Files
OmniRoute/tests/unit/deepseek-web-tools-variants.test.ts
Diego Rodrigues de Sa e Souza 19d91d82e2 Release v3.8.34 (#4614)
* chore(release): open v3.8.34 development cycle

* chore(quality): release-green pre-flight validator + nightly signal (C+D) (#4622)

C — scripts/quality/validate-release-green.mjs (npm run check:release-green):
reproduces the release-equivalent validation (typecheck, eslint, db-rules,
public-creds, full unit, vitest, ratchets, optional --with-build package-artifact)
against the current working tree and classifies each red as HARD (real defect,
exit 1) vs DRIFT (ratchet — reported, never affects exit / never blocks). Pure
helpers exported + orchestration behind a direct-run guard; unit-tested.

D — .github/workflows/nightly-release-green.yml: runs C on the active release
branch nightly (and on workflow_dispatch) and opens/updates a single tracking
issue on HARD failures. Never a required check, never touches a contributor PR.

Closes the gap where the full gate (ci.yml) only ran on the release PR, so reds
accrued silently on release/** and surfaced in 40-min layers at release time.
Non-blocking by construction; drift is the maintainer's to rebaseline at release.

Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br>

* fix(providers): show revealed connection API keys (#4583)

Integrated into release/v3.8.34

* fix(resilience): respect upstream retry hint toggle (#4585)

Integrated into release/v3.8.34

* feat(settings): expose stream recovery feature flags (#4586)

Integrated into release/v3.8.34

* fix(logs): make active request stale sweep configurable (#4599)

Integrated into release/v3.8.34

* fix(plugin): auto-prefix providerId with 'opencode-' for OC 1.17.8+ native gate (#4527)

Integrated into release/v3.8.34 (supersedes #4445)

* fix(models): treat unknown output caps as unset (#4584)

Integrated into release/v3.8.34

* fix(executors): strip temperature for GitHub Copilot gpt-5.4 family (#4564)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(oauth): update Qwen OAuth URLs from chat.qwen.ai to qwen.ai (#4561)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(api/settings): prevent cached /api/settings responses (port from 9router#951) (#4566)

Integrated into release/v3.8.34 (rebuilt onto tip)

* feat(audio): MiniMax T2A v2 TTS dispatch in audioSpeech (port #1043) (#4553)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(dashboard): surface manual config CTA when Open Claw CLI auto-detect fails (#4562)

Integrated into release/v3.8.34 (rebuilt onto tip)

* feat(providers): optional model ID for custom API-key validation (#4555)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(cli): align data dir and env loading with runtime (#4607)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(quota): expose Bailian quota windows (#4610)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix: retain provider cooldowns for configured max window (#4588)

Integrated into release/v3.8.34 (rebuilt — bundled commits stripped)

* fix: reject invalid provider cooldown bounds (#4589)

Integrated into release/v3.8.34 (rebuilt — bundled commits stripped)

* fix: preserve production combo metrics on shadow eviction (#4590)

Integrated into release/v3.8.34 (rebuilt — bundled commits stripped)

* fix(stream): estimate input tokens when upstream reports prompt_tokens=0 (#4615)

Integrated into release/v3.8.34 (rebuilt onto tip)

* fix(catalog): shorten no-thinking gateway prefix to no-think/ (#4525)

Integrated into release/v3.8.34 (rebuilt — kept only the prefix rename, dropped stale-base reverts)

* fix(relay): apply IP rate limit to bifrost sidecar (#4593)

Integrated into release/v3.8.34 (rebuilt onto tip; merge before #4612)

* fix(bifrost): finalize SSE relay usage after stream (#4612)

Integrated into release/v3.8.34 (rebuilt + reconciled with #4593)

* feat(compression): per-request `x-omniroute-compression` header (Phase 3) (#4645)

* docs(compression): Phase 3 per-request header design spec

Approved brainstorming output for the x-omniroute-compression header:
header-first precedence, name-first combo matching (Decision A), explicit
value bypasses auto-trigger (Decision B), DerivedPlan.source, and the
X-OmniRoute-Compression response header.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(compression): Phase 3 per-request header implementation plan

4-task TDD plan (resolver header-first + source, parser, chatCore wiring +
response header, docs/file-size) with full code and exact commands.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(compression): header-first resolver + plan source (Phase 3 core)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(compression): resolveCompressionHeader parser (Phase 3)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* feat(compression): wire x-omniroute-compression header + response header (Phase 3)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* refactor(compression): extract plan-resolution leaf (planResolution.ts) under size cap (Phase 3)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(compression): document x-omniroute-compression header (Phase 3)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(compression): harden named-combo map + trim engine: header id (Phase 3 review)

Addresses gemini-code-assist review on #4645:
- Extract buildNamedComboLookup (pure) so a blank/whitespace/null combo name
  contributes only its id key (no '' key, no throw that disables all combos).
- Trim the engine:<id> header value so 'engine: rtk' resolves.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix: exclude exhausted connections from auto scoring (#4592)

Integrated into release/v3.8.34 (rebuilt + opt-in gate fix)

* fix(dashboard): memoize compatible provider groups (#4613)

Integrated into release/v3.8.34 (rebuilt + test added)

* fix(dashboard): isolate quota widget refresh clock (#4611)

Integrated into release/v3.8.34 (rebuilt + jsdom test)

* fix(dashboard): gate topology side effects behind widget visibility (#4606)

Integrated into release/v3.8.34 (rebuilt + jsdom test)

* fix(dashboard): keep play_arrow spinning on provider Test All buttons (#4563)

Integrated into release/v3.8.34 (rebuilt onto tip; UI-cosmetic per owner)

* fix(db): schedule retention cleanup + fix cleanup table/column names (extracted from #4428) (#4691)

Integrated into release/v3.8.34 (cleanup core extracted from #4428, credit @oyi77)

* fix(telemetry): back off live-WS event forwarding when the sidecar is unreachable (#4604) (#4687)

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(api): serve GET /v1/models/{model} as JSON, not the HTML dashboard (#4674) (#4677)

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* feat(opencode): add go deepseek reasoning variants (#4647)

Integrated into release/v3.8.34

* fix(executors): robust deepseek-web tool-call parsing and agentic context retention (#4644)

Integrated into release/v3.8.34

* fix(cli): authenticate `omniroute logs` and honor active context (#4638)

Integrated into release/v3.8.34 (authored by Rahul Sharma, AI co-author trailer stripped per project policy)

* fix(proxy): apply pipelining:0 + connections cap to the direct dispatcher (#4580) (#4684)

Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>

* fix(executors): Firecrawl web_fetch 500 with include_metadata=true (#4692)

Integrated into release/v3.8.34

* fix(routing): include all noAuth models in auto-combos + add reka-flash + best-free template (#4621)

Integrated into release/v3.8.34 (dead getFirstRegistryModelId dropped, rebuilt onto tip)

* fix(dashboard): gate home topology live-WS networking (#4596) (#4618)

Integrated into release/v3.8.34 (adapted onto #4606's extracted topology section: default-hidden flip + enabled gate on useLiveDashboard)

* fix(cli): align `omniroute` env loading with the runtime data dir (#4597) (#4619)

Integrated into release/v3.8.34 (data-dir.mjs refactor reconciled with #4607; loadEnvFile aligned to getDefaultDataDir)

* chore(quality): reconcile file-size baseline for #4644 (deepseek-web.ts 1117->1125) (#4695)

file-size reconcile for #4644

* Support quota scraping for OpenCode Go and Ollama Cloud (#4642)

Integrated into release/v3.8.34 (Ollama Cloud + OpenCode Go dashboard quota scraping; rebuilt onto tip, gates green: typecheck/public-creds/file-size/lint/docs-sync + 31 tests)

* feat(executors): land M365 Copilot pure framing + connection helpers (#4042) (#4696)

Land M365 pure modules ahead of draft #4400

* deps: bump production + development groups; migrate js-yaml to v5 ESM (#4697)

Incorporates Dependabot #4667 + #4668 + js-yaml v5 ESM migration into release/v3.8.34

* fix: noAuth provider validation + kimi executor routing (#4699)

Integrated into release/v3.8.34 (noAuth in NOAUTH_PROVIDERS dynamic check + remove misrouted kimi web alias; 9 tests)

* refactor(imageGeneration): extract 8 provider families to co-located files (#4609)

Integrated into release/v3.8.34 (extraction completed: added missing imports/exports per module, main imports handlers locally; 145 image-gen tests pass, typecheck/cycles/file-size green)

* chore(release): v3.8.34 — finalize changelog, rebaseline drift, fix release-green reds

- Finalize CHANGELOG [3.8.34] (43 bullets, full contributor attribution) + seed i18n mirrors
- Rebaseline inherited cycle drift surfaced by release-green pre-flight: eslint warnings
  3900->3907, cognitive-complexity 797->801 (release-finalize touches no prod code; all
  drift is from this cycle's contributor merges)
- fix(providers): keep reka-flash-3 as the Reka provider default. #4621 inserted reka-flash
  at the head of the model list, silently changing the default from reka-flash-3 (the
  free-tier model) to reka-flash; reorder so reka-flash-3 stays default, reka-flash retained.
- test: align provider-models-config / provider-models-route / web-cookie-providers-new with
  #4621 (reka-flash now in the Reka catalog) and #4699 (the `kimi` API-key provider correctly
  falls through to DefaultExecutor instead of KimiWebExecutor)
- chore(quality): allowlist the COMPRESSION_GUIDE doc name in check-fabricated-docs
  (false-positive env-var match; docs/compression/COMPRESSION_GUIDE.md exists)

* fix(release-green): resolve release-PR full-CI reds for v3.8.34

Surfaced only on the release PR (these gates don't run on PR->release fast-gates):

- fix(quota): complete HTML-comment sanitization in opencodeOllamaUsage SSR reset-time
  parsing — strip any <!--...--> generically instead of the two literal React hydration
  markers, so no partial "<!--" can survive (CodeQL js/incomplete-multi-character-
  sanitization, HIGH, introduced by #4642). Regression test added.
- test(codex): correct the Codex-fingerprint body key order assertion to match the
  canonical bodyFieldOrder (prompt_cache_key precedes include); #4584 flipped the two
  and integration tests don't run on fast-gates so it never executed until the release PR.
- chore(quality): rebaseline inherited cycle drift surfaced by full CI —
  zizmorFindings 152->155 (+3 unpinned-uses in nightly-release-green.yml from #4622,
  same @vN convention as ci.yml) and openapiCoverage.pct 38.4->37.8 (-0.6, contributor
  routes added faster than openapi docs). Release-finalize touches no prod routes.

* fix(release-green): complete CodeQL sanitization + rebaseline complexity drift

- fix(quota): handle unterminated HTML comments in opencodeOllamaUsage SSR reset-time
  parsing — the `(?:-->|$)` arm consumes a trailing "<!--" with no closing "-->", so no
  partial "<!--" can survive (CodeQL js/incomplete-multi-character-sanitization persisted
  with the plain <!--...--> form because an unclosed comment could still leave "<!--").
- chore(quality): rebaseline cyclomatic complexity 1915->1916 (+1) — inherited v3.8.34
  cycle drift (contributor feature branches); check:complexity does not run on PR->release
  fast-gates so it surfaced only on the release PR. Release-finalize adds 0 complexity
  (measured 1916 with/without the regex tweak). dead-code/cognitive/type-coverage/
  compression-budget/codeql ratchets all pass.

---------

Co-authored-by: Diego Rodrigues de Sa e Souza <diego.souza@cdwasolutions.com.br>
Co-authored-by: Randi <55005611+rdself@users.noreply.github.com>
Co-authored-by: Hernan Javier Ardila Sanchez <hjasgr@gmail.com>
Co-authored-by: KooshaPari <42529354+KooshaPari@users.noreply.github.com>
Co-authored-by: Abhishek Divekar <adivekar@utexas.edu>
Co-authored-by: Rahul sharma <sharmaR0810@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Diego Rodrigues de Sa e Souza <souzamiriamrodrigues790@gmail.com>
Co-authored-by: Ronald Estacion <DevEstacion@users.noreply.github.com>
Co-authored-by: Igor <60442260+BugsBag@users.noreply.github.com>
Co-authored-by: Oonishi <275808243+ponkcore@users.noreply.github.com>
Co-authored-by: Paijo <14921983+oyi77@users.noreply.github.com>
Co-authored-by: Jan Leon <Jan.gaschler@gmail.com>
2026-06-23 03:08:29 -03:00

226 lines
10 KiB
TypeScript

import { describe, test } from "node:test";
import assert from "node:assert/strict";
import {
parseDeepSeekToolCalls,
serializeDeepSeekToolPrompt,
buildToolConversationPrompt,
} from "../../open-sse/translator/deepseekWebTools.ts";
// chat.deepseek.com emits tool invocations in many ad-hoc shapes. The deepseek-specific
// parser must recognize all of them, recover the real tool name/arguments, and preserve
// any surrounding natural-language text so it can still be streamed to the client.
const TOOLS = [
{ type: "function", function: { name: "todowrite", description: "Write todos" } },
{ type: "function", function: { name: "bash", description: "Run a shell command" } },
{ type: "function", function: { name: "write", description: "Write a file" } },
{
type: "function",
function: {
name: "get_weather",
parameters: { type: "object", properties: { city: { type: "string" } } },
},
},
];
function firstCall(text: string) {
const { toolCalls } = parseDeepSeekToolCalls(text, "call", TOOLS);
assert.ok(toolCalls && toolCalls.length >= 1, `expected a tool call for: ${text.slice(0, 60)}`);
return toolCalls[0];
}
describe("deepseekWebTools — variants", () => {
test("Ex1: <tool:todowrite>{json} </tool> — name in tag suffix, body is the arguments", () => {
const text = `I'll write a script.\n\n<tool:todowrite>\n{"todos": [{"content": "a", "status": "in_progress", "priority": "high"}]}\n</tool>`;
const { content, toolCalls } = parseDeepSeekToolCalls(text, "call", TOOLS);
assert.equal(toolCalls?.length, 1);
assert.equal(toolCalls![0].function.name, "todowrite");
assert.deepEqual(JSON.parse(toolCalls![0].function.arguments), {
todos: [{ content: "a", status: "in_progress", priority: "high" }],
});
assert.ok(content.includes("I'll write a script."), "surrounding text preserved");
assert.ok(!content.includes("<tool"), "tool block stripped");
});
test("Ex3: <tool_call> with id/type/params shape", () => {
const text = `I'll draft a plan.\n<tool_call>\n{"id": "todo_1", "type": "todo", "params": {"todos": [{"content": "x", "status": "pending", "priority": "high"}]}}\n</tool_call>`;
const call = firstCall(text);
assert.equal(call.function.name, "todowrite", "type 'todo' fuzzy-resolves to todowrite");
assert.deepEqual(JSON.parse(call.function.arguments), {
todos: [{ content: "x", status: "pending", priority: "high" }],
});
});
test("Ex5: nested <tool><tool>{json}</tool> — inner canonical call", () => {
const text = `<tool>\n<tool>{"name": "todowrite", "arguments": {"todos": [{"content": "y", "status": "pending", "priority": "high"}]}}</tool>`;
const { content, toolCalls } = parseDeepSeekToolCalls(text, "call", TOOLS);
assert.equal(toolCalls?.length, 1);
assert.equal(toolCalls![0].function.name, "todowrite");
assert.ok(!content.includes("<tool"), "stray/nested tool tags stripped");
});
test("Ex6: <tool:bash>{command} </tool> — body is the arguments payload", () => {
const text = `I'll create a script.\n\n<tool:bash>\n{"command": "echo hi"}\n</tool>`;
const call = firstCall(text);
assert.equal(call.function.name, "bash");
assert.deepEqual(JSON.parse(call.function.arguments), { command: "echo hi" });
});
test('Ex7: <tool id="1"><name>write</name><arguments>{json}</arguments></tool>', () => {
const text = `I'll create a script.\n<tool id="1">\n <name>write</name>\n <arguments>\n {"filePath": "/tmp/train.py", "content": "print(1)"}\n </arguments>\n</tool>`;
const call = firstCall(text);
assert.equal(call.function.name, "write");
assert.deepEqual(JSON.parse(call.function.arguments), {
filePath: "/tmp/train.py",
content: "print(1)",
});
});
test('Ex8: <tool><tool name="todowrite">{json}</tool></tool> — name attribute on inner', () => {
const text = `<tool>\n<tool name="todowrite">{"todos":[{"content":"c","status":"in_progress","priority":"high"}]}</tool>\n</tool>`;
const call = firstCall(text);
assert.equal(call.function.name, "todowrite");
assert.deepEqual(JSON.parse(call.function.arguments), {
todos: [{ content: "c", status: "in_progress", priority: "high" }],
});
});
test('Ex9: <tool:write><parameter name="content" content="..."> — parameter style', () => {
const text = `<tool:write>\n<parameter name="content" content="print('hi')">`;
const call = firstCall(text);
assert.equal(call.function.name, "write");
assert.deepEqual(JSON.parse(call.function.arguments), { content: "print('hi')" });
});
test('Ex12: <tool id="todo_write">{json}</tool> — id resolves to a tool name', () => {
const text = `I'll create a script.\n<tool id="todo_write">\n{"todos": [{"content": "z", "status": "in_progress", "priority": "high"}]}\n</tool>`;
const call = firstCall(text);
assert.equal(call.function.name, "todowrite");
assert.deepEqual(JSON.parse(call.function.arguments), {
todos: [{ content: "z", status: "in_progress", priority: "high" }],
});
});
test("canonical <tool>{name,arguments}</tool> still works (no regression)", () => {
const text = `<tool>{"name": "get_weather", "arguments": {"city": "Paris"}}</tool>`;
const call = firstCall(text);
assert.equal(call.function.name, "get_weather");
assert.deepEqual(JSON.parse(call.function.arguments), { city: "Paris" });
});
test("bare JSON (no tags) still resolves via fuzzy name match", () => {
const text = `{"name":"getWeather","arguments":{"city":"Paris"}}`;
const call = firstCall(text);
assert.equal(call.function.name, "get_weather");
assert.deepEqual(JSON.parse(call.function.arguments), { city: "Paris" });
});
test("#3260: tag name attribute is bogus, real name is in JSON body", () => {
const text = `<tool_call name="skill">{"name": "get_weather", "arguments": {"city": "SP"}}</tool_call>`;
const call = firstCall(text);
assert.equal(call.function.name, "get_weather");
});
test("multiple <parameter> tags mixing content-attr and body styles are all captured", () => {
// Regression: an attribute-style <parameter ...> with no closing tag must not let the
// body matcher swallow a following body-style <parameter>...</parameter> (lost param).
const text = `<tool:write>\n<parameter name="filePath" content="/tmp/a.py">\n<parameter name="content">print(1)</parameter>\n</tool>`;
const call = firstCall(text);
assert.equal(call.function.name, "write");
assert.deepEqual(JSON.parse(call.function.arguments), {
filePath: "/tmp/a.py",
content: "print(1)",
});
});
test("surrounding text is preserved both before and after the tool block", () => {
const text = `Before text.\n<tool:bash>\n{"command": "ls"}\n</tool>\nAfter text.`;
const { content, toolCalls } = parseDeepSeekToolCalls(text, "call", TOOLS);
assert.equal(toolCalls?.length, 1);
assert.ok(content.includes("Before text."));
assert.ok(content.includes("After text."));
});
});
describe("deepseekWebTools — pure-text (no tool) replies", () => {
for (const [label, text] of [
["Ex2 plan only", "I'll build a train animation. Plan:\n1. step\n2. step\nStarting now."],
["Ex4 code fence only", "Plan:\n```python\nimport os\nprint(os.getcwd())\n```"],
["Ex13 bash fence only", "```bash\nuv pip install rich\n```"],
] as const) {
test(`${label} — returns plain content, no tool calls`, () => {
const { content, toolCalls } = parseDeepSeekToolCalls(text, "call", TOOLS);
assert.equal(toolCalls, null, "no tool call should be parsed");
assert.equal(content, text, "content returned unchanged");
});
}
});
describe("deepseekWebTools — strict prompt", () => {
test("lists tools and mandates the exact <tool> JSON format", () => {
const prompt = serializeDeepSeekToolPrompt(TOOLS);
assert.ok(prompt.includes("todowrite"));
assert.ok(prompt.includes("get_weather"));
assert.ok(prompt.includes('<tool>{"name"'), "shows the canonical format");
assert.ok(/never|not|do not/i.test(prompt), "warns against alternative formats");
});
test("returns empty string when there are no usable tools", () => {
assert.equal(serializeDeepSeekToolPrompt([]), "");
assert.equal(serializeDeepSeekToolPrompt(undefined), "");
});
});
describe("deepseekWebTools — buildToolConversationPrompt (agentic context)", () => {
// A tool-using conversation must replay the WHOLE trajectory (prior assistant tool_calls +
// their tool results) into the flat web `prompt`, otherwise the model is amnesiac and
// restarts every turn — re-creating todos, re-listing files, etc.
// The legacy builder only forwarded the last user message and dropped
// tool_calls / role:"tool" messages. The executor-level coverage lives in
// deepseek-web-tools-execute.test.ts.
test("replays prior tool calls and their results", () => {
const messages = [
{ role: "user", content: "write train.py" },
{
role: "assistant",
content: "",
tool_calls: [
{
id: "c1",
type: "function",
function: { name: "todowrite", arguments: '{"todos":[{"content":"a"}]}' },
},
],
},
{ role: "tool", tool_call_id: "c1", content: "todos created" },
{
role: "assistant",
content: "",
tool_calls: [
{ id: "c2", type: "function", function: { name: "bash", arguments: '{"command":"ls"}' } },
],
},
{ role: "tool", tool_call_id: "c2", content: "train.py\ncat.md" },
];
const prompt = buildToolConversationPrompt(messages, "TOOLS-HERE");
assert.ok(prompt.includes("TOOLS-HERE"), "tool system prompt leads");
assert.ok(prompt.includes("User: write train.py"), "original task present");
assert.ok(prompt.includes('"name": "todowrite"'), "prior todowrite call replayed");
assert.ok(
prompt.includes("Tool result (todowrite): todos created"),
"todowrite result replayed"
);
assert.ok(prompt.includes('"name": "bash"'), "prior bash call replayed");
assert.ok(prompt.includes("Tool result (bash): train.py"), "bash result replayed");
assert.ok(/Continue the task/i.test(prompt), "anchored to continue, not restart");
});
test("first-turn (no prior tool activity) omits the continue anchor", () => {
const prompt = buildToolConversationPrompt([{ role: "user", content: "hi" }], "TOOLS");
assert.ok(prompt.includes("User: hi"));
assert.ok(!/Continue the task/i.test(prompt), "no continue anchor on the first turn");
});
});