Files
OmniRoute/tests/unit/sse-parser.test.ts
Bob.Hou 60580ffeb7 fix(antigravity): streaming passthrough for non-streaming clients (#7408)
* chore(ci): add .mergify.yml to main — Mergify only reads config from the default branch (#7168)

* fix(ci): add the auto-enqueue pull_request_rule to the Mergify config (queue_conditions alone are eligibility-only) (#7179)

* fix(ci): migrate Mergify auto-enqueue to merge_protections_settings.auto_merge_conditions (rules-based path is EOL 2026-07-16) (#7216)

* fix(ci): drop Mergify batch settings (batching is a paid-tier feature; free plan queue is serial) (#7220)

* fix(ci): merge queue tolerates the advisory dast-smoke failure (its GH-hosted build hang dequeued every attempt) (#7225)

* test(ci): make the #6634 selfref guard hermetic — main's copy hard-fails every PR (#7341)

main's copy of this test still does git I/O inside a unit test:

    const baseSrc = git(['show', 'origin/main:' + FILE]);

Runners check out a shallow single ref, so origin/main does not resolve and the
test dies with 'fatal: invalid object name origin/main'. Every PR into main
fails Unit Tests (7/8) on it — today that is #7313, #7315, #7316, #7334, #7336
and #7337, six PRs red on a defect none of them introduced. #7313 has no other
red at all.

release/v3.8.49 already carries a fix (2e42b8efc, #7174: try/catch, fetch
origin/main on demand, t.skip() when unreachable), but it only reaches main at
release time — so main stays broken for the whole cycle. Cherry-picking it would
also import a new problem: PR Test Policy classifies t.skip() as a silenced
assertion, which we watched it correctly catch on #7300 today.

This is the hermetic version instead (ported from #7327, which does the same for
the release branch): read the file straight off disk, compare against an empty
base so baseTaut/baseExtTaut are 0 — the strictest possible comparison point —
and call evaluateMasking() directly. No git ref, no fetch, no skip, nothing the
runner's checkout depth can break.

The #6634 regression stays covered: the guard's logic lives in
SELF_TEST_FIXTURE_RE (check-test-masking.mjs:337), not in the test. Proven both
ways on main before committing — neutralise SELF_TEST_FIXTURE_RE to /$^/ and
the test FAILS; restore it and it passes 2/2, with check-test-masking.mjs left
byte-identical.

Co-authored-by: growab <nekron@icloud.com>

* chore(quality): tighten main's coverage baseline to the CI's real numbers (#7347)

main's ratchet had been failing --require-tighten on every PR: 11 metrics
improved but the baseline was never tightened. Same class as the #6634
selfref guard — an infra fix that lands only on the release branch leaves
main red for the whole cycle, and every PR into main pays for it.

Values are the merged-coverage numbers from a run on main itself (a local
run measures ~68% vs CI's ~80%; the baseline's own note warns about that
gap). Only the 11 coverage values change — gitleaks and semgrepFindings
keep main's own state.

No changelog fragment: #7326 carries it on release/v3.8.49, and a second
one here would double the entry at release time.

* fix(antigravity): remove hardcoded 120s SSE collect timeout

The SSE collection in collectStreamToResponse had a hardcoded 120 s
timeout.  Reasoning-heavy models like gemini-3.1-pro-high on large
prompts (>30 KB) regularly exceed 120 s of generation time, causing
the executor to return a synthetic 504 before the model finishes.

Replace the hardcoded value with FETCH_TIMEOUT_MS (default 600 s,
overridable via FETCH_TIMEOUT_MS env var), which is the standard
upstream-request budget across all OmniRoute providers.

Signed-off-by: Minxi Hou <houminxi@gmail.com>

* fix(antigravity): streaming passthrough for non-streaming clients

When a client sends stream: false to the Antigravity executor
(Gemini models), OmniRoute buffered the entire SSE stream before
responding. Long-thinking models exceeded the 120s timeout.

Remove hardcoded SSE_COLLECT_TIMEOUT_MS. Extract shared
createCreditsExtractionTransform with 16KB buffer cap and abort
handling for client disconnect. Add parseSSEToGeminiResponse for
the non-streaming drain path. Fix hasGeminiTerminalFinishReason
to check top-level candidates (no response wrapper). Add signal
null guards for credits retry path. Return 499 on early abort
instead of piping cancelled body.

Also remove duplicate SKILLS_SANDBOX_RUNTIME from .env.example
and clarify .artifacts/ vs _artifacts/ in .gitignore.

Signed-off-by: Minxi Hou <houminxi@gmail.com>

* refactor(antigravity): extract streaming passthrough to module (file-size cap)

#7408 added the non-streaming SSE pass-through (createCreditsExtractionTransform
plus its two call sites: the credits-retry path and the main non-streaming
path) inline in antigravity.ts, growing it to 1806 lines. Combined with two
other authorized PRs touching the same file (#6979 +11, #7290 +30), the
projected total exceeds the frozen file-size gate (1813).

Extract the new streaming-passthrough logic verbatim into
open-sse/executors/antigravity/streamingPassthrough.ts
(createCreditsExtractionTransform + a new buildSsePassthroughResult that
deduplicates the two near-identical call sites), following the existing
sseCollect.ts submodule pattern -- pure, no host state, no fetch/auth.
antigravity.ts keeps a thin wrapper for createCreditsExtractionTransform
(same public signature the existing unit tests import) that injects
updateAntigravityRemainingCredits so the two modules don't import each
other.

No behavior change: same abort handling, same 499-on-early-disconnect,
same 16KB credits sliding-window cap. antigravity.ts: 1806 -> 1693 lines
(under the 1755 pre-PR baseline, with margin). New module: 176 lines
(cap 800).

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

* refactor(antigravity): split incremental parser + move new tests to own file (file-size caps)

Two remaining frozen file-size violations from #7408, resolved by
extraction/move with zero behavior or assert changes:

- open-sse/handlers/sseParser.ts (979 > frozen 830): the PR appended
  parseSSEToGeminiResponse (+153, the Gemini buffered-SSE ->
  chat.completion parser). Moved verbatim to
  open-sse/handlers/sseParser/geminiResponse.ts, following the handlers
  submodule pattern (chatCore/, responseSanitizer/). sseParser.ts is now
  byte-identical to its pre-PR content (825 lines; PR delta 0). Importers
  (chatCore/nonStreamingSse.ts, tests) point at the new module.

- tests/unit/executor-antigravity.test.ts (1058 > testFrozen 942): the
  PR's new streaming-passthrough tests moved verbatim (same tests, same
  asserts) to tests/unit/antigravity-streaming-passthrough.test.ts:
  the 3 createCreditsExtractionTransform tests plus the non-streaming
  passthrough drain test ("auto-retries short 429 ... collects SSE for
  non-stream clients"), which the PR rewired onto the new raw-SSE path.
  The frozen file drops to 888 lines (below its pre-PR 941).

New files: geminiResponse.ts 156 lines, passthrough test 202 lines (caps
800). Also fixes the stale sseParser.ts path in collectStreamToResponse's
deprecation note.

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

* refactor(antigravity): decompose execute + gemini parser below complexity gate

executeOnce() (complexity 127, 436 lines) and parseSSEToGeminiResponse()
(complexity 39, 117 lines) were both over the check-complexity.mjs gate
(complexity>15, max-lines-per-function>80). Decomposed each into small
named helpers, no behavior change:

- geminiResponse.ts: split into pure per-concern functions (markdown
  shortcut, candidate-parts walk, finishReason, usageMetadata, final
  response assembly).
- antigravity.ts: extracted the per-url-index attempt pipeline
  (runAntigravityAttempt, handleAntigravityRateLimit,
  tryResolveRetryFromErrorBody, shouldAutoRetryTransient) and moved the
  request/result-building helpers (send, credits-retry, embed-retry,
  non-streaming/streaming result builders) into a new
  antigravity/executeAttempt.ts submodule, mirroring the existing
  streamingPassthrough.ts/sseCollect.ts pattern. Also fixes the
  antigravity.ts file-size cap (was pushed to 2084 lines > 1813 frozen
  ceiling by the decomposition itself; now 1428).

check-complexity.mjs: 2054 violations (baseline 2058) — net improvement.
execute/executeOnce/parseSSEToGeminiResponse no longer appear with
ruleId complexity or max-lines-per-function.

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

* Merge branch 'release/v3.8.49' into fix/antigravity-streaming-passthrough

Resolves conflict in open-sse/executors/antigravity.ts between this
branch's streaming-passthrough decomposition and #7290's fallback-chain
decomposition (already merged into release/v3.8.49) — both sides added
imports from the same new antigravity/ submodule files, kept both.

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

* fix(antigravity): keep buffered JSON contract for non-streaming callers

#3786's Pro-family fallback-chain retry loop (execute()) calls executeOnce()
per candidate and inspects result.response directly, expecting a
synthesized chat.completion JSON body on success. The streaming-passthrough
migration made ALL non-streaming (stream: false) responses a raw SSE
pass-through instead, so a successful retry candidate's response.json()
threw ("data: {...}" is not valid JSON) — breaking the fallback chain
(tests/unit/agy-pro-fallback-chain-3786.test.ts, 3 of 13 red).

Route non-streaming (stream: false) responses back through
collectStreamToResponse (buffered collect-to-JSON), which already uses
FETCH_TIMEOUT_MS with no hardcoded 120s ceiling, so long-thinking models
are not penalized. Passthrough is reserved for actual streaming clients
(stream: true), which was the PR's real target scenario.

Extracted the branch into buildAntigravityAttemptResult() to keep
runAntigravityAttempt under the 80-line ratchet cap.

Co-authored-by: diegosouzapw <8016841+diegosouzapw@users.noreply.github.com>

---------

Signed-off-by: Minxi Hou <houminxi@gmail.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <8016841+diegosouzapw@users.noreply.github.com>
Co-authored-by: growab <nekron@icloud.com>
Co-authored-by: HouMinXi <1000+HouMinXi@users.noreply.github.com>
Co-authored-by: HouMinXi <19586012+HouMinXi@users.noreply.github.com>
2026-07-18 21:19:20 -03:00

434 lines
17 KiB
TypeScript

import test from "node:test";
import assert from "node:assert/strict";
const { parseSSEToOpenAIResponse, parseSSEToClaudeResponse, parseSSEToResponsesOutput } =
await import("../../open-sse/handlers/sseParser.ts");
const { parseSSEToGeminiResponse } =
await import("../../open-sse/handlers/sseParser/geminiResponse.ts");
test("parseSSEToOpenAIResponse parses a single SSE event with a done marker", () => {
const rawSSE = [
'data: {"id":"chatcmpl_1","model":"gpt-4o-mini","choices":[{"index":0,"delta":{"content":"hello"},"finish_reason":"stop"}]}',
"",
"data: [DONE]",
"",
].join("\n");
const parsed = parseSSEToOpenAIResponse(rawSSE, "fallback-model");
assert.equal(parsed.id, "chatcmpl_1");
assert.equal(parsed.model, "gpt-4o-mini");
assert.equal(parsed.choices[0].message.content, "hello");
assert.equal(parsed.choices[0].finish_reason, "stop");
});
test("parseSSEToOpenAIResponse concatenates content, reasoning, and usage from multiple events", () => {
const rawSSE = [
'data: {"id":"chatcmpl_2","choices":[{"index":0,"delta":{"reasoning_content":"think "}}]}',
'data: {"id":"chatcmpl_2","choices":[{"index":0,"delta":{"content":"hel"}}]}',
'data: {"id":"chatcmpl_2","choices":[{"index":0,"delta":{"content":"lo"},"finish_reason":"stop"}],"usage":{"prompt_tokens":5,"completion_tokens":2,"total_tokens":7}}',
].join("\n");
const parsed = parseSSEToOpenAIResponse(rawSSE, "fallback-model");
assert.equal(parsed.choices[0].message.content, "hello");
assert.equal(parsed.choices[0].message.reasoning_content, "think");
assert.deepEqual(parsed.usage, {
prompt_tokens: 5,
completion_tokens: 2,
total_tokens: 7,
});
});
test("parseSSEToOpenAIResponse ignores malformed and non-data lines", () => {
const rawSSE = [
"event: message",
"id: abc-1",
"not-data: ignored",
"data: not-json",
'data: {"id":"chatcmpl_3","choices":[{"index":0,"delta":{"content":"ok"},"finish_reason":"stop"}]}',
].join("\n");
const parsed = parseSSEToOpenAIResponse(rawSSE, "fallback-model");
assert.equal(parsed.id, "chatcmpl_3");
assert.equal(parsed.choices[0].message.content, "ok");
});
test("parseSSEToOpenAIResponse preserves UTF-8 multibyte content", () => {
const rawSSE = [
'data: {"id":"chatcmpl_utf8","choices":[{"index":0,"delta":{"content":"Olá "}}]}',
'data: {"id":"chatcmpl_utf8","choices":[{"index":0,"delta":{"content":"世界"},"finish_reason":"stop"}]}',
].join("\n");
const parsed = parseSSEToOpenAIResponse(rawSSE, "fallback-model");
assert.equal(parsed.choices[0].message.content, "Olá 世界");
});
test("parseSSEToOpenAIResponse ignores Responses API SSE payloads", () => {
const rawSSE = [
'data: {"type":"response.created","response":{"id":"resp_1","model":"gpt-5.3-codex","status":"in_progress","output":[]}}',
'data: {"type":"response.output_text.delta","output_index":0,"delta":"Brasilia"}',
'data: {"type":"response.completed","response":{"id":"resp_1","object":"response","model":"gpt-5.3-codex","status":"completed","output":[{"type":"message","role":"assistant","content":[{"type":"output_text","text":"Brasilia"}]}]}}',
"data: [DONE]",
].join("\n");
const parsed = parseSSEToOpenAIResponse(rawSSE, "fallback-model");
assert.equal(parsed, null);
});
test("parseSSEToClaudeResponse parses text, thinking, tool_use, and usage events", () => {
const rawSSE = [
"event: message_start",
'data: {"type":"message_start","message":{"id":"msg_1","model":"claude-3-5-sonnet","role":"assistant","usage":{"input_tokens":10}}}',
"",
"event: content_block_start",
'data: {"type":"content_block_start","index":0,"content_block":{"type":"thinking","thinking":"step 1","signature":"sig-1"}}',
"",
"event: content_block_delta",
'data: {"type":"content_block_delta","index":1,"delta":{"text":"Hello"}}',
"",
"event: content_block_start",
'data: {"type":"content_block_start","index":2,"content_block":{"type":"tool_use","id":"toolu_1","name":"lookup","input":{}}}',
"",
"event: content_block_delta",
'data: {"type":"content_block_delta","index":2,"delta":{"type":"input_json_delta","partial_json":"{\\"q\\":\\"docs\\"}"}}',
"",
"event: message_delta",
'data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":"END"},"usage":{"output_tokens":4}}',
"",
].join("\n");
const parsed = parseSSEToClaudeResponse(rawSSE, "fallback-model");
assert.equal(parsed.id, "msg_1");
assert.equal(parsed.model, "claude-3-5-sonnet");
assert.equal((parsed.content[0] as { type: string }).type, "thinking");
assert.equal((parsed.content[0] as { thinking: string }).thinking, "step 1");
assert.equal((parsed.content[0] as { signature: string }).signature, "sig-1");
assert.equal((parsed.content[1] as { text: string }).text, "Hello");
assert.equal((parsed.content[2] as { type: string }).type, "tool_use");
assert.deepEqual((parsed.content[2] as { input: unknown }).input, { q: "docs" });
assert.equal(parsed.stop_reason, "tool_use");
assert.equal(parsed.stop_sequence, "END");
assert.deepEqual(parsed.usage, { input_tokens: 10, output_tokens: 4 });
});
test("parseSSEToClaudeResponse tolerates event-only types and missing blank separators", () => {
const rawSSE = [
"event: message_start",
'data: {"message":{"id":"msg_event_fallback","model":"claude-sonnet-4-6","role":"assistant","usage":{"input_tokens":3}}}',
"event: content_block_delta",
'data: {"index":0,"delta":{"text":"event fallback ok"}}',
"event: message_delta",
'data: {"delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":2}}',
"event: message_stop",
"data: {}",
].join("\n");
const parsed = parseSSEToClaudeResponse(rawSSE, "fallback-model");
assert.equal(parsed.id, "msg_event_fallback");
assert.equal(parsed.model, "claude-sonnet-4-6");
assert.equal((parsed.content[0] as { text: string }).text, "event fallback ok");
assert.deepEqual(parsed.usage, { input_tokens: 3, output_tokens: 2 });
});
test("parseSSEToClaudeResponse merges signature_delta into an existing thinking block", () => {
const rawSSE = [
"event: message_start",
'data: {"type":"message_start","message":{"id":"msg_thinking_sig","model":"claude-sonnet-4-6","role":"assistant"}}',
"",
"event: content_block_delta",
'data: {"type":"content_block_delta","index":0,"delta":{"type":"thinking_delta","thinking":"first "}}',
"",
"event: content_block_delta",
'data: {"type":"content_block_delta","index":0,"delta":{"type":"thinking_delta","thinking":"second"}}',
"",
"event: content_block_delta",
'data: {"type":"content_block_delta","index":0,"delta":{"type":"signature_delta","signature":"sig-1"}}',
"",
].join("\n");
const parsed = parseSSEToClaudeResponse(rawSSE, "fallback-model");
assert.equal((parsed.content[0] as { type: string }).type, "thinking");
assert.equal((parsed.content[0] as { thinking: string }).thinking, "first second");
assert.equal((parsed.content[0] as { signature: string }).signature, "sig-1");
});
test("parseSSEToClaudeResponse preserves signature_delta when it arrives before thinking_delta", () => {
const rawSSE = [
"event: message_start",
'data: {"type":"message_start","message":{"id":"msg_sig_first","model":"claude-sonnet-4-6","role":"assistant"}}',
"",
"event: content_block_delta",
'data: {"type":"content_block_delta","index":0,"delta":{"type":"signature_delta","signature":"sig-before"}}',
"",
"event: content_block_delta",
'data: {"type":"content_block_delta","index":0,"delta":{"type":"thinking_delta","thinking":"later thinking"}}',
"",
].join("\n");
const parsed = parseSSEToClaudeResponse(rawSSE, "fallback-model");
assert.equal((parsed.content[0] as { type: string }).type, "thinking");
assert.equal((parsed.content[0] as { thinking: string }).thinking, "later thinking");
assert.equal((parsed.content[0] as { signature: string }).signature, "sig-before");
});
test("parseSSEToClaudeResponse ignores malformed payloads and returns null when nothing valid remains", () => {
const parsed = parseSSEToClaudeResponse(
["event: content_block_delta", "data: not-json", "", "data: [DONE]"].join("\n"),
"fallback-model"
);
assert.equal(parsed, null);
});
test("parseSSEToClaudeResponse ignores Responses API SSE payloads", () => {
const rawSSE = [
"event: response.created",
'data: {"type":"response.created","response":{"id":"resp_1","model":"gpt-5.3-codex","status":"in_progress","output":[]}}',
"",
"event: response.output_text.delta",
'data: {"type":"response.output_text.delta","output_index":0,"delta":"Brasilia"}',
"",
"data: [DONE]",
].join("\n");
const parsed = parseSSEToClaudeResponse(rawSSE, "fallback-model");
assert.equal(parsed, null);
});
test("parseSSEToResponsesOutput prefers response.completed payloads when available", () => {
const rawSSE = [
'data: {"type":"response.created","response":{"id":"resp_1","model":"gpt-4.1","status":"in_progress","output":[]}}',
'data: {"type":"response.completed","response":{"id":"resp_1","model":"gpt-4.1","status":"completed","output":[{"type":"message"}],"usage":{"input_tokens":3}}}',
"data: [DONE]",
].join("\n");
const parsed = parseSSEToResponsesOutput(rawSSE, "fallback-model");
assert.equal(parsed.id, "resp_1");
assert.equal(parsed.status, "completed");
assert.equal(parsed.output.length, 1);
assert.deepEqual(parsed.usage, { input_tokens: 3 });
});
test("parseSSEToResponsesOutput falls back to the latest response object when completion is absent", () => {
const rawSSE = [
'data: {"type":"response.in_progress","response":{"id":"resp_2","model":"gpt-4.1","status":"in_progress","output":[],"metadata":{"source":"sse"}}}',
].join("\n");
const parsed = parseSSEToResponsesOutput(rawSSE, "fallback-model");
assert.equal(parsed.id, "resp_2");
assert.equal(parsed.model, "gpt-4.1");
assert.equal(parsed.status, "in_progress");
assert.deepEqual(parsed.metadata, { source: "sse" });
});
test("parseSSEToResponsesOutput handles large payloads without truncation", () => {
const largeText = "A".repeat(10_000);
const rawSSE = `data: ${JSON.stringify({
type: "response.completed",
response: {
id: "resp_big",
object: "response",
model: "gpt-4.1",
status: "completed",
output: [{ type: "message", content: [{ type: "output_text", text: largeText }] }],
},
})}`;
const parsed = parseSSEToResponsesOutput(rawSSE, "fallback-model");
assert.equal(parsed.output[0].content[0].text.length, 10_000);
});
test("parseSSEToResponsesOutput treats response.cancelled as terminal and reconstructs output from deltas", () => {
const rawSSE = [
"event: response.created",
'data: {"type":"response.created","response":{"id":"resp_cancelled","model":"gpt-5.3-codex","status":"in_progress","output":[]}}',
"",
"event: response.output_item.added",
'data: {"type":"response.output_item.added","output_index":0,"item":{"id":"msg_1","type":"message","role":"assistant","content":[{"type":"output_text","text":""}]}}',
"",
"event: response.output_text.delta",
'data: {"type":"response.output_text.delta","item_id":"msg_1","output_index":0,"content_index":0,"delta":"Hel"}',
"",
"event: response.output_text.delta",
'data: {"type":"response.output_text.delta","item_id":"msg_1","output_index":0,"content_index":0,"delta":"lo"}',
"",
"event: response.cancelled",
'data: {"type":"response.cancelled","response":{"id":"resp_cancelled","model":"gpt-5.3-codex","status":"cancelled","output":[],"usage":{"input_tokens":3}}}',
"",
"data: [DONE]",
].join("\n");
const parsed = parseSSEToResponsesOutput(rawSSE, "fallback-model");
assert.equal(parsed.id, "resp_cancelled");
assert.equal(parsed.status, "cancelled");
assert.equal(parsed.output[0].type, "message");
assert.equal(parsed.output[0].content[0].text, "Hello");
assert.deepEqual(parsed.usage, { input_tokens: 3 });
});
test("parseSSEToResponsesOutput treats response.canceled as terminal and reconstructs message text without added item", () => {
const rawSSE = [
'data: {"type":"response.output_text.delta","output_index":0,"content_index":0,"delta":"Bye"}',
'data: {"type":"response.canceled","response":{"id":"resp_canceled","model":"gpt-5.3-codex","output":[]}}',
"data: [DONE]",
].join("\n");
const parsed = parseSSEToResponsesOutput(rawSSE, "fallback-model");
assert.equal(parsed.id, "resp_canceled");
assert.equal(parsed.status, "canceled");
assert.equal(parsed.output[0].type, "message");
assert.equal(parsed.output[0].content[0].text, "Bye");
});
test("parseSSEToOpenAIResponse deduplicates repeated tool call snapshots", () => {
const args = JSON.stringify({ command: "find /tmp -name test.txt" });
const first = {
id: "chatcmpl_tool",
choices: [
{
index: 0,
delta: {
tool_calls: [
{
index: 0,
id: "call_1",
type: "function",
function: { name: "shell", arguments: args },
},
],
},
},
],
};
const second = {
id: "chatcmpl_tool",
choices: [
{
index: 0,
delta: { tool_calls: [{ index: 0, function: { arguments: args } }] },
finish_reason: "tool_calls",
},
],
};
const rawSSE = [
`data: ${JSON.stringify(first)}`,
`data: ${JSON.stringify(second)}`,
"data: [DONE]",
].join("\n");
const parsed = parseSSEToOpenAIResponse(rawSSE, "fallback-model");
const toolCall = parsed.choices[0].message.tool_calls[0];
assert.equal(toolCall.function.arguments, args);
assert.equal(JSON.parse(toolCall.function.arguments).command, "find /tmp -name test.txt");
});
// ---------------------------------------------------------------------------
// parseSSEToGeminiResponse
// ---------------------------------------------------------------------------
test("parseSSEToGeminiResponse extracts text content from candidate parts", () => {
const rawSSE = [
'data: {"response":{"candidates":[{"content":{"parts":[{"text":"Hello "}]}}]}}',
'data: {"response":{"candidates":[{"content":{"parts":[{"text":"world"}]},"finishReason":"STOP"}],"usageMetadata":{"promptTokenCount":5,"candidatesTokenCount":3,"totalTokenCount":8}}}',
].join("\n");
const parsed = parseSSEToGeminiResponse(rawSSE, "gemini-2.5-flash");
assert.ok(parsed);
assert.equal(parsed.object, "chat.completion");
assert.equal(parsed.choices[0].message.content, "Hello world");
assert.equal(parsed.choices[0].finish_reason, "stop");
assert.deepEqual(parsed.usage, {
prompt_tokens: 5,
completion_tokens: 3,
total_tokens: 8,
});
});
test("parseSSEToGeminiResponse handles markdown shortcut format", () => {
const rawSSE = [
'data: {"markdown":"Hello "}',
'data: {"markdown":"world"}',
'data: {"response":{"candidates":[{"finishReason":"STOP"}]}}',
].join("\n");
const parsed = parseSSEToGeminiResponse(rawSSE, "gemini-2.5-flash");
assert.ok(parsed);
assert.equal(parsed.choices[0].message.content, "Hello world");
assert.equal(parsed.choices[0].finish_reason, "stop");
});
test("parseSSEToGeminiResponse extracts tool calls from textual format", () => {
const rawSSE = [
`data: ${JSON.stringify({
response: {
candidates: [
{
content: {
parts: [
{
text: '[Tool call: search_files]\nArguments: {"path":"/tmp"}',
},
],
},
finishReason: "STOP",
},
],
},
})}`,
].join("\n");
const parsed = parseSSEToGeminiResponse(rawSSE, "gemini-3.5-flash-low");
assert.ok(parsed);
assert.equal(parsed.choices[0].finish_reason, "tool_calls");
const toolCalls = parsed.choices[0].message.tool_calls;
assert.equal(toolCalls.length, 1);
assert.equal(toolCalls[0].function.name, "search_files");
assert.deepEqual(JSON.parse(toolCalls[0].function.arguments), { path: "/tmp" });
});
test("parseSSEToGeminiResponse returns null for empty or non-content SSE", () => {
assert.equal(parseSSEToGeminiResponse("", "model"), null);
assert.equal(parseSSEToGeminiResponse("data: [DONE]\n", "model"), null);
assert.equal(parseSSEToGeminiResponse("event: ping\n", "model"), null);
});
test("parseSSEToGeminiResponse ignores thought/thoughtSignature parts", () => {
const rawSSE = [
`data: ${JSON.stringify({
response: {
candidates: [
{
content: {
parts: [{ text: "internal reasoning", thought: true }, { text: "visible answer" }],
},
finishReason: "STOP",
},
],
},
})}`,
].join("\n");
const parsed = parseSSEToGeminiResponse(rawSSE, "model");
assert.ok(parsed);
assert.equal(parsed.choices[0].message.content, "visible answer");
});