses): virtualize previous_response_id continuation regardless of upstream support OmniRoute now exposes OpenAI-compatible previous_response_id/store continuation to clients unconditionally, even when the selected upstream provider has no native Responses-API state support. Reconstruction happens server-side in handleChatImplementation, before any downstream validation or provider translation: OmniRoute resolves the response id back to the full input/output it previously produced, prepends it to the client's delta, and forwards the full reconstructed history upstream exactly as it does today. Client<->OmniRoute traffic shrinks to the new delta only; OmniRoute<->provider traffic is unchanged. Storage reuses the existing call-log pipeline artifact (already gated by call_log_pipeline_enabled, already retained/cleaned up by the existing call-log lifecycle) instead of duplicating conversation content into a second store -- only a lightweight call_logs.response_id index is new. Every lookup is scoped by api_key_id so one client can never resolve another client's stored conversation, and any unresolvable/missing/ size-limit-omitted state fails closed with OpenAI's own previous_response_not_found contract. Stacked on feat/openai-responses-store-toggle (#10121). * fix(db): re-export responsesContinuationStore from the localDb barrel check-db-rules requires every db/ module to be re-exported (or explicitly allowlisted as intentionally-internal) for discoverability. Missed this when the module was first added. * fix(db): renumber previous_response_id index migration to 154 The migration was numbered 153, but release/v3.8.50 already carries 153_radar_local_model_state.sql. The emngrating runner's collision guard throws on two live .sql files sharing a numeric prefix, so the refreshed merge would fail DB startup. Renumber to the next free slot (154). Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * docs(db): sync migration count to 149 across llm.txt mirrors The responses-continuation store adds one migration, so the docs' migration count is now 149 (was 148). Update README/AGENTS/llm.txt and regenerate the i18n llm.txt mirrors to keep check:docs-all green. Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com> * fix(responses-continuation): respect preserve mode, drop dead export - Un-export ResponsesContinuationState: it's never imported outside responsesContinuationStore.ts, its own defining file. Fixes the check:dead-code regression (410 > baseline 409). - Scope the previous_response_id virtualization interception in chat.ts to skip entirely when responsesPreviousResponseIdMode=preserve. The interception ran unconditionally before target/connection selection, ahead of applyResponsesPreviousResponseIdPolicy (chatCore.ts) -- the existing per-target enforcement point for this setting -- so "preserve" (the explicit, connection-independent contract for "let the upstream resolve previous_response_id natively") was silently unreachable: the field was already deleted and replaced with locally-reconstructed input by the time that policy ran. This also broke Codex's own executor, which relies on an untouched previous_response_id to delegate history resolution upstream (see stripOrphanedCodexFunctionCallOutputs in codex.ts). "auto" and "strip" modes are unaffected -- virtualization is a strict improvement over their old "drop the field, hope the client resent everything" behavior. - Add a regression test exercising the actual chat.ts handler (not just the policy helper in isolation): confirms mode=preserve now proceeds to normal routing instead of the virtualization's previous_response_not_found rejection, and that default/auto mode's existing virtualization behavior is unchanged. Verified the test fails for the right reason against pre-fix chat.ts. Addresses PR review feedback. --------- Co-authored-by: adevwithpurpose <adevwithpurpose@users.noreply.github.com> Co-authored-by: hartmark <hartmark@users.noreply.github.com> Co-authored-by: diegosouzapw <diegosouza.pw@gmail.com>
160 lines
5.1 KiB
TypeScript
160 lines
5.1 KiB
TypeScript
import test from "node:test";
|
|
import assert from "node:assert/strict";
|
|
import fs from "node:fs";
|
|
import os from "node:os";
|
|
import path from "node:path";
|
|
|
|
// OmniRoute-native `previous_response_id` virtualization: resolvePreviousResponseState
|
|
// resolves a response id back to the full input/output a prior call produced by
|
|
// reading the already-persisted call-log artifact, so a later request can be
|
|
// reconstructed to full history server-side without duplicating conversation
|
|
// content into a second store.
|
|
|
|
const TEST_DATA_DIR = fs.mkdtempSync(path.join(os.tmpdir(), "omniroute-responses-continuation-"));
|
|
process.env.DATA_DIR = TEST_DATA_DIR;
|
|
|
|
const core = await import("../../src/lib/db/core.ts");
|
|
const store = await import("../../src/lib/db/responsesContinuationStore.ts");
|
|
|
|
test.after(() => {
|
|
core.resetDbInstance();
|
|
fs.rmSync(TEST_DATA_DIR, { recursive: true, force: true });
|
|
});
|
|
|
|
function insertCallLog(row: {
|
|
id: string;
|
|
responseId: string | null;
|
|
apiKeyId: string | null;
|
|
detailState: string;
|
|
artifactRelPath: string | null;
|
|
}) {
|
|
const db = core.getDbInstance();
|
|
db.prepare(
|
|
`INSERT INTO call_logs
|
|
(id, timestamp, method, path, status, model, provider, account, duration,
|
|
tokens_in, tokens_out, api_key_id, detail_state, artifact_relpath, response_id)
|
|
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`
|
|
).run(
|
|
row.id,
|
|
new Date().toISOString(),
|
|
"POST",
|
|
"/v1/responses",
|
|
200,
|
|
"gpt-5.4-pro",
|
|
"openai",
|
|
"acc1",
|
|
100,
|
|
10,
|
|
20,
|
|
row.apiKeyId,
|
|
row.detailState,
|
|
row.artifactRelPath,
|
|
row.responseId
|
|
);
|
|
}
|
|
|
|
function writeArtifact(relPath: string, pipeline: Record<string, unknown>) {
|
|
const absPath = path.join(TEST_DATA_DIR, "call_logs", relPath);
|
|
fs.mkdirSync(path.dirname(absPath), { recursive: true });
|
|
fs.writeFileSync(
|
|
absPath,
|
|
JSON.stringify({
|
|
schemaVersion: 5,
|
|
summary: {},
|
|
requestBody: null,
|
|
responseBody: null,
|
|
error: null,
|
|
pipeline,
|
|
})
|
|
);
|
|
}
|
|
|
|
test("resolvePreviousResponseState reconstructs input/output from the call-log artifact", () => {
|
|
insertCallLog({
|
|
id: "log-1",
|
|
responseId: "resp_abc",
|
|
apiKeyId: "key-1",
|
|
detailState: "ready",
|
|
artifactRelPath: "2026-01-01/log-1.json",
|
|
});
|
|
writeArtifact("2026-01-01/log-1.json", {
|
|
providerRequest: { body: { input: [{ type: "message", role: "user", content: "hi" }] } },
|
|
clientResponse: {
|
|
id: "resp_abc",
|
|
output: [{ type: "message", role: "assistant", content: "hello" }],
|
|
},
|
|
});
|
|
|
|
const result = store.resolvePreviousResponseState("resp_abc", "key-1");
|
|
assert.deepEqual(result, {
|
|
input: [{ type: "message", role: "user", content: "hi" }],
|
|
output: [{ type: "message", role: "assistant", content: "hello" }],
|
|
});
|
|
});
|
|
|
|
test("resolvePreviousResponseState returns null for an unknown response id", () => {
|
|
const result = store.resolvePreviousResponseState("resp_does_not_exist", "key-1");
|
|
assert.equal(result, null);
|
|
});
|
|
|
|
test("resolvePreviousResponseState never crosses tenants (scoped by api_key_id)", () => {
|
|
insertCallLog({
|
|
id: "log-2",
|
|
responseId: "resp_tenant_a",
|
|
apiKeyId: "key-a",
|
|
detailState: "ready",
|
|
artifactRelPath: "2026-01-01/log-2.json",
|
|
});
|
|
writeArtifact("2026-01-01/log-2.json", {
|
|
providerRequest: { body: { input: [{ role: "user", content: "secret" }] } },
|
|
clientResponse: { id: "resp_tenant_a", output: [{ role: "assistant", content: "reply" }] },
|
|
});
|
|
|
|
assert.equal(store.resolvePreviousResponseState("resp_tenant_a", "key-b"), null);
|
|
assert.equal(store.resolvePreviousResponseState("resp_tenant_a", null), null);
|
|
assert.notEqual(store.resolvePreviousResponseState("resp_tenant_a", "key-a"), null);
|
|
});
|
|
|
|
test("resolvePreviousResponseState returns null when the artifact is missing on disk", () => {
|
|
insertCallLog({
|
|
id: "log-3",
|
|
responseId: "resp_missing_file",
|
|
apiKeyId: "key-1",
|
|
detailState: "ready",
|
|
artifactRelPath: "2026-01-01/does-not-exist.json",
|
|
});
|
|
|
|
assert.equal(store.resolvePreviousResponseState("resp_missing_file", "key-1"), null);
|
|
});
|
|
|
|
test("resolvePreviousResponseState fails closed when the pipeline payload was size-limit-omitted", () => {
|
|
insertCallLog({
|
|
id: "log-4",
|
|
responseId: "resp_omitted",
|
|
apiKeyId: "key-1",
|
|
detailState: "ready",
|
|
artifactRelPath: "2026-01-01/log-4.json",
|
|
});
|
|
// A size-limit-omitted payload is replaced with a placeholder string, not
|
|
// an object -- resolvePreviousResponseState must never try to reconstruct
|
|
// from it and silently drop history.
|
|
writeArtifact("2026-01-01/log-4.json", {
|
|
providerRequest: { body: "[omitted: call log artifact size limit exceeded]" },
|
|
clientResponse: { id: "resp_omitted", output: [] },
|
|
});
|
|
|
|
assert.equal(store.resolvePreviousResponseState("resp_omitted", "key-1"), null);
|
|
});
|
|
|
|
test("resolvePreviousResponseState returns null when detail logging was never captured for this row", () => {
|
|
insertCallLog({
|
|
id: "log-5",
|
|
responseId: "resp_no_detail",
|
|
apiKeyId: "key-1",
|
|
detailState: "none",
|
|
artifactRelPath: null,
|
|
});
|
|
|
|
assert.equal(store.resolvePreviousResponseState("resp_no_detail", "key-1"), null);
|
|
});
|