mirror of
https://github.com/anomalyco/opencode.git
synced 2026-07-25 12:16:19 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Kit Langton
|
0918b7d805 |
@@ -1,5 +0,0 @@
|
||||
---
|
||||
"@opencode-ai/ai": patch
|
||||
---
|
||||
|
||||
Report OpenAI prompt cache write tokens in normalized usage.
|
||||
@@ -1,5 +0,0 @@
|
||||
---
|
||||
"@opencode-ai/cli": patch
|
||||
---
|
||||
|
||||
Expose a TUI plugin slot at the top of the session view.
|
||||
@@ -1,8 +0,0 @@
|
||||
---
|
||||
"@opencode-ai/plugin": minor
|
||||
"@opencode-ai/sdk": minor
|
||||
"@opencode-ai/client": minor
|
||||
"@opencode-ai/protocol": minor
|
||||
---
|
||||
|
||||
Replace the V2 tool result model with one canonical representation per fact. Tools lose `structured`, projection callbacks, the `Structured` generic, and the exported `Tool.settle` interpreter; tool responses carry schema-validated `output`, model-visible `content`, and optional compact JSON `metadata`. Code Mode receives the validated encoded output. Durable tool success stores non-empty model content plus optional metadata; failure stores one error plus the final bounded partial snapshot. Progress carries metadata only, while `execute.after` hooks receive the canonical terminal outcome and managed `outputPaths`. A one-time migration rewrites existing projected tool rows and moves provider-hosted result payloads into provider-owned result state.
|
||||
@@ -1,7 +0,0 @@
|
||||
---
|
||||
"@opencode-ai/client": patch
|
||||
"@opencode-ai/plugin": patch
|
||||
"@opencode-ai/protocol": patch
|
||||
---
|
||||
|
||||
Expose transient, read-only session generation through the HTTP API, generated clients, and V2 plugin session context.
|
||||
@@ -1,5 +0,0 @@
|
||||
---
|
||||
"@opencode-ai/cli": patch
|
||||
---
|
||||
|
||||
Expose a TUI plugin slot above the session composer.
|
||||
@@ -1,5 +0,0 @@
|
||||
---
|
||||
"@opencode-ai/ai": patch
|
||||
---
|
||||
|
||||
Improve Anthropic and Bedrock prompt reuse with layered cache breakpoints that roll through long tool loops.
|
||||
@@ -1,3 +1,2 @@
|
||||
packages/core/migration/**/snapshot.json linguist-generated
|
||||
packages/core/src/database/migration.gen.ts linguist-generated
|
||||
packages/core/src/**/*.txt text eol=lf
|
||||
|
||||
@@ -90,18 +90,11 @@ jobs:
|
||||
opencode-app-id: ${{ vars.OPENCODE_APP_ID }}
|
||||
opencode-app-secret: ${{ secrets.OPENCODE_APP_SECRET }}
|
||||
|
||||
- name: Build legacy CLI
|
||||
if: github.ref_name != 'v2'
|
||||
run: ./packages/opencode/script/build.ts ${{ (github.ref_name == 'beta' && '--sourcemaps') || '' }}
|
||||
env:
|
||||
OPENCODE_VERSION: ${{ needs.version.outputs.version }}
|
||||
OPENCODE_RELEASE: ${{ needs.version.outputs.release }}
|
||||
GH_REPO: ${{ needs.version.outputs.repo }}
|
||||
GH_TOKEN: ${{ steps.committer.outputs.token }}
|
||||
|
||||
- name: Build preview CLI
|
||||
- name: Build
|
||||
id: build
|
||||
run: ./packages/cli/script/build.ts ${{ (github.ref_name == 'beta' && '--sourcemaps') || '' }}
|
||||
run: |
|
||||
./packages/opencode/script/build.ts ${{ (github.ref_name == 'beta' && '--sourcemaps') || '' }}
|
||||
./packages/cli/script/build.ts ${{ (github.ref_name == 'beta' && '--sourcemaps') || '' }}
|
||||
env:
|
||||
OPENCODE_VERSION: ${{ needs.version.outputs.version }}
|
||||
OPENCODE_RELEASE: ${{ needs.version.outputs.release }}
|
||||
@@ -109,7 +102,6 @@ jobs:
|
||||
GH_TOKEN: ${{ steps.committer.outputs.token }}
|
||||
|
||||
- uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
|
||||
if: github.ref_name != 'v2'
|
||||
with:
|
||||
name: opencode-cli
|
||||
path: |
|
||||
@@ -117,7 +109,6 @@ jobs:
|
||||
packages/opencode/dist/opencode-linux*
|
||||
|
||||
- uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
|
||||
if: github.ref_name != 'v2'
|
||||
with:
|
||||
name: opencode-cli-windows
|
||||
path: packages/opencode/dist/opencode-windows*
|
||||
@@ -130,55 +121,6 @@ jobs:
|
||||
outputs:
|
||||
version: ${{ needs.version.outputs.version }}
|
||||
|
||||
build-node-cli:
|
||||
needs: version
|
||||
if: github.repository == 'anomalyco/opencode'
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
settings:
|
||||
- target: linux-arm64
|
||||
host: blacksmith-4vcpu-ubuntu-2404-arm
|
||||
- target: linux-x64
|
||||
host: blacksmith-4vcpu-ubuntu-2404
|
||||
- target: darwin-arm64
|
||||
host: macos-26
|
||||
- target: windows-arm64
|
||||
host: blacksmith-4vcpu-windows-2025
|
||||
- target: windows-x64
|
||||
host: blacksmith-4vcpu-windows-2025
|
||||
runs-on: ${{ matrix.settings.host }}
|
||||
defaults:
|
||||
run:
|
||||
shell: bash
|
||||
steps:
|
||||
- uses: actions/checkout@f43a0e5ff2bd294095638e18286ca9a3d1956744 # v3.6.0
|
||||
|
||||
- uses: ./.github/actions/setup-bun
|
||||
with:
|
||||
install-flags: --os=* --cpu=*
|
||||
|
||||
- uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
|
||||
with:
|
||||
node-version: "26.4.0"
|
||||
|
||||
- name: Build
|
||||
run: bun packages/cli/script/build-node.ts --target=${{ matrix.settings.target }} --skip-install --outdir=dist/node
|
||||
env:
|
||||
OPENCODE_VERSION: ${{ needs.version.outputs.version }}
|
||||
OPENCODE_RELEASE: ${{ needs.version.outputs.release }}
|
||||
|
||||
- name: Verify service lifecycle
|
||||
if: matrix.settings.target != 'windows-arm64'
|
||||
working-directory: packages/cli
|
||||
run: bun run script/service-smoke.ts --node
|
||||
|
||||
- uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
|
||||
with:
|
||||
name: opencode-node-cli-${{ matrix.settings.target }}
|
||||
path: packages/cli/dist/node/cli-node-*
|
||||
if-no-files-found: error
|
||||
|
||||
sign-cli-windows:
|
||||
needs:
|
||||
- build-cli
|
||||
@@ -471,7 +413,6 @@ jobs:
|
||||
needs:
|
||||
- version
|
||||
- build-cli
|
||||
- build-node-cli
|
||||
- sign-cli-windows
|
||||
- build-electron
|
||||
if: always() && !failure() && !cancelled()
|
||||
@@ -500,13 +441,11 @@ jobs:
|
||||
registry-url: "https://registry.npmjs.org"
|
||||
|
||||
- uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
|
||||
if: github.ref_name != 'v2'
|
||||
with:
|
||||
name: opencode-cli
|
||||
path: packages/opencode/dist
|
||||
|
||||
- uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
|
||||
if: github.ref_name != 'v2'
|
||||
with:
|
||||
name: opencode-cli-windows
|
||||
path: packages/opencode/dist
|
||||
@@ -522,12 +461,6 @@ jobs:
|
||||
name: opencode-preview-cli
|
||||
path: packages/cli/dist
|
||||
|
||||
- uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
|
||||
with:
|
||||
pattern: opencode-node-cli-*
|
||||
path: packages/cli/dist/node
|
||||
merge-multiple: true
|
||||
|
||||
- uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
|
||||
if: needs.version.outputs.release
|
||||
with:
|
||||
|
||||
@@ -78,30 +78,11 @@ jobs:
|
||||
bun run script/build.ts --single --skip-install
|
||||
bun run script/service-smoke.ts
|
||||
|
||||
- name: Setup Node build runtime
|
||||
if: always()
|
||||
uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4.4.0
|
||||
with:
|
||||
node-version: "26.4.0"
|
||||
|
||||
- name: Verify Node build
|
||||
if: always()
|
||||
timeout-minutes: 15
|
||||
working-directory: packages/cli
|
||||
run: |
|
||||
bun run script/build-node.ts --single --skip-install --outdir=dist/node
|
||||
bun run script/service-smoke.ts --node
|
||||
|
||||
- name: Check generated client
|
||||
if: runner.os == 'Linux'
|
||||
working-directory: packages/client
|
||||
run: bun run check:generated
|
||||
|
||||
- name: Check generated documentation
|
||||
if: runner.os == 'Linux'
|
||||
working-directory: packages/docs
|
||||
run: bun run check:generated
|
||||
|
||||
e2e:
|
||||
name: e2e (${{ matrix.settings.name }})
|
||||
if: github.ref_name != 'v2' && github.head_ref != 'v2'
|
||||
|
||||
@@ -11,7 +11,6 @@ node_modules
|
||||
playground
|
||||
tmp
|
||||
dist
|
||||
dist-node
|
||||
ts-dist
|
||||
.turbo
|
||||
.typecheck-profiles
|
||||
@@ -26,7 +25,6 @@ Session.vim
|
||||
a.out
|
||||
target
|
||||
.scripts
|
||||
.cache
|
||||
.direnv/
|
||||
|
||||
# Local dev files
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
---
|
||||
description: translate English to other languages
|
||||
model: opencode/gpt-5.6-sol
|
||||
model: opencode/claude-opus-4-8
|
||||
---
|
||||
|
||||
run git diff and translate changed english doc and UI copy files to other international languages. Translate all languages in parallel to save time.
|
||||
|
||||
@@ -1,68 +0,0 @@
|
||||
---
|
||||
name: ideal-pseudocode
|
||||
description: Function-by-function refactoring loop driven by ideal pseudocode. Use when the user says "ideal pseudocode", asks to make a function read like its pseudocode, or wants a dense module cleaned up one function at a time.
|
||||
---
|
||||
|
||||
# Ideal Pseudocode
|
||||
|
||||
Clean up one function at a time by writing the pseudocode it _should_ read as, naming every delta between that and the real code, and closing only the gaps the user approves.
|
||||
|
||||
## Loop
|
||||
|
||||
One function per round. Never touch code before the user picks a direction.
|
||||
|
||||
1. **Pick the target** with the user — usually the next function up or down the call chain from the last round.
|
||||
2. **Read the current code** fresh from disk. It may have unsaved or parallel edits; ask before overwriting anything unexpected.
|
||||
3. **Distill.** Write the function's ideal pseudocode in a `ts`-fenced code block — TypeScript-flavored for syntax highlighting, but pseudocode: comments over mechanics, one line per idea, every arm of a loop visible as an arm. For a dense or unfamiliar function, first show the _current_ structure as pseudocode, then the ideal.
|
||||
4. **Name the deltas.** A numbered list; each delta is one concrete gap: control flow smuggled through combinators, a flag-typed parameter, colliding names, side-effect plumbing drowning a loop body, twin functions differing only by a filter. For each, give an honest cost/benefit and a decisive recommendation — including "leave it" when the density has reasons (state the reasons).
|
||||
5. **Verify before proposing.** Any API the proposal builds on (a combinator, schedule, matcher) gets checked against the installed version's source, not memory.
|
||||
6. **Get buy-in, then apply.** Minimal edits. Quarantine irreducible ugliness inside a small helper whose name is the pseudocode line it implements. Collapse shallow sibling functions into one deep function only when the distinguishing argument is a domain noun, not a behavior switch.
|
||||
7. **Validate.** Typecheck and the focused test suites from the package directory; rerun timing-sensitive tests repeatedly. Flag any semantic change the restructure introduced, even when tests pass.
|
||||
8. **Offer the next target** and stop.
|
||||
|
||||
## Style
|
||||
|
||||
- Keep each round tight: pseudocode block, deltas, recommendation, one question.
|
||||
- State mutation belongs in one visible place (usually the loop tail), never spread across error channels or callback closures.
|
||||
- Prefer early return and `if` chains for control flow; matchers are for producing values.
|
||||
- Compare names against the question each caller is actually asking; rename toward the domain noun.
|
||||
|
||||
## Example round
|
||||
|
||||
Every round should read like this (abridged from a real one, on an Effect step-runner):
|
||||
|
||||
> `runStep` it is. The ideal pseudocode:
|
||||
>
|
||||
> ```ts
|
||||
> // One logical step: one settled model call, however many attempts it takes.
|
||||
> // An attempt can end without settling in two ways:
|
||||
> // transient provider failure -> retry the same call, same assistant message
|
||||
> // compaction rewrote history -> rebuild the request and call again
|
||||
> function runStep(session, promotable, step) {
|
||||
> while (true) {
|
||||
> const result = callModel(session, promotable, step)
|
||||
>
|
||||
> if (result.completed) return result
|
||||
>
|
||||
> if (result.retryable) {
|
||||
> wait(retrySchedule) // exhausted -> publish Step.Failed, fail drain
|
||||
> promotable = none // never re-promote on a second attempt
|
||||
> continue
|
||||
> }
|
||||
>
|
||||
> // compaction restarted the step: fresh request from rewritten history
|
||||
> promotable = none
|
||||
> step = result.step
|
||||
> }
|
||||
> }
|
||||
> ```
|
||||
>
|
||||
> Comparing against the real thing, three deltas:
|
||||
>
|
||||
> 1. **The retry arm doesn't live in the loop.** In the pseudocode, retry is just another loop arm. In the real code it's smuggled through the error channel: `Effect.tapError` mutating loop variables via `Effect.sync` closures, then `Effect.retryOrElse` re-running a suspended call. Four mutable variables mutated from three different places — the state flow is invisible unless you already know the trick.
|
||||
> 2. **`recoverOverflow: typeof compaction.compact | undefined`** — a function-typed parameter used as a one-shot armed/disarmed flag. The callee already closes over `compaction`; a boolean says what it is.
|
||||
> 3. **`assistantMessageID`** exists solely to resume the same durable message across retries — fine, but only legible once the retry arm is visible in the loop.
|
||||
>
|
||||
> The unifying move for (1): a schedule driver, so a retryable failure becomes a caught value handled in the loop body exactly like the compaction arm. One honest trade: it's more manual than the blessed combinator — but the manual version is the loop the combinator was hiding, and the loop already exists for restarts. Two restart mechanisms, one control structure.
|
||||
>
|
||||
> Want me to apply it — unified loop, simplified schedule input, boolean `recoverOverflow`?
|
||||
@@ -19,6 +19,8 @@ Valid types are `feat`, `fix`, `docs`, `chore`, `refactor`, and `test`. Scopes a
|
||||
|
||||
Examples: `fix(tui): simplify thinking toggle styling`, `docs: update contributing guide`, `chore(sdk): regenerate types`.
|
||||
|
||||
Never bypass Git hooks. Do not use `--no-verify` or otherwise disable, skip, or circumvent commit or push hooks. If a hook fails, fix the failure or stop and report it to the user.
|
||||
|
||||
## Style Guide
|
||||
|
||||
### General Principles
|
||||
|
||||
@@ -8,25 +8,6 @@ export const zoneID = "430ba34c138cfb5360826c4909f99be8"
|
||||
export const awsStage = $app.stage === "production" ? "production" : "dev"
|
||||
export const deployAws = $app.stage === awsStage
|
||||
|
||||
if ($app.stage === "production") {
|
||||
new cloudflare.DnsRecord("TrustCenter", {
|
||||
zoneId: zoneID,
|
||||
name: "trust.opencode.ai",
|
||||
type: "CNAME",
|
||||
content: "3a69a5bb27875189.vercel-dns-016.com",
|
||||
proxied: false,
|
||||
ttl: 60,
|
||||
})
|
||||
|
||||
new cloudflare.DnsRecord("TrustCenterVerification", {
|
||||
zoneId: zoneID,
|
||||
name: "opencode.ai",
|
||||
type: "TXT",
|
||||
content: "compai-domain-verification=org_6993a99c6200a2d642bb115d",
|
||||
ttl: 60,
|
||||
})
|
||||
}
|
||||
|
||||
new cloudflare.RegionalHostname("RegionalHostname", {
|
||||
hostname: domain,
|
||||
regionKey: "us",
|
||||
|
||||
+33
-66
@@ -8,8 +8,6 @@
|
||||
makeWrapper,
|
||||
writableTmpDirAsHomeHook,
|
||||
autoPatchelfHook,
|
||||
copyDesktopItems,
|
||||
makeDesktopItem,
|
||||
opencode,
|
||||
}:
|
||||
let
|
||||
@@ -29,12 +27,9 @@ stdenv.mkDerivation (finalAttrs: {
|
||||
nodejs
|
||||
makeWrapper
|
||||
writableTmpDirAsHomeHook
|
||||
]
|
||||
++ lib.optionals stdenv.hostPlatform.isLinux [
|
||||
] ++ lib.optionals stdenv.hostPlatform.isLinux [
|
||||
autoPatchelfHook
|
||||
copyDesktopItems
|
||||
]
|
||||
++ lib.optionals stdenv.hostPlatform.isDarwin [
|
||||
] ++ lib.optionals stdenv.hostPlatform.isDarwin [
|
||||
# Ad-hoc sign the .app: --config.mac.identity=null below skips signing.
|
||||
darwin.autoSignDarwinBinariesHook
|
||||
];
|
||||
@@ -43,37 +38,20 @@ stdenv.mkDerivation (finalAttrs: {
|
||||
(lib.getLib stdenv.cc.cc)
|
||||
];
|
||||
|
||||
desktopItems = lib.optional stdenv.hostPlatform.isLinux (makeDesktopItem {
|
||||
name = "ai.opencode.desktop";
|
||||
desktopName = "OpenCode";
|
||||
exec = "opencode-desktop %U";
|
||||
icon = "ai.opencode.desktop";
|
||||
# Electron 41 derives X11 WM_CLASS from app.name.
|
||||
startupWMClass = "OpenCode";
|
||||
categories = [ "Development" ];
|
||||
});
|
||||
|
||||
env = opencode.env // {
|
||||
ELECTRON_SKIP_BINARY_DOWNLOAD = "1";
|
||||
};
|
||||
|
||||
postPatch =
|
||||
# NOTE: Relax Bun version check to be a warning instead of an error
|
||||
''
|
||||
substituteInPlace packages/script/src/index.ts \
|
||||
--replace-fail 'throw new Error(`This script requires bun@''${expectedBunVersionRange}' \
|
||||
'console.warn(`Warning: This script requires bun@''${expectedBunVersionRange}'
|
||||
''
|
||||
# https://github.com/electron/electron/issues/31121
|
||||
# mac builds use a .app bundle which doesnt have this issue
|
||||
+ lib.optionalString stdenv.isLinux ''
|
||||
BASE_PATH=packages/desktop
|
||||
FILES=(src/main/windows.ts)
|
||||
for file in "''${FILES[@]}"; do
|
||||
substituteInPlace $BASE_PATH/$file \
|
||||
--replace-fail "process.resourcesPath" "'$out/opt/opencode-desktop/resources'"
|
||||
done
|
||||
'';
|
||||
# https://github.com/electron/electron/issues/31121
|
||||
# mac builds use a .app bundle which doesnt have this issue
|
||||
postPatch = lib.optionalString stdenv.isLinux ''
|
||||
BASE_PATH=packages/desktop
|
||||
FILES=(src/main/windows.ts)
|
||||
for file in "''${FILES[@]}"; do
|
||||
substituteInPlace $BASE_PATH/$file \
|
||||
--replace-fail "process.resourcesPath" "'$out/opt/opencode-desktop/resources'"
|
||||
done
|
||||
'';
|
||||
|
||||
preBuild = ''
|
||||
cp -r "${electron.dist}" $HOME/.electron-dist
|
||||
@@ -98,38 +76,27 @@ stdenv.mkDerivation (finalAttrs: {
|
||||
runHook postBuild
|
||||
'';
|
||||
|
||||
installPhase = ''
|
||||
runHook preInstall
|
||||
''
|
||||
+ lib.optionalString stdenv.hostPlatform.isDarwin ''
|
||||
mkdir -p $out/Applications
|
||||
mv dist/mac*/*.app $out/Applications
|
||||
makeWrapper "$out/Applications/OpenCode.app/Contents/MacOS/OpenCode" $out/bin/opencode-desktop
|
||||
''
|
||||
+ lib.optionalString stdenv.hostPlatform.isLinux ''
|
||||
mkdir -p $out/opt/opencode-desktop
|
||||
cp -r dist/linux*-unpacked/{resources,LICENSE*} $out/opt/opencode-desktop
|
||||
install -Dm644 resources/icons/32x32.png \
|
||||
"$out/share/icons/hicolor/32x32/apps/ai.opencode.desktop.png"
|
||||
install -Dm644 resources/icons/64x64.png \
|
||||
"$out/share/icons/hicolor/64x64/apps/ai.opencode.desktop.png"
|
||||
install -Dm644 resources/icons/128x128.png \
|
||||
"$out/share/icons/hicolor/128x128/apps/ai.opencode.desktop.png"
|
||||
install -Dm644 resources/icons/128x128@2x.png \
|
||||
"$out/share/icons/hicolor/256x256/apps/ai.opencode.desktop.png"
|
||||
install -Dm644 resources/icons/icon.png \
|
||||
"$out/share/icons/hicolor/512x512/apps/ai.opencode.desktop.png"
|
||||
install -Dm644 resources/ai.opencode.desktop.metainfo.xml \
|
||||
"$out/share/metainfo/ai.opencode.desktop.metainfo.xml"
|
||||
makeWrapper ${lib.getExe electron} $out/bin/opencode-desktop \
|
||||
--inherit-argv0 \
|
||||
--set ELECTRON_FORCE_IS_PACKAGED 1 \
|
||||
--add-flags $out/opt/opencode-desktop/resources/app.asar \
|
||||
--add-flags "\''${NIXOS_OZONE_WL:+\''${WAYLAND_DISPLAY:+--ozone-platform-hint=auto --enable-features=WaylandWindowDecorations --enable-wayland-ime=true}}"
|
||||
''
|
||||
+ ''
|
||||
runHook postInstall
|
||||
'';
|
||||
installPhase =
|
||||
''
|
||||
runHook preInstall
|
||||
''
|
||||
+ lib.optionalString stdenv.hostPlatform.isDarwin ''
|
||||
mkdir -p $out/Applications
|
||||
mv dist/mac*/*.app $out/Applications
|
||||
makeWrapper "$out/Applications/OpenCode.app/Contents/MacOS/OpenCode" $out/bin/opencode-desktop
|
||||
''
|
||||
+ lib.optionalString stdenv.hostPlatform.isLinux ''
|
||||
mkdir -p $out/opt/opencode-desktop
|
||||
cp -r dist/linux*-unpacked/{resources,LICENSE*} $out/opt/opencode-desktop
|
||||
makeWrapper ${lib.getExe electron} $out/bin/opencode-desktop \
|
||||
--inherit-argv0 \
|
||||
--set ELECTRON_FORCE_IS_PACKAGED 1 \
|
||||
--add-flags $out/opt/opencode-desktop/resources/app.asar \
|
||||
--add-flags "\''${NIXOS_OZONE_WL:+\''${WAYLAND_DISPLAY:+--ozone-platform-hint=auto --enable-features=WaylandWindowDecorations --enable-wayland-ime=true}}"
|
||||
''
|
||||
+ ''
|
||||
runHook postInstall
|
||||
'';
|
||||
|
||||
autoPatchelfIgnoreMissingDeps = [
|
||||
"libc.musl-x86_64.so.1"
|
||||
|
||||
+4
-4
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"nodeModules": {
|
||||
"x86_64-linux": "sha256-0kcwV34P2C3yKg2eG9W2nW+OedrSBb+1TdpuUeYtauY=",
|
||||
"aarch64-linux": "sha256-yHVygApQchAB34wrtFR4GU0CkmZOlLsl3wsp15u0xzs=",
|
||||
"aarch64-darwin": "sha256-DyalcwyK2Wn5R6249keFcNVECbgtjYNjscOFqTi88FI=",
|
||||
"x86_64-darwin": "sha256-BkGw0GWN9W9q+/g4FYR0MqxUuFP80BPoERO+ypz/arQ="
|
||||
"x86_64-linux": "sha256-F1luclnqCPQk9yxfmeSYGaM/nScf28yBu9K3Fv+Xd24=",
|
||||
"aarch64-linux": "sha256-XW0XZnsCRkU3MFJH9TjMRYZHffzVy3cQyiNCkec2gl4=",
|
||||
"aarch64-darwin": "sha256-bf8kvORs3Fs2UYLp3PekF+AJR7NKOcHb+fIQA79RtMk=",
|
||||
"x86_64-darwin": "sha256-sBdQPkzd7JXNW6Lbi9JHiAsfHwdLwTKWY+uPeXAv2Nw="
|
||||
}
|
||||
}
|
||||
|
||||
+10
-13
@@ -15,7 +15,7 @@
|
||||
"dev:www": "bun run --cwd packages/www dev",
|
||||
"dev:storybook": "bun --cwd packages/storybook storybook",
|
||||
"lint": "oxlint",
|
||||
"lint:effect-patterns": "ast-grep scan -c script/ast-grep/sgconfig.yml packages/util/src packages/core/src packages/server/src packages/protocol/src packages/cli/src",
|
||||
"lint:effect-patterns": "ast-grep scan -c script/ast-grep/sgconfig.yml packages/core/src packages/server/src packages/protocol/src packages/cli/src",
|
||||
"test:lint-rules": "ast-grep test -c script/ast-grep/sgconfig.yml",
|
||||
"typecheck": "bun turbo typecheck --concurrency=3",
|
||||
"typecheck:profile": "bun script/profile-typecheck.ts",
|
||||
@@ -37,18 +37,18 @@
|
||||
"packages/slack"
|
||||
],
|
||||
"catalog": {
|
||||
"@effect/opentelemetry": "4.0.0-beta.98",
|
||||
"@effect/platform-node": "4.0.0-beta.98",
|
||||
"@effect/sql-sqlite-bun": "4.0.0-beta.98",
|
||||
"@effect/opentelemetry": "4.0.0-beta.83",
|
||||
"@effect/platform-node": "4.0.0-beta.83",
|
||||
"@effect/sql-sqlite-bun": "4.0.0-beta.83",
|
||||
"@npmcli/arborist": "9.4.0",
|
||||
"@types/bun": "1.3.13",
|
||||
"@types/cross-spawn": "6.0.6",
|
||||
"@octokit/rest": "22.0.0",
|
||||
"@hono/standard-validator": "0.2.0",
|
||||
"@hono/zod-validator": "0.4.2",
|
||||
"@opentui/core": "0.4.5",
|
||||
"@opentui/keymap": "0.4.5",
|
||||
"@opentui/solid": "0.4.5",
|
||||
"@opentui/core": "0.4.3",
|
||||
"@opentui/keymap": "0.4.3",
|
||||
"@opentui/solid": "0.4.3",
|
||||
"@tanstack/solid-virtual": "3.13.32",
|
||||
"@shikijs/stream": "4.2.0",
|
||||
"ulid": "3.0.1",
|
||||
@@ -69,13 +69,12 @@
|
||||
"dompurify": "3.3.1",
|
||||
"drizzle-kit": "1.0.0-rc.2",
|
||||
"drizzle-orm": "1.0.0-rc.2",
|
||||
"effect": "4.0.0-beta.98",
|
||||
"effect": "4.0.0-beta.83",
|
||||
"ai": "6.0.168",
|
||||
"cross-spawn": "7.0.6",
|
||||
"hono": "4.10.7",
|
||||
"hono-openapi": "1.1.2",
|
||||
"fuzzysort": "3.1.0",
|
||||
"get-east-asian-width": "1.6.0",
|
||||
"luxon": "3.6.1",
|
||||
"marked": "17.0.6",
|
||||
"marked-shiki": "1.2.1",
|
||||
@@ -86,11 +85,9 @@
|
||||
"@typescript/native-preview": "7.0.0-dev.20251207.1",
|
||||
"zod": "4.1.8",
|
||||
"remeda": "2.26.0",
|
||||
"resolve.exports": "2.0.3",
|
||||
"sst": "4.13.1",
|
||||
"shiki": "4.2.0",
|
||||
"solid-list": "0.3.0",
|
||||
"string-width": "7.2.0",
|
||||
"tailwindcss": "4.1.11",
|
||||
"vite": "7.1.4",
|
||||
"@solidjs/meta": "0.29.4",
|
||||
@@ -155,18 +152,18 @@
|
||||
"@types/node": "catalog:"
|
||||
},
|
||||
"patchedDependencies": {
|
||||
"@ff-labs/fff-bun@0.9.3": "patches/@ff-labs%2Ffff-bun@0.9.3.patch",
|
||||
"@npmcli/agent@4.0.2": "patches/@npmcli%2Fagent@4.0.2.patch",
|
||||
"@silvia-odwyer/photon-node@0.3.4": "patches/@silvia-odwyer%2Fphoton-node@0.3.4.patch",
|
||||
"@standard-community/standard-openapi@0.2.9": "patches/@standard-community%2Fstandard-openapi@0.2.9.patch",
|
||||
"solid-js@1.9.10": "patches/solid-js@1.9.10.patch",
|
||||
"@ai-sdk/xai@3.0.102": "patches/@ai-sdk%2Fxai@3.0.102.patch",
|
||||
"@ai-sdk/mistral@3.0.51": "patches/@ai-sdk%2Fmistral@3.0.51.patch",
|
||||
"gcp-metadata@8.1.2": "patches/gcp-metadata@8.1.2.patch",
|
||||
"pacote@21.5.0": "patches/pacote@21.5.0.patch",
|
||||
"@ai-sdk/google@3.0.73": "patches/@ai-sdk%2Fgoogle@3.0.73.patch",
|
||||
"@pierre/trees@1.0.0-beta.4": "patches/@pierre%2Ftrees@1.0.0-beta.4.patch",
|
||||
"@modelcontextprotocol/sdk@1.29.0": "patches/@modelcontextprotocol%2Fsdk@1.29.0.patch",
|
||||
"effect@4.0.0-beta.98": "patches/effect@4.0.0-beta.98.patch",
|
||||
"effect@4.0.0-beta.83": "patches/effect@4.0.0-beta.83.patch",
|
||||
"@tanstack/virtual-core@3.17.3": "patches/@tanstack%2Fvirtual-core@3.17.3.patch"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,362 +0,0 @@
|
||||
# @opencode-ai/ai
|
||||
|
||||
Schema-first AI primitives for opencode. Provider quirks live in adapters, not in calling code.
|
||||
|
||||
```ts
|
||||
import { Effect } from "effect"
|
||||
import { LLM, LLMClient } from "@opencode-ai/ai"
|
||||
import { OpenAI } from "@opencode-ai/ai/providers"
|
||||
|
||||
const model = OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY }).responses("gpt-4o-mini")
|
||||
|
||||
const request = LLM.request({
|
||||
model,
|
||||
system: "You are concise.",
|
||||
prompt: "Say hello in one short sentence.",
|
||||
generation: { maxTokens: 40 },
|
||||
})
|
||||
|
||||
const program = Effect.gen(function* () {
|
||||
const response = yield* LLMClient.generate(request)
|
||||
console.log(response.text)
|
||||
})
|
||||
```
|
||||
|
||||
Run `LLMClient.stream(request)` instead of `generate` when you want incremental `LLMEvent`s. The event stream is provider-neutral — same shape across OpenAI Chat, OpenAI Responses, Anthropic Messages, Gemini, Bedrock Converse, and any OpenAI-compatible deployment.
|
||||
|
||||
## Image generation
|
||||
|
||||
Use `Image.generate` with an image model for direct asset generation:
|
||||
|
||||
```ts
|
||||
import { Image, ImageInput } from "@opencode-ai/ai"
|
||||
import { OpenAI } from "@opencode-ai/ai/providers"
|
||||
|
||||
const program = Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model: OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY }).image("gpt-image-2"),
|
||||
prompt: "A robot tending a rooftop garden",
|
||||
options: {
|
||||
n: 2,
|
||||
size: "1024x1024",
|
||||
quality: "high", // inferred from the OpenAI image model
|
||||
outputFormat: "webp",
|
||||
future_option: true, // unknown native options pass through unchanged
|
||||
},
|
||||
})
|
||||
|
||||
return response.images // GeneratedImage[] with owned bytes or a provider URL
|
||||
})
|
||||
```
|
||||
|
||||
Pass ordered image inputs to the same method for editing, composition, or image-conditioned generation:
|
||||
|
||||
```ts
|
||||
const response =
|
||||
yield *
|
||||
Image.generate({
|
||||
model,
|
||||
prompt: "Combine these product photos into one studio scene",
|
||||
images: [
|
||||
ImageInput.bytes(firstBytes, "image/png"),
|
||||
ImageInput.url("https://example.com/second.webp"),
|
||||
ImageInput.file("file_123"),
|
||||
],
|
||||
options,
|
||||
http,
|
||||
})
|
||||
```
|
||||
|
||||
`ImageInput.fileUri(uri, mediaType)` represents provider file URIs such as Gemini Files. Raw strings are not
|
||||
accepted as image inputs, avoiding ambiguity between base64, URLs, and provider IDs. Empty or omitted `images`
|
||||
uses text-to-image generation; a non-empty array selects the provider's edit behavior without enforcing provider
|
||||
image-count limits locally. `images` is the only common image-editing field. OpenAI uses multipart for byte/data-URL
|
||||
edits and its JSON reference body for URL or file-ID edits. Its provider-specific `options.mask` accepts an
|
||||
`ImageInput` for inpainting:
|
||||
|
||||
```ts
|
||||
yield *
|
||||
Image.generate({
|
||||
model: OpenAI.configure({ apiKey }).image("gpt-image-2"),
|
||||
prompt,
|
||||
images: [ImageInput.bytes(sourceBytes, "image/png")],
|
||||
options: { mask: ImageInput.bytes(maskBytes, "image/png") },
|
||||
})
|
||||
```
|
||||
|
||||
The OpenAI adapter extracts this helper value into the edit request's native `mask` field rather than passing the
|
||||
tagged `ImageInput` object through as an ordinary option. On multipart requests, `http.body` can override option
|
||||
fields but not structural `model`, `prompt`, `image[]`, or `mask` fields, and the transport owns the multipart
|
||||
`Content-Type` boundary. For JSON requests, `http.body` remains the final raw-native overlay. Gemini does not fetch
|
||||
public HTTP URLs, and hosted Z.ai image generation does not accept image inputs. These cases fail with
|
||||
`InvalidRequest` before network I/O.
|
||||
|
||||
Provider-native image options belong to each request. Raw `http.body` fields have final precedence over them:
|
||||
|
||||
```ts
|
||||
const model = OpenAI.configure({ apiKey }).image("gpt-image-2")
|
||||
|
||||
yield *
|
||||
Image.generate({
|
||||
model,
|
||||
prompt,
|
||||
options: { quality: "medium" },
|
||||
http,
|
||||
})
|
||||
```
|
||||
|
||||
xAI image models use the same request API with xAI-native controls:
|
||||
|
||||
```ts
|
||||
yield *
|
||||
Image.generate({
|
||||
model: XAI.configure({ apiKey }).image("any-model-id"),
|
||||
prompt,
|
||||
options: {
|
||||
n: 2,
|
||||
aspectRatio: "16:9",
|
||||
resolution: "1k",
|
||||
responseFormat: "b64_json",
|
||||
future_option: true,
|
||||
},
|
||||
http,
|
||||
})
|
||||
```
|
||||
|
||||
Google's current Gemini image models use the same direct API:
|
||||
|
||||
```ts
|
||||
import { Google } from "@opencode-ai/ai/providers"
|
||||
|
||||
const googleProgram = Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model: Google.configure({ apiKey }).image("any-model-id"),
|
||||
prompt: "A robot tending a rooftop garden",
|
||||
options: {
|
||||
aspectRatio: "16:9",
|
||||
imageSize: "2K",
|
||||
seed: 42,
|
||||
thinkingLevel: "HIGH",
|
||||
includeThoughts: true,
|
||||
futureOption: true,
|
||||
},
|
||||
http,
|
||||
})
|
||||
|
||||
return response.images
|
||||
})
|
||||
```
|
||||
|
||||
Google image options are request-scoped and inferred from the selected model. Known fields autocomplete while
|
||||
future string values and arbitrary native Gemini `generationConfig` fields remain available. Native fields override
|
||||
their mapped aliases, and `http.body` is the final deep overlay. The selected model ID is sent to Gemini
|
||||
`generateContent` without a local allowlist.
|
||||
|
||||
Z.ai image models infer open Z.ai-native options from the selected model:
|
||||
|
||||
```ts
|
||||
yield *
|
||||
Image.generate({
|
||||
model: ZAI.configure({ apiKey }).image("any-model-id"),
|
||||
prompt,
|
||||
options: {
|
||||
quality: "hd",
|
||||
userID: "user-123",
|
||||
future_option: true,
|
||||
},
|
||||
http,
|
||||
})
|
||||
```
|
||||
|
||||
Z.ai does not include trustworthy MIME metadata for output URLs, so generated images use
|
||||
`application/octet-stream`. Output URLs expire after 30 days; download and persist them promptly if they must
|
||||
remain available.
|
||||
|
||||
Conversational image generation remains part of the LLM interaction. OpenAI Responses exposes it through its hosted image tool:
|
||||
|
||||
```ts
|
||||
const program = Effect.gen(function* () {
|
||||
const response = yield* LLM.generate(
|
||||
LLM.request({
|
||||
model: OpenAI.configure({ apiKey }).responses("gpt-5"),
|
||||
prompt: "Design a solarpunk rooftop garden, then show me.",
|
||||
tools: [OpenAI.imageGeneration({ quality: "high" })],
|
||||
}),
|
||||
)
|
||||
|
||||
return response.message
|
||||
})
|
||||
```
|
||||
|
||||
The hosted result is represented as a provider-executed tool call and tool result. Its image is a `file` content item with a data URI, so retaining `response.message` preserves the generated image for continuation.
|
||||
|
||||
## Public API
|
||||
|
||||
- **`LLM.request({...})`** — build a provider-neutral `LLMRequest`. Accepts ergonomic inputs (`system: string`, `prompt: string`) that normalize into the canonical Schema classes.
|
||||
- **`LLM.generate` / `LLM.stream`** — re-exported from `LLMClient` for one-import use.
|
||||
- **`Message.user(...)` / `Message.assistant(...)` / `Message.tool(...)`** — message constructors from the canonical schema model.
|
||||
- **`Model.make(...)` / `ToolCallPart.make(...)` / `ToolResultPart.make(...)` / `ToolDefinition.make(...)`** — model and tool-related constructors from the canonical schema model.
|
||||
- **`LLMClient.prepare(request)`** — compile a request through protocol body construction, validation, and HTTP preparation without sending. Useful for inspection and testing.
|
||||
- **`LLMEvent.is.*`** — typed guards (`is.textDelta`, `is.toolCall`, `is.finish`, …) for filtering streams.
|
||||
- **`Image.generate({...})`** — generate images through a provider-neutral image request and response model.
|
||||
- **`ImageClient`** — Effect service and layer for image execution, parallel to `LLMClient`.
|
||||
|
||||
## Caching
|
||||
|
||||
Prompt caching is **on by default**. Every `LLMRequest` resolves to `cache: "auto"` unless the caller opts out with `cache: "none"`. Each protocol translates `CacheHint`s to its wire format (`cache_control` on Anthropic, `cachePoint` on Bedrock; OpenAI and Gemini do implicit caching server-side and don't need inline markers — auto is a no-op there).
|
||||
|
||||
### Auto placement
|
||||
|
||||
`"auto"` places up to four breakpoints — the last tool definition, the first system part, the last system part when distinct, and the final message boundary. These expose successively larger reusable prefixes for tools, the base agent, project instructions, and the active conversation. The rolling final-message boundary is the load-bearing detail in tool loops: it advances on every request so the previous cache entry stays within Anthropic's 20-block lookback.
|
||||
|
||||
Tools precede every system and conversation block in the provider prefix, so tool definitions must remain byte-stable and deterministically ordered for downstream breakpoints to remain reusable.
|
||||
|
||||
The math justifies the default: Anthropic's 5-minute cache write is 1.25× base, read is 0.1×, so a single reuse within 5 minutes already wins. One-shot completions below the per-model minimum-cacheable-token threshold silently no-op on the wire, so the worst case is harmless.
|
||||
|
||||
### Opting out
|
||||
|
||||
```ts
|
||||
LLM.request({
|
||||
model,
|
||||
system,
|
||||
prompt: "one-off question",
|
||||
cache: "none",
|
||||
})
|
||||
```
|
||||
|
||||
### Granular policy
|
||||
|
||||
```ts
|
||||
cache: {
|
||||
tools?: boolean,
|
||||
system?: boolean,
|
||||
messages?: "latest-user-message" | "latest-assistant" | { tail: number },
|
||||
ttlSeconds?: number, // ≥ 3600 → 1h on Anthropic/Bedrock; else 5m
|
||||
}
|
||||
```
|
||||
|
||||
### Manual hints
|
||||
|
||||
Inline `CacheHint` on any text / system / tool / tool-result part overrides automatic placement. The auto policy preserves manual hints, counts them against Anthropic and Bedrock's four-breakpoint limit, and only fills the remaining slots.
|
||||
|
||||
```ts
|
||||
LLM.request({
|
||||
model,
|
||||
system: [
|
||||
{ type: "text", text: "stable system prompt", cache: { type: "ephemeral" } },
|
||||
],
|
||||
...
|
||||
})
|
||||
```
|
||||
|
||||
### Provider behavior table
|
||||
|
||||
| Protocol | `cache: "auto"` |
|
||||
| ----------------------- | ------------------------------------------------------------------------- |
|
||||
| Anthropic Messages | emits up to 4 `cache_control` markers (4-breakpoint cap enforced) |
|
||||
| Bedrock Converse | emits up to 4 `cachePoint` blocks (4-breakpoint cap enforced) |
|
||||
| OpenAI Chat / Responses | no-op (implicit caching above 1024 tokens) |
|
||||
| Gemini | no-op (implicit caching on 2.5+; explicit `CachedContent` is out-of-band) |
|
||||
|
||||
Normalized cache usage is read back into `response.usage.cacheReadInputTokens` and `cacheWriteInputTokens` across every provider.
|
||||
|
||||
## Providers
|
||||
|
||||
Provider facades configure endpoint/auth/deployment details first, then expose model selectors that take only a model or deployment id. The selected model carries the executable route value used at runtime.
|
||||
|
||||
```ts
|
||||
import { OpenAI, CloudflareAIGateway } from "@opencode-ai/ai/providers"
|
||||
|
||||
const openai = OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY }).responses("gpt-4o-mini")
|
||||
const gateway = CloudflareAIGateway.configure({
|
||||
accountId: process.env.CLOUDFLARE_ACCOUNT_ID,
|
||||
gatewayApiKey: process.env.CLOUDFLARE_API_TOKEN,
|
||||
}).model("workers-ai/@cf/meta/llama-3.1-8b-instruct")
|
||||
```
|
||||
|
||||
Included providers: OpenAI, Anthropic, Google (Gemini), Google Vertex Gemini and Anthropic, Amazon Bedrock, Azure OpenAI, Cloudflare AI Gateway, Cloudflare Workers AI, GitHub Copilot, OpenRouter, xAI, Z.ai, plus generic OpenAI-compatible Chat and Responses entrypoints and an Anthropic Messages-compatible entrypoint.
|
||||
|
||||
### Package-like entrypoints
|
||||
|
||||
Native catalog integrations load provider behavior through package-like entrypoints. These are export paths from the same `@opencode-ai/ai` npm package, not independently published packages. Each entrypoint exports the same `model(modelID, settings)` contract, and `settings` contains serializable provider configuration plus common `headers`, `body`, and `limits` overlays.
|
||||
|
||||
```ts
|
||||
import { model } from "@opencode-ai/ai/providers/openai/responses"
|
||||
|
||||
const selected = model("gpt-5", {
|
||||
apiKey: process.env.OPENAI_API_KEY,
|
||||
transport: "websocket",
|
||||
headers: { "x-application": "opencode" },
|
||||
limits: { context: 200_000, output: 64_000 },
|
||||
})
|
||||
```
|
||||
|
||||
OpenAI Chat and OpenAI Responses are separate semantic entrypoints:
|
||||
|
||||
- `@opencode-ai/ai/providers/openai/chat`
|
||||
- `@opencode-ai/ai/providers/openai/responses`
|
||||
- `@opencode-ai/ai/providers/openai-compatible/responses`
|
||||
- `@opencode-ai/ai/providers/anthropic-compatible`
|
||||
- `@opencode-ai/ai/providers/google-vertex/gemini`
|
||||
- `@opencode-ai/ai/providers/google-vertex/chat`
|
||||
- `@opencode-ai/ai/providers/google-vertex/responses`
|
||||
- `@opencode-ai/ai/providers/google-vertex/messages`
|
||||
|
||||
Responses HTTP versus WebSocket is a scoped `transport` setting on the OpenAI Responses entrypoint, not another entrypoint. Azure follows the same Chat/Responses split at `providers/azure/chat` and `providers/azure/responses`. Generic OpenAI-compatible Chat remains at `providers/openai-compatible`; the Responses adapter at `providers/openai-compatible/responses` uses the provider-neutral Open Responses protocol. OpenAI Responses extends that baseline with OpenAI tools, event variants, metadata, defaults, and transports. Generic Anthropic Messages-compatible providers use `providers/anthropic-compatible`, which the named Anthropic provider composes. Google Gemini and Amazon Bedrock expose their single native API through their existing provider paths.
|
||||
|
||||
Vertex Gemini, Vertex Chat, Vertex Responses, and Vertex Messages are separate API entrypoints. All accept `project`, `location`, and an optional `accessToken`; when no explicit token or auth override is supplied they lazily use Google Application Default Credentials. Vertex Gemini instead selects express mode when `apiKey` or `GOOGLE_VERTEX_API_KEY` is present. Vertex Chat targets MaaS models through the OpenAI-compatible Chat Completions endpoint, while Vertex Responses targets Grok models and defaults `store` to `false` as required by Vertex. `providers/google-vertex` remains the default alias for `providers/google-vertex/gemini`.
|
||||
|
||||
Tuned Vertex Gemini deployments use model ids shaped like `endpoints/1234567890` and require OAuth or ADC; Vertex express-mode API keys support publisher models only.
|
||||
|
||||
```ts
|
||||
import { model } from "@opencode-ai/ai/providers/google-vertex/gemini"
|
||||
|
||||
model("gemini-3.5-flash", { project: "my-project", location: "global" })
|
||||
```
|
||||
|
||||
```ts
|
||||
import { model } from "@opencode-ai/ai/providers/google-vertex/chat"
|
||||
|
||||
model("deepseek-ai/deepseek-v3.2-maas", { project: "my-project", location: "global" })
|
||||
```
|
||||
|
||||
```ts
|
||||
import { model } from "@opencode-ai/ai/providers/google-vertex/responses"
|
||||
|
||||
model("xai/grok-4.20-reasoning", { project: "my-project", location: "global" })
|
||||
```
|
||||
|
||||
```ts
|
||||
import { model } from "@opencode-ai/ai/providers/google-vertex/messages"
|
||||
|
||||
model("claude-sonnet-4-6", { project: "my-project", location: "global" })
|
||||
```
|
||||
|
||||
Provider facades such as `OpenAI.configure(...).responses(...)` remain the direct application API. Package-like entrypoints are the self-similar loading contract used when a catalog selects behavior by export path.
|
||||
|
||||
Other provider exports listed above remain direct facades until they explicitly implement the package-like contract. Exporting a provider facade does not implicitly make it a catalog-loadable provider package.
|
||||
|
||||
## Provider options & HTTP overlays
|
||||
|
||||
Three escape hatches in order of stability:
|
||||
|
||||
1. **`generation`** — portable knobs (`maxTokens`, `temperature`, `topP`, `topK`, penalties, seed, stop).
|
||||
2. **`providerOptions: { <provider>: {...} }`** — typed-at-the-facade provider-specific knobs (OpenAI `promptCacheKey`, Anthropic `thinking`, Gemini `thinkingConfig`, OpenRouter routing).
|
||||
3. **`http: { body, headers, query }`** — last-resort serializable overlays merged into the final HTTP request. Reach for this only when a stable typed path doesn't yet exist.
|
||||
|
||||
Route/provider defaults are overridden by request-level values for each axis.
|
||||
|
||||
## Routes
|
||||
|
||||
Adding a new model or deployment is usually 5-15 lines using `Route.make({ protocol, endpoint, auth, framing, ... })`. The route owns endpoint/auth/framing and the protocol owns body construction plus stream parsing. Transports are reusable IO templates that receive route endpoint/auth at compile time. Capability/catalog metadata lives outside this low-level package; unsupported request shapes fail during protocol lowering. See `AGENTS.md` for the architectural detail.
|
||||
|
||||
## Effect
|
||||
|
||||
This package is built on Effect. Public methods return `Effect` or `Stream`; provide `LLMClient.layer` for LLM dispatch and `ImageClient.layer` for image dispatch, then import the provider/protocol modules for the routes you use. The example at `example/tutorial.ts` is a runnable walkthrough.
|
||||
|
||||
## See also
|
||||
|
||||
- `AGENTS.md` — architecture, route construction, contributor guide
|
||||
- `STATUS.md` — native provider parity status and AI SDK migration gaps
|
||||
- `example/tutorial.ts` — runnable end-to-end walkthrough
|
||||
- `test/provider/*.test.ts` — fixture-first protocol tests; `*.recorded.test.ts` files cover live cassettes
|
||||
@@ -1,108 +0,0 @@
|
||||
# LLM Provider Parity Status
|
||||
|
||||
Last reviewed: 2026-07-24
|
||||
|
||||
This file tracks the gap between the native `@opencode-ai/ai` package and the AI SDK provider packages that opencode still depends on for many catalog/runtime paths.
|
||||
|
||||
## Existing Status Sources
|
||||
|
||||
| File | What it tracks | Limitation |
|
||||
| ----------------------------------- | ----------------------------------------------------------------------- | ------------------------------------------------------- |
|
||||
| `packages/ai/DESIGN.md` | Future clean-break API proposal for `@opencode-ai/ai`. | Not a provider parity tracker. |
|
||||
| `packages/ai/example/call-sites.md` | Route/value/provider-facade migration checklist and call-site sketches. | Architecture migration only; not AI SDK package parity. |
|
||||
|
||||
## Current Implementation Snapshot
|
||||
|
||||
| Native slice | Source | Current state | Main gaps |
|
||||
| ---------------------------------- | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| OpenAI Chat | `src/protocols/openai-chat.ts`, `src/providers/openai.ts` | Usable. Streams text, reasoning deltas, tool calls, usage, images, and common generation controls. | No typed structured-output / `response_format` path. Limited typed OpenAI option surface compared with SDK escape hatches. |
|
||||
| OpenAI Responses HTTP | `src/protocols/open-responses.ts`, `src/protocols/openai-responses.ts`, `src/providers/openai.ts` | Usable. Extends the Open Responses baseline with hosted-tool event surfacing, reasoning replay metadata, GPT-5 defaults, and cache usage. | No explicit `previous_response_id` path. Typed options cover only a subset of Responses fields. Structured output is still mostly synthetic-tool based. |
|
||||
| OpenAI Responses WebSocket | `src/protocols/openai-responses.ts`, `src/route/transport/websocket.ts` | Present as `OpenAI.responsesWebSocket(...)`. | Runner/catalog support explicitly must not downgrade WebSocket routes; broader runtime selection is not complete. |
|
||||
| OpenAI-compatible Chat | `src/protocols/openai-compatible-chat.ts`, `src/providers/openai-compatible.ts` | Usable for generic Chat and several profiles: Baseten, Cerebras, DeepInfra, DeepSeek, Fireworks, Groq, TogetherAI. | Family quirks are mostly endpoint defaults, not full typed behavior. |
|
||||
| Open Responses-compatible | `src/protocols/open-responses.ts`, `src/protocols/openai-compatible-responses.ts`, `src/providers/openai-compatible-responses.ts` | Usable for deployments that implement the provider-neutral Open Responses protocol. The deployment adapter does not inherit OpenAI tools, events, metadata, or defaults. | No named family profiles or recorded deployment coverage yet. |
|
||||
| Anthropic-compatible Messages | `src/protocols/anthropic-messages.ts`, `src/providers/anthropic-compatible.ts` | Usable for deployments that implement the Anthropic Messages wire protocol. Named Anthropic composes this base; MiniMax M3 has recorded text and tool-loop coverage. | No named compatible family profiles yet. |
|
||||
| Anthropic Messages | `src/protocols/anthropic-messages.ts`, `src/providers/anthropic.ts` | Usable. Supports tools, thinking, cache control, images, server-hosted tool events, and usage. | Provider option surface is small. Beta/header handling, metadata, and newer Messages fields need a typed parity pass. |
|
||||
| Gemini Developer API | `src/protocols/gemini.ts`, `src/providers/google.ts` | Usable for Google API key flow. Supports text, images, tools, thinking signatures, and cache usage. | This is not Vertex. Typed provider options are narrow; many Gemini request fields currently require raw `http.body` overlays. |
|
||||
| Vertex Gemini | `src/protocols/gemini.ts`, `src/providers/google-vertex.ts` | Usable through API-key express mode, explicit OAuth tokens, or ADC with project/location endpoint derivation, including tuned `endpoints/...` deployments. | Core runner/catalog mapping and recorded provider coverage are missing. |
|
||||
| Vertex Chat | `src/protocols/openai-chat.ts`, `src/providers/google-vertex-chat.ts` | Usable for MaaS models through OpenAI-compatible Chat Completions with explicit OAuth tokens or ADC and project/location endpoint derivation. | Core runner/catalog mapping and recorded provider coverage are missing; MaaS family-specific request parity needs review. |
|
||||
| Vertex Responses | `src/protocols/open-responses.ts`, `src/providers/google-vertex-responses.ts` | Usable for Grok models through Open Responses with explicit OAuth tokens or ADC, project/location endpoint derivation, and an explicit `store: false` Vertex default. | Core runner/catalog mapping and recorded provider coverage are missing; stateful continuation is not supported by Vertex. |
|
||||
| Vertex Messages | `src/protocols/anthropic-messages.ts`, `src/providers/google-vertex-messages.ts` | Usable through explicit OAuth tokens or ADC, including global, regional, and `eu`/`us` multi-region endpoints. | Core runner/catalog mapping and recorded provider coverage are missing; Vertex-specific hosted-tool parity needs review. |
|
||||
| Bedrock Converse | `src/protocols/bedrock-converse.ts`, `src/providers/amazon-bedrock.ts` | Partial but real. Supports AWS event-stream framing, SigV4 with supplied credentials, bearer auth, tools, reasoning signatures, media, cache points, and recorded tests. | Native facade does not mirror the AI SDK plugin's default AWS credential chain/profile behavior. Runner/catalog mapping is missing. Guardrails, inference profiles, region-specific model ID fixes, and model-specific request fields need a parity pass. |
|
||||
| Azure OpenAI | `src/providers/azure.ts` using OpenAI Chat/Responses protocols | Partial. Supports resource/base URL setup, API key auth, API version query, Chat, and Responses selectors. | Core runner does not map `@ai-sdk/azure` to this native facade. AAD/token auth and Azure-specific endpoint variants need review. |
|
||||
| Cloudflare AI Gateway / Workers AI | `src/providers/cloudflare.ts` | Present via OpenAI-compatible Chat routes. | Useful but not part of the critical AI SDK replacement set yet. Needs per-product recorded coverage before relying on it broadly. |
|
||||
| OpenRouter | `src/providers/openrouter.ts` | Present with OpenRouter-specific usage/reasoning/prompt-cache options over Chat. | Responses-style OpenRouter support is absent. |
|
||||
| xAI | `src/providers/xai.ts` | Present with Responses and Chat selectors. | Needs package-parity review against the AI SDK xAI provider. |
|
||||
| GitHub Copilot | `src/providers/github-copilot.ts` | Present as explicit-base-URL OpenAI Chat/Responses facade. | Runtime/catalog integration remains specialized and should stay separate from public OpenAI-compatible defaults. |
|
||||
|
||||
## V2 Runner Status
|
||||
|
||||
`packages/core/src/session/runner/model.ts` currently resolves only this native subset from catalog `aisdk` metadata:
|
||||
|
||||
| Catalog API | Native route used today |
|
||||
| --------------------------------------------------- | ---------------------------- |
|
||||
| `aisdk:@ai-sdk/openai` | `OpenAIResponses.route` |
|
||||
| `aisdk:@ai-sdk/anthropic` | `AnthropicMessages.route` |
|
||||
| `aisdk:@ai-sdk/openai-compatible` with explicit URL | `OpenAICompatibleChat.route` |
|
||||
|
||||
Other `aisdk:` packages, including Google Vertex, Azure, and Bedrock, currently fall back through the AI SDK loader in the production runner. The dependency-free resolver seam rejects them with `SessionRunnerModel.UnsupportedPackageError`; they are not native route mappings yet.
|
||||
|
||||
## AI SDK Package Parity Matrix
|
||||
|
||||
| AI SDK package | Intended native target | Status | Biggest gaps |
|
||||
| --------------------------------- | -------------------------------------------------------------- | ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `@ai-sdk/openai` | `OpenAI.chat`, `OpenAI.responses`, `OpenAI.responsesWebSocket` | Partial / usable | Add complete typed option coverage, structured output strategy, explicit Responses continuation support, and runner route selection between Chat/Responses/WebSocket. |
|
||||
| `@ai-sdk/openai-compatible` | Generic OpenAI-compatible Chat and Responses | Partial / usable | Decide per-family namespace/profile behavior and runner API selection for providers that support Responses versus Chat only. |
|
||||
| `@ai-sdk/anthropic` | `AnthropicMessages` | Partial / usable | Finish Messages API parity for headers/betas/metadata/newer fields and document hosted-tool continuation expectations. |
|
||||
| `@ai-sdk/google` | Gemini Developer API | Partial / usable | Add typed options for safety, response schema/modalities, cached content, grounding/search/code execution, and non-text output modes where supported. |
|
||||
| `@ai-sdk/google-vertex` | Vertex Gemini namespace/facade | Partial / usable | Add runner/catalog mapping, recorded coverage, and broader provider-option parity. |
|
||||
| `@ai-sdk/google-vertex/anthropic` | Anthropic Messages over Vertex namespace/facade | Partial / usable | Add runner/catalog mapping, recorded coverage, and Vertex-specific hosted-tool parity. |
|
||||
| `@ai-sdk/google-vertex/maas` | Vertex Chat | Partial / usable | Add runner/catalog mapping, recorded coverage, and MaaS family-specific request parity. |
|
||||
| `@ai-sdk/google-vertex/xai` | Vertex Chat / Responses | Partial / usable | Decide Chat/Responses selection for catalog models, add runner mapping and recorded coverage, and review xAI-specific request options. |
|
||||
| `@ai-sdk/azure` | Azure OpenAI Chat/Responses facade | Partial | Map runner/catalog metadata to native Azure, handle resourceName/baseURL/apiVersion variants, add AAD/token auth story, and verify Chat vs Responses deployment selection. |
|
||||
| `@ai-sdk/amazon-bedrock` | Bedrock Converse | Partial | Add default AWS credential chain/profile support, region/inference-profile model ID handling, provider option parity via `additionalModelRequestFields`, guardrails/performance config, and runner/catalog mapping. |
|
||||
| `@ai-sdk/amazon-bedrock/mantle` | Bedrock Mantle OpenAI-compatible Chat/Responses namespace | Missing | Decide native Mantle shape, likely separate from Converse because it uses OpenAI-compatible Chat/Responses semantics over Bedrock. Add package mapping and tests. |
|
||||
|
||||
## Highest-Risk Gaps
|
||||
|
||||
1. Runner support is narrower than the LLM package. The package has native provider facades for Google, Azure, and Bedrock, but the V2 Session runner only maps OpenAI, Anthropic, and explicit OpenAI-compatible Chat from `aisdk` catalog metadata.
|
||||
2. The Open Responses adapter is available through a separate package entrypoint, but the V2 runner still maps `@ai-sdk/openai-compatible` to Chat only. Catalog selection must become API-aware before Responses deployments can use it.
|
||||
3. Bedrock native auth is not AI SDK parity. The AI SDK plugin uses the default AWS provider chain, profile, container credentials, and Bedrock bearer token env behavior. Native Bedrock currently expects explicit credentials or bearer auth on the facade.
|
||||
4. Vertex Gemini, Vertex Chat, Vertex Responses, and Vertex Messages now have native package entrypoints, but the core runner does not map catalog metadata to them yet and recorded provider coverage is still missing.
|
||||
5. Azure is only a provider facade, not a full runtime replacement. Native Azure exists, but the catalog runner does not select it, and token auth/resource variants need review.
|
||||
6. Provider option typing is uneven. OpenAI, Anthropic, Gemini, Bedrock, and OpenRouter each expose a small typed subset plus raw HTTP overlays; this is useful but not equivalent to AI SDK provider option coverage.
|
||||
7. Structured output is not provider-native yet. `LLM.generateObject` still uses a synthetic tool strategy, while the future design expects native structured output where reliable and tool fallback where needed.
|
||||
8. Package/namespace boundaries for the current native loading set are explicit in docs and exports. Other exported provider facades are not catalog package entrypoints until they implement the contract. Vertex xAI still needs catalog API selection; the missing native boundary is Bedrock Mantle.
|
||||
9. Recorded coverage is uneven. OpenAI, Anthropic, Gemini, Bedrock Converse, Cloudflare, OpenRouter, and several OpenAI-compatible Chat providers have cassettes. Azure, Vertex, and Mantle need first-class recorded scenarios before switching defaults.
|
||||
|
||||
## Native Namespace Shape
|
||||
|
||||
These are implementation/API slices, not separate npm packages.
|
||||
|
||||
| API slice | Package-like entrypoint | Purpose |
|
||||
| ----------------------------- | ------------------------------------------------------- | ---------------------------------------------------------------------------- |
|
||||
| OpenAI Chat | `@opencode-ai/ai/providers/openai/chat` | OpenAI `/chat/completions` semantics. |
|
||||
| OpenAI Responses | `@opencode-ai/ai/providers/openai/responses` | OpenAI `/responses` semantics with HTTP/WebSocket selected through settings. |
|
||||
| OpenAI-compatible Chat | `@opencode-ai/ai/providers/openai-compatible` | Generic OpenAI-compatible `/chat/completions`. |
|
||||
| Open Responses-compatible | `@opencode-ai/ai/providers/openai-compatible/responses` | Generic provider-neutral `/responses`. |
|
||||
| Anthropic-compatible Messages | `@opencode-ai/ai/providers/anthropic-compatible` | Generic Anthropic-compatible `/messages`. |
|
||||
| Anthropic Messages | `@opencode-ai/ai/providers/anthropic` | Anthropic Messages API. |
|
||||
| Gemini Developer API | `@opencode-ai/ai/providers/google` | Google AI Studio Gemini API. |
|
||||
| Vertex Gemini | `@opencode-ai/ai/providers/google-vertex/gemini` | Vertex Gemini API; `providers/google-vertex` is the default alias. |
|
||||
| Vertex Chat | `@opencode-ai/ai/providers/google-vertex/chat` | Vertex OpenAI-compatible Chat Completions for MaaS models. |
|
||||
| Vertex Responses | `@opencode-ai/ai/providers/google-vertex/responses` | Vertex Open Responses for Grok models. |
|
||||
| Vertex Messages | `@opencode-ai/ai/providers/google-vertex/messages` | Vertex-hosted Anthropic Messages API. |
|
||||
| Bedrock Converse | `@opencode-ai/ai/providers/amazon-bedrock` | AWS Bedrock Converse API. |
|
||||
| Bedrock Mantle | Missing | AWS Bedrock Mantle OpenAI-compatible APIs. |
|
||||
| Azure OpenAI Chat | `@opencode-ai/ai/providers/azure/chat` | Azure specialization of OpenAI Chat. |
|
||||
| Azure OpenAI Responses | `@opencode-ai/ai/providers/azure/responses` | Azure specialization of OpenAI Responses. |
|
||||
|
||||
## Suggested Next Work Slices
|
||||
|
||||
1. Add native runner/catalog mappings for `@ai-sdk/azure`, `@ai-sdk/google`, and `@ai-sdk/amazon-bedrock` where the existing native facades are already close.
|
||||
2. Add API-aware runner/catalog selection between OpenAI-compatible Chat and Responses.
|
||||
3. Bring Bedrock native auth/config to AI SDK parity: region, profile, default AWS credential chain, bearer token env, endpoint override, and cross-region inference profile handling.
|
||||
4. Add runner/catalog mappings and recorded scenarios for the native Vertex Gemini, Chat, Responses, and Messages entrypoints.
|
||||
5. Decide Chat/Responses selection for `@ai-sdk/google-vertex/xai` catalog models.
|
||||
6. Add Bedrock Mantle as a separate OpenAI-compatible Bedrock namespace after deciding whether it uses Chat, Responses, or both by model.
|
||||
7. Expand typed provider options from the existing V1 lowerer knowledge in `packages/core/src/v1/config/provider-options.ts` before adding more raw overlay examples.
|
||||
8. Add recorded provider tests for Azure, Vertex Gemini, Vertex Chat, Vertex Responses, Vertex Messages, Bedrock credential-chain behavior, and Mantle before making native runtime the default for those packages.
|
||||
@@ -1,37 +0,0 @@
|
||||
{
|
||||
"$schema": "https://json.schemastore.org/package.json",
|
||||
"version": "1.17.20",
|
||||
"name": "@opencode-ai/ai",
|
||||
"type": "module",
|
||||
"license": "MIT",
|
||||
"scripts": {
|
||||
"setup:recording-env": "bun run script/setup-recording-env.ts",
|
||||
"test": "bun test --timeout 30000 --only-failures",
|
||||
"typecheck": "tsgo --noEmit && tsgo --noEmit -p tsconfig.types.json",
|
||||
"build": "tsc -p tsconfig.build.json"
|
||||
},
|
||||
"files": [
|
||||
"dist"
|
||||
],
|
||||
"exports": {
|
||||
".": "./src/index.ts",
|
||||
"./*": "./src/*.ts"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@clack/prompts": "1.0.0-alpha.1",
|
||||
"@effect/platform-node": "catalog:",
|
||||
"@opencode-ai/http-recorder": "workspace:*",
|
||||
"@tsconfig/bun": "catalog:",
|
||||
"@types/bun": "catalog:",
|
||||
"@typescript/native-preview": "catalog:",
|
||||
"typescript": "catalog:"
|
||||
},
|
||||
"dependencies": {
|
||||
"@smithy/eventstream-codec": "4.2.14",
|
||||
"@smithy/util-utf8": "4.2.2",
|
||||
"@opencode-ai/schema": "workspace:*",
|
||||
"aws4fetch": "1.0.20",
|
||||
"effect": "catalog:",
|
||||
"google-auth-library": "10.5.0"
|
||||
}
|
||||
}
|
||||
@@ -1,38 +0,0 @@
|
||||
#!/usr/bin/env bun
|
||||
import { Script } from "@opencode-ai/script"
|
||||
import { $ } from "bun"
|
||||
import { fileURLToPath } from "url"
|
||||
|
||||
const dir = fileURLToPath(new URL("..", import.meta.url))
|
||||
process.chdir(dir)
|
||||
|
||||
async function published(name: string, version: string) {
|
||||
return (await $`npm view ${name}@${version} version`.nothrow()).exitCode === 0
|
||||
}
|
||||
|
||||
await $`bun run build`
|
||||
const originalText = await Bun.file("package.json").text()
|
||||
const pkg = JSON.parse(originalText) as {
|
||||
name: string
|
||||
version: string
|
||||
exports: Record<string, string>
|
||||
}
|
||||
if (await published(pkg.name, pkg.version)) {
|
||||
console.log(`already published ${pkg.name}@${pkg.version}`)
|
||||
} else {
|
||||
for (const [key, value] of Object.entries(pkg.exports)) {
|
||||
const file = value.replace("./src/", "./dist/").replace(".ts", "")
|
||||
// @ts-ignore
|
||||
pkg.exports[key] = {
|
||||
import: file + ".js",
|
||||
types: file + ".d.ts",
|
||||
}
|
||||
}
|
||||
await Bun.write("package.json", JSON.stringify(pkg, null, 2))
|
||||
try {
|
||||
await $`bun pm pack`
|
||||
await $`npm publish *.tgz --tag ${Script.channel} --access public`
|
||||
} finally {
|
||||
await Bun.write("package.json", originalText)
|
||||
}
|
||||
}
|
||||
@@ -1,38 +0,0 @@
|
||||
import { Context, Effect, Layer } from "effect"
|
||||
import { RequestExecutor } from "./route/executor"
|
||||
import type { ImageOptions, ImageRequest, ImageRequestFor, ImageResponse } from "./image"
|
||||
import type { LLMError } from "./schema"
|
||||
|
||||
export type Execute = RequestExecutor.Interface["execute"]
|
||||
|
||||
export interface Interface {
|
||||
readonly generate: <Options extends ImageOptions>(
|
||||
request: ImageRequestFor<Options>,
|
||||
) => Effect.Effect<ImageResponse, LLMError>
|
||||
}
|
||||
|
||||
export class Service extends Context.Service<Service, Interface>()("@opencode/ImageClient") {}
|
||||
|
||||
export const generate = <Options extends ImageOptions>(
|
||||
request: ImageRequestFor<Options>,
|
||||
): Effect.Effect<ImageResponse, LLMError> =>
|
||||
Effect.gen(function* () {
|
||||
const client = yield* Service
|
||||
return yield* client.generate(request)
|
||||
}) as Effect.Effect<ImageResponse, LLMError>
|
||||
|
||||
export const layer: Layer.Layer<Service, never, RequestExecutor.Service> = Layer.effect(
|
||||
Service,
|
||||
Effect.gen(function* () {
|
||||
const executor = yield* RequestExecutor.Service
|
||||
return Service.of({
|
||||
generate: (request) => request.model.route.generate(request, executor.execute),
|
||||
})
|
||||
}),
|
||||
)
|
||||
|
||||
export const ImageClient = {
|
||||
Service,
|
||||
layer,
|
||||
generate,
|
||||
} as const
|
||||
@@ -1,166 +0,0 @@
|
||||
import { Effect, Schema } from "effect"
|
||||
import { HttpOptions, InvalidRequestReason, LLMError, ModelID, ProviderID, ProviderMetadata, Usage } from "./schema"
|
||||
import { ImageClient, Service, type Execute as ImageExecute } from "./image-client"
|
||||
|
||||
export interface ImageRoute<Options extends ImageOptions = ImageOptions> {
|
||||
readonly id: string
|
||||
readonly generate: (
|
||||
request: ImageRequestFor<Options>,
|
||||
execute: ImageExecute,
|
||||
) => Effect.Effect<ImageResponse, LLMError>
|
||||
}
|
||||
|
||||
export type ImageOptions = Record<string, unknown>
|
||||
|
||||
export class ImageModel<Options extends ImageOptions = ImageOptions> {
|
||||
declare protected readonly _Options: (options: Options) => Options
|
||||
readonly id: ModelID
|
||||
readonly provider: ProviderID
|
||||
readonly route: ImageRoute<Options>
|
||||
readonly http?: HttpOptions
|
||||
|
||||
constructor(input: ImageModel.Input<Options>) {
|
||||
this.id = input.id
|
||||
this.provider = input.provider
|
||||
this.route = input.route
|
||||
this.http = input.http
|
||||
}
|
||||
|
||||
static make<Options extends ImageOptions = ImageOptions>(input: ImageModel.MakeInput<Options>) {
|
||||
return new ImageModel<Options>({
|
||||
id: ModelID.make(input.id),
|
||||
provider: ProviderID.make(input.provider),
|
||||
route: input.route,
|
||||
http: input.http,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
export namespace ImageModel {
|
||||
export interface Input<Options extends ImageOptions = ImageOptions> {
|
||||
readonly id: ModelID
|
||||
readonly provider: ProviderID
|
||||
readonly route: ImageRoute<Options>
|
||||
readonly http?: HttpOptions
|
||||
}
|
||||
|
||||
export interface MakeInput<Options extends ImageOptions = ImageOptions>
|
||||
extends Omit<Input<Options>, "id" | "provider"> {
|
||||
readonly id: string | ModelID
|
||||
readonly provider: string | ProviderID
|
||||
}
|
||||
}
|
||||
|
||||
export const ImageModelSchema = Schema.declare((value): value is ImageModel => value instanceof ImageModel, {
|
||||
expected: "Image.Model",
|
||||
})
|
||||
|
||||
const ImageBytesInput = Schema.Struct({
|
||||
type: Schema.Literal("bytes"),
|
||||
data: Schema.Uint8Array,
|
||||
mediaType: Schema.String,
|
||||
})
|
||||
const ImageUrlInput = Schema.Struct({
|
||||
type: Schema.Literal("url"),
|
||||
url: Schema.String,
|
||||
})
|
||||
const ImageFileIDInput = Schema.Struct({
|
||||
type: Schema.Literal("file-id"),
|
||||
id: Schema.String,
|
||||
})
|
||||
const ImageFileURIInput = Schema.Struct({
|
||||
type: Schema.Literal("file-uri"),
|
||||
uri: Schema.String,
|
||||
mediaType: Schema.String,
|
||||
})
|
||||
|
||||
export const ImageInputSchema = Schema.Union([
|
||||
ImageBytesInput,
|
||||
ImageUrlInput,
|
||||
ImageFileIDInput,
|
||||
ImageFileURIInput,
|
||||
]).pipe(Schema.toTaggedUnion("type"))
|
||||
export type ImageInput = Schema.Schema.Type<typeof ImageInputSchema>
|
||||
|
||||
export const ImageInput = {
|
||||
bytes: (data: Uint8Array, mediaType: string): ImageInput => ({ type: "bytes", data, mediaType }),
|
||||
url: (url: string): ImageInput => ({ type: "url", url }),
|
||||
file: (id: string): ImageInput => ({ type: "file-id", id }),
|
||||
fileUri: (uri: string, mediaType: string): ImageInput => ({ type: "file-uri", uri, mediaType }),
|
||||
} as const
|
||||
|
||||
export class ImageRequest extends Schema.Class<ImageRequest>("Image.Request")({
|
||||
model: ImageModelSchema,
|
||||
prompt: Schema.String,
|
||||
images: Schema.optional(Schema.Array(ImageInputSchema)),
|
||||
options: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
|
||||
http: Schema.optional(HttpOptions),
|
||||
}) {
|
||||
declare protected readonly _ImageRequest: void
|
||||
}
|
||||
|
||||
export type ImageRequestFor<Options extends ImageOptions = ImageOptions> = Omit<ImageRequest, "model" | "options"> & {
|
||||
readonly model: ImageModel<Options>
|
||||
readonly options?: Options
|
||||
}
|
||||
|
||||
export type ImageModelOptions<Model> = Model extends ImageModel<infer Options> ? Options : never
|
||||
|
||||
export type ImageRequestInput<Model extends object = ImageModel> = Omit<
|
||||
ConstructorParameters<typeof ImageRequest>[0],
|
||||
"model" | "options" | "http"
|
||||
> & {
|
||||
readonly model: Model
|
||||
readonly options?: NoInfer<ImageModelOptions<Model>>
|
||||
readonly http?: HttpOptions.Input
|
||||
} & (Model extends ImageModel<ImageModelOptions<Model>> ? unknown : never)
|
||||
|
||||
export class GeneratedImage extends Schema.Class<GeneratedImage>("Image.Generated")({
|
||||
mediaType: Schema.String,
|
||||
data: Schema.Union([Schema.String, Schema.Uint8Array]),
|
||||
providerMetadata: Schema.optional(ProviderMetadata),
|
||||
}) {}
|
||||
|
||||
export class ImageResponse extends Schema.Class<ImageResponse>("Image.Response")({
|
||||
images: Schema.Array(GeneratedImage),
|
||||
usage: Schema.optional(Usage),
|
||||
providerMetadata: Schema.optional(ProviderMetadata),
|
||||
}) {
|
||||
get image() {
|
||||
return this.images[0]
|
||||
}
|
||||
}
|
||||
|
||||
export function request<const Model extends object>(
|
||||
input: ImageRequestInput<Model>,
|
||||
): ImageRequestFor<ImageModelOptions<Model>>
|
||||
export function request(input: ImageRequest): ImageRequest
|
||||
export function request(input: ImageRequest | ImageRequestInput) {
|
||||
if (input instanceof ImageRequest) return input
|
||||
return new ImageRequest({
|
||||
...input,
|
||||
model: input.model as unknown as ImageModel,
|
||||
http: input.http === undefined ? undefined : HttpOptions.make(input.http),
|
||||
})
|
||||
}
|
||||
|
||||
export function generate<const Model extends object>(
|
||||
input: ImageRequestInput<Model>,
|
||||
): Effect.Effect<ImageResponse, LLMError, Service>
|
||||
export function generate(input: ImageRequest): Effect.Effect<ImageResponse, LLMError, Service>
|
||||
export function generate(input: ImageRequest | ImageRequestInput) {
|
||||
return Effect.try({
|
||||
try: () => (input instanceof ImageRequest ? input : request(input)),
|
||||
catch: (error) =>
|
||||
new LLMError({
|
||||
module: "Image",
|
||||
method: "generate",
|
||||
reason: new InvalidRequestReason({ message: error instanceof Error ? error.message : String(error) }),
|
||||
}),
|
||||
}).pipe(Effect.flatMap((request) => ImageClient.generate(request as unknown as ImageRequestFor<ImageOptions>)))
|
||||
}
|
||||
|
||||
export const Image = {
|
||||
request,
|
||||
generate,
|
||||
} as const
|
||||
@@ -1 +0,0 @@
|
||||
export * from "./protocols/index"
|
||||
@@ -1,314 +0,0 @@
|
||||
import { Effect, Encoding, Schema } from "effect"
|
||||
import { Headers, HttpClientRequest } from "effect/unstable/http"
|
||||
import {
|
||||
GeneratedImage,
|
||||
ImageModel,
|
||||
ImageResponse,
|
||||
type ImageInput,
|
||||
type ImageRequestFor,
|
||||
type ImageRoute,
|
||||
} from "../image"
|
||||
import { Auth, type Definition as AuthDefinition } from "../route/auth"
|
||||
import {
|
||||
InvalidProviderOutputReason,
|
||||
LLMError,
|
||||
Usage,
|
||||
mergeHttpOptions,
|
||||
mergeJsonRecords,
|
||||
type HttpOptions,
|
||||
type ProviderMetadata,
|
||||
} from "../schema"
|
||||
import { ProviderShared } from "./shared"
|
||||
import { ImageInputs } from "./utils/image-input"
|
||||
|
||||
const ADAPTER = "google-images"
|
||||
export const DEFAULT_BASE_URL = "https://generativelanguage.googleapis.com/v1beta"
|
||||
|
||||
export type GoogleImageString<Known extends string> = Known | (string & {})
|
||||
|
||||
export type GoogleImageOptions = {
|
||||
readonly aspectRatio?: GoogleImageString<
|
||||
"1:1" | "2:3" | "3:2" | "3:4" | "4:3" | "4:5" | "5:4" | "9:16" | "16:9" | "21:9"
|
||||
>
|
||||
readonly imageSize?: GoogleImageString<"1K" | "2K" | "4K">
|
||||
readonly seed?: number
|
||||
readonly thinkingLevel?: GoogleImageString<"MINIMAL" | "LOW" | "MEDIUM" | "HIGH">
|
||||
readonly includeThoughts?: boolean
|
||||
} & Record<string, unknown>
|
||||
|
||||
export type GoogleImageBody = Record<string, unknown> & {
|
||||
readonly contents: ReadonlyArray<{
|
||||
readonly role: "user"
|
||||
readonly parts: ReadonlyArray<Record<string, unknown>>
|
||||
}>
|
||||
readonly generationConfig: Record<string, unknown>
|
||||
}
|
||||
|
||||
const GoogleUsage = Schema.StructWithRest(
|
||||
Schema.Struct({
|
||||
cachedContentTokenCount: Schema.optional(Schema.Number),
|
||||
thoughtsTokenCount: Schema.optional(Schema.Number),
|
||||
promptTokenCount: Schema.optional(Schema.Number),
|
||||
candidatesTokenCount: Schema.optional(Schema.Number),
|
||||
totalTokenCount: Schema.optional(Schema.Number),
|
||||
promptTokensDetails: Schema.optional(Schema.Unknown),
|
||||
candidatesTokensDetails: Schema.optional(Schema.Unknown),
|
||||
}),
|
||||
[Schema.Record(Schema.String, Schema.Unknown)],
|
||||
)
|
||||
|
||||
const GoogleImageResponse = Schema.Struct({
|
||||
candidates: Schema.optional(
|
||||
Schema.Array(
|
||||
Schema.Struct({
|
||||
index: Schema.optional(Schema.Number),
|
||||
content: Schema.optional(
|
||||
Schema.Struct({
|
||||
parts: Schema.Array(
|
||||
Schema.Struct({
|
||||
text: Schema.optional(Schema.String),
|
||||
thought: Schema.optional(Schema.Boolean),
|
||||
thoughtSignature: Schema.optional(Schema.String),
|
||||
inlineData: Schema.optional(
|
||||
Schema.Struct({
|
||||
mimeType: Schema.String,
|
||||
data: Schema.String,
|
||||
}),
|
||||
),
|
||||
}),
|
||||
),
|
||||
}),
|
||||
),
|
||||
finishReason: Schema.optional(Schema.String),
|
||||
finishMessage: Schema.optional(Schema.String),
|
||||
safetyRatings: Schema.optional(Schema.Unknown),
|
||||
citationMetadata: Schema.optional(Schema.Unknown),
|
||||
groundingMetadata: Schema.optional(Schema.Unknown),
|
||||
}),
|
||||
),
|
||||
),
|
||||
usageMetadata: Schema.optional(GoogleUsage),
|
||||
modelVersion: Schema.optional(Schema.String),
|
||||
responseId: Schema.optional(Schema.String),
|
||||
promptFeedback: Schema.optional(Schema.Unknown),
|
||||
})
|
||||
|
||||
export interface ModelInput {
|
||||
readonly id: string
|
||||
readonly auth: AuthDefinition
|
||||
readonly baseURL?: string
|
||||
readonly headers?: Record<string, string>
|
||||
readonly http?: HttpOptions
|
||||
}
|
||||
|
||||
const nativeOptions = (options: GoogleImageOptions | undefined) => {
|
||||
const { aspectRatio, imageSize, seed, thinkingLevel, includeThoughts, ...native } = options ?? {}
|
||||
const image = {
|
||||
aspectRatio,
|
||||
imageSize,
|
||||
}
|
||||
const thinkingConfig = {
|
||||
thinkingLevel,
|
||||
includeThoughts,
|
||||
}
|
||||
return (
|
||||
mergeJsonRecords(
|
||||
{
|
||||
responseModalities: ["IMAGE"],
|
||||
imageConfig: Object.values(image).some((value) => value !== undefined) ? image : undefined,
|
||||
seed,
|
||||
thinkingConfig: Object.values(thinkingConfig).some((value) => value !== undefined) ? thinkingConfig : undefined,
|
||||
},
|
||||
native,
|
||||
) ?? { responseModalities: ["IMAGE"] }
|
||||
)
|
||||
}
|
||||
|
||||
const invalidOutput = (message: string, providerMetadata?: ProviderMetadata) =>
|
||||
new LLMError({
|
||||
module: ADAPTER,
|
||||
method: "generate",
|
||||
reason: new InvalidProviderOutputReason({ message, route: ADAPTER, providerMetadata }),
|
||||
})
|
||||
|
||||
const applyQuery = (url: string, query: Record<string, string> | undefined) => {
|
||||
if (!query) return url
|
||||
const next = new URL(url)
|
||||
Object.entries(query).forEach(([key, value]) => next.searchParams.set(key, value))
|
||||
return next.toString()
|
||||
}
|
||||
|
||||
export const model = (input: ModelInput) => {
|
||||
const route: ImageRoute<GoogleImageOptions> = {
|
||||
id: ADAPTER,
|
||||
generate: Effect.fn("GoogleImages.generate")(function* (request: ImageRequestFor<GoogleImageOptions>, execute) {
|
||||
const imageParts = yield* Effect.forEach(request.images ?? [], googleImagePart)
|
||||
const http = mergeHttpOptions(request.model.http, request.http)
|
||||
const requestBody = mergeJsonRecords(
|
||||
{
|
||||
contents: [{ role: "user", parts: [{ text: request.prompt }, ...imageParts] }],
|
||||
generationConfig: nativeOptions(request.options),
|
||||
},
|
||||
http?.body,
|
||||
) as GoogleImageBody
|
||||
const text = ProviderShared.encodeJson(requestBody)
|
||||
const url = applyQuery(
|
||||
`${(input.baseURL ?? DEFAULT_BASE_URL).replace(/\/$/, "")}/models/${request.model.id}:generateContent`,
|
||||
http?.query,
|
||||
)
|
||||
const headers = yield* Auth.toEffect(input.auth)({
|
||||
request,
|
||||
method: "POST",
|
||||
url,
|
||||
body: text,
|
||||
headers: Headers.fromInput({ ...input.headers, ...http?.headers }),
|
||||
})
|
||||
const response = yield* execute(
|
||||
HttpClientRequest.post(url).pipe(
|
||||
HttpClientRequest.setHeaders(headers),
|
||||
HttpClientRequest.bodyText(text, "application/json"),
|
||||
),
|
||||
)
|
||||
const payload = yield* response.json.pipe(
|
||||
Effect.mapError(() => invalidOutput("Failed to read the Google Images response")),
|
||||
)
|
||||
const decoded = yield* Schema.decodeUnknownEffect(GoogleImageResponse)(payload).pipe(
|
||||
Effect.mapError(() => invalidOutput("Google Images returned an invalid response")),
|
||||
)
|
||||
const candidates = decoded.candidates ?? []
|
||||
const candidateMetadata = candidates.map((candidate, candidateIndex) => ({
|
||||
index: candidate.index ?? candidateIndex,
|
||||
finishReason: candidate.finishReason,
|
||||
finishMessage: candidate.finishMessage,
|
||||
safetyRatings: candidate.safetyRatings,
|
||||
citationMetadata: candidate.citationMetadata,
|
||||
groundingMetadata: candidate.groundingMetadata,
|
||||
parts: (candidate.content?.parts ?? []).map((part) =>
|
||||
part.inlineData === undefined
|
||||
? {
|
||||
type: "text",
|
||||
text: part.text,
|
||||
thought: part.thought,
|
||||
thoughtSignature: part.thoughtSignature,
|
||||
}
|
||||
: {
|
||||
type: "inlineData",
|
||||
mediaType: part.inlineData.mimeType,
|
||||
thought: part.thought,
|
||||
thoughtSignature: part.thoughtSignature,
|
||||
},
|
||||
),
|
||||
}))
|
||||
const encoded = candidates.flatMap((candidate, candidateIndex) =>
|
||||
(candidate.content?.parts ?? []).flatMap((part, partIndex) =>
|
||||
part.inlineData === undefined || part.thought === true
|
||||
? []
|
||||
: [{ candidate, candidateIndex, partIndex, inlineData: part.inlineData }],
|
||||
),
|
||||
)
|
||||
const images = yield* Effect.forEach(encoded, (item) =>
|
||||
Effect.fromResult(Encoding.decodeBase64(item.inlineData.data)).pipe(
|
||||
Effect.mapError(() =>
|
||||
invalidOutput(
|
||||
`Google Images candidate ${item.candidateIndex} part ${item.partIndex} contains invalid base64 data`,
|
||||
),
|
||||
),
|
||||
Effect.map(
|
||||
(data) =>
|
||||
new GeneratedImage({
|
||||
mediaType: item.inlineData.mimeType,
|
||||
data,
|
||||
providerMetadata: {
|
||||
google: {
|
||||
candidateIndex: item.candidate.index ?? item.candidateIndex,
|
||||
partIndex: item.partIndex,
|
||||
finishReason: item.candidate.finishReason,
|
||||
safetyRatings: item.candidate.safetyRatings,
|
||||
citationMetadata: item.candidate.citationMetadata,
|
||||
groundingMetadata: item.candidate.groundingMetadata,
|
||||
thoughtSignature: item.candidate.content?.parts[item.partIndex]?.thoughtSignature,
|
||||
},
|
||||
},
|
||||
}),
|
||||
),
|
||||
),
|
||||
)
|
||||
if (images.length === 0) {
|
||||
const finishReasons = candidates.flatMap((candidate) =>
|
||||
candidate.finishReason === undefined ? [] : [candidate.finishReason],
|
||||
)
|
||||
return yield* invalidOutput(
|
||||
`Google Images returned no final images${
|
||||
finishReasons.length === 0 ? "" : ` (finish reasons: ${finishReasons.join(", ")})`
|
||||
}; inspect reason.providerMetadata.google for prompt feedback and candidate details`,
|
||||
{
|
||||
google: {
|
||||
promptFeedback: decoded.promptFeedback,
|
||||
candidates: candidateMetadata,
|
||||
},
|
||||
},
|
||||
)
|
||||
}
|
||||
const usage = decoded.usageMetadata
|
||||
const outputTokens =
|
||||
usage?.candidatesTokenCount === undefined
|
||||
? undefined
|
||||
: usage.candidatesTokenCount + (usage.thoughtsTokenCount ?? 0)
|
||||
return new ImageResponse({
|
||||
images,
|
||||
usage:
|
||||
usage === undefined
|
||||
? undefined
|
||||
: new Usage({
|
||||
inputTokens: usage.promptTokenCount,
|
||||
outputTokens,
|
||||
nonCachedInputTokens: ProviderShared.subtractTokens(
|
||||
usage.promptTokenCount,
|
||||
usage.cachedContentTokenCount,
|
||||
),
|
||||
cacheReadInputTokens: usage.cachedContentTokenCount,
|
||||
reasoningTokens: usage.thoughtsTokenCount,
|
||||
totalTokens: ProviderShared.totalTokens(usage.promptTokenCount, outputTokens, usage.totalTokenCount),
|
||||
providerMetadata: { google: usage },
|
||||
}),
|
||||
providerMetadata: {
|
||||
google: {
|
||||
modelVersion: decoded.modelVersion,
|
||||
responseId: decoded.responseId,
|
||||
promptFeedback: decoded.promptFeedback,
|
||||
candidates: candidateMetadata,
|
||||
},
|
||||
},
|
||||
})
|
||||
}),
|
||||
}
|
||||
return ImageModel.make<GoogleImageOptions>({ id: input.id, provider: "google", route, http: input.http })
|
||||
}
|
||||
|
||||
const googleImagePart = (image: ImageInput): Effect.Effect<Record<string, unknown>, LLMError> => {
|
||||
if (image.type === "bytes")
|
||||
return Effect.succeed({ inlineData: { mimeType: image.mediaType, data: Encoding.encodeBase64(image.data) } })
|
||||
if (image.type === "file-uri") return Effect.succeed({ fileData: { mimeType: image.mediaType, fileUri: image.uri } })
|
||||
if (image.type === "url")
|
||||
return ImageInputs.decodeDataUrl(image.url, ADAPTER).pipe(
|
||||
Effect.flatMap((decoded) => {
|
||||
if (decoded === undefined)
|
||||
return Effect.fail(
|
||||
ImageInputs.invalid(
|
||||
ADAPTER,
|
||||
"Google generateContent does not fetch public image URLs; use bytes, a data URL, or a Gemini file URI",
|
||||
),
|
||||
)
|
||||
return Effect.succeed({
|
||||
inlineData: { mimeType: decoded.mediaType, data: Encoding.encodeBase64(decoded.data) },
|
||||
})
|
||||
}),
|
||||
)
|
||||
return Effect.fail(
|
||||
ImageInputs.invalid(ADAPTER, "Google generateContent requires Gemini file URIs rather than provider file IDs"),
|
||||
)
|
||||
}
|
||||
|
||||
export const GoogleImages = {
|
||||
model,
|
||||
} as const
|
||||
@@ -1,22 +0,0 @@
|
||||
import { Route, type RouteRoutedModelInput } from "../route/client"
|
||||
import { Endpoint } from "../route/endpoint"
|
||||
import { OpenResponses } from "./open-responses"
|
||||
|
||||
const ADAPTER = "openai-compatible-responses"
|
||||
|
||||
export type OpenAICompatibleResponsesModelInput = RouteRoutedModelInput
|
||||
|
||||
/**
|
||||
* Deployment adapter for providers that expose an Open Responses-compatible
|
||||
* `/responses` endpoint. Provider helpers configure identity, endpoint, and
|
||||
* auth while the semantic protocol remains provider-neutral.
|
||||
*/
|
||||
export const route = Route.make({
|
||||
id: ADAPTER,
|
||||
providerMetadataKey: "openresponses",
|
||||
protocol: OpenResponses.protocol,
|
||||
endpoint: Endpoint.path(OpenResponses.PATH),
|
||||
transport: OpenResponses.httpTransport,
|
||||
})
|
||||
|
||||
export * as OpenAICompatibleResponses from "./openai-compatible-responses"
|
||||
@@ -1,270 +0,0 @@
|
||||
import { Effect, Encoding, Schema } from "effect"
|
||||
import { Headers, HttpClientRequest, HttpClientResponse } from "effect/unstable/http"
|
||||
import {
|
||||
ImageModel,
|
||||
GeneratedImage,
|
||||
ImageResponse,
|
||||
type ImageInput,
|
||||
type ImageRequestFor,
|
||||
type ImageRoute,
|
||||
} from "../image"
|
||||
import { Auth, type Definition as AuthDefinition } from "../route/auth"
|
||||
import {
|
||||
InvalidProviderOutputReason,
|
||||
LLMError,
|
||||
Usage,
|
||||
mergeHttpOptions,
|
||||
mergeJsonRecords,
|
||||
type HttpOptions,
|
||||
} from "../schema"
|
||||
import { ProviderShared } from "./shared"
|
||||
import { ImageInputs } from "./utils/image-input"
|
||||
import { OpenAIImage } from "./utils/openai-image"
|
||||
|
||||
const ADAPTER = "openai-images"
|
||||
export const DEFAULT_BASE_URL = "https://api.openai.com/v1"
|
||||
export const PATH = "/images/generations"
|
||||
export const EDIT_PATH = "/images/edits"
|
||||
|
||||
export type OpenAIImageString<Known extends string> = Known | (string & {})
|
||||
|
||||
export type OpenAIImageOptions = {
|
||||
readonly mask?: ImageInput
|
||||
readonly n?: number
|
||||
readonly size?: OpenAIImageString<
|
||||
"auto" | "256x256" | "512x512" | "1024x1024" | "1536x1024" | "1024x1536" | "1792x1024" | "1024x1792"
|
||||
>
|
||||
readonly quality?: OpenAIImageString<"auto" | "low" | "medium" | "high" | "standard" | "hd">
|
||||
readonly background?: OpenAIImageString<"auto" | "opaque" | "transparent">
|
||||
readonly moderation?: OpenAIImageString<"auto" | "low">
|
||||
readonly outputFormat?: OpenAIImageString<"png" | "jpeg" | "webp">
|
||||
readonly outputCompression?: number
|
||||
} & Record<string, unknown>
|
||||
|
||||
export type OpenAIImageBody = Record<string, unknown> & {
|
||||
readonly model: string
|
||||
readonly prompt: string
|
||||
}
|
||||
|
||||
const OpenAIImageResponse = Schema.Struct({
|
||||
data: Schema.Array(
|
||||
Schema.Struct({
|
||||
b64_json: Schema.optional(Schema.String),
|
||||
url: Schema.optional(Schema.String),
|
||||
revised_prompt: Schema.optional(Schema.String),
|
||||
}),
|
||||
),
|
||||
output_format: Schema.optional(Schema.String),
|
||||
usage: Schema.optional(
|
||||
Schema.Struct({
|
||||
input_tokens: Schema.optional(Schema.Number),
|
||||
output_tokens: Schema.optional(Schema.Number),
|
||||
total_tokens: Schema.optional(Schema.Number),
|
||||
input_tokens_details: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
|
||||
output_tokens_details: Schema.optional(Schema.Record(Schema.String, Schema.Unknown)),
|
||||
}),
|
||||
),
|
||||
})
|
||||
|
||||
export interface ModelInput {
|
||||
readonly id: string
|
||||
readonly auth: AuthDefinition
|
||||
readonly baseURL?: string
|
||||
readonly headers?: Record<string, string>
|
||||
readonly http?: HttpOptions
|
||||
}
|
||||
|
||||
const nativeOptions = (options: OpenAIImageOptions | undefined) => {
|
||||
if (!options) return undefined
|
||||
const { mask: _, outputFormat, outputCompression, ...native } = options
|
||||
return {
|
||||
output_format: outputFormat,
|
||||
output_compression: outputCompression,
|
||||
...native,
|
||||
}
|
||||
}
|
||||
|
||||
const invalidOutput = (message: string) =>
|
||||
new LLMError({
|
||||
module: ADAPTER,
|
||||
method: "generate",
|
||||
reason: new InvalidProviderOutputReason({ message, route: ADAPTER }),
|
||||
})
|
||||
|
||||
const applyQuery = (url: string, query: Record<string, string> | undefined) => {
|
||||
if (!query) return url
|
||||
const next = new URL(url)
|
||||
Object.entries(query).forEach(([key, value]) => next.searchParams.set(key, value))
|
||||
return next.toString()
|
||||
}
|
||||
|
||||
export const model = (input: ModelInput) => {
|
||||
const route: ImageRoute<OpenAIImageOptions> = {
|
||||
id: ADAPTER,
|
||||
generate: Effect.fn("OpenAIImages.generate")(function* (request: ImageRequestFor<OpenAIImageOptions>, execute) {
|
||||
const mask = request.options?.mask
|
||||
if (mask !== undefined && (request.images?.length ?? 0) === 0)
|
||||
return yield* ImageInputs.invalid(ADAPTER, "An OpenAI image mask requires at least one input image")
|
||||
const http = mergeHttpOptions(request.model.http, request.http)
|
||||
const sourceImages = request.images ?? []
|
||||
const multipartImages = yield* Effect.forEach(sourceImages, (image) => {
|
||||
if (image.type === "bytes") return Effect.succeed({ data: image.data, mediaType: image.mediaType })
|
||||
if (image.type === "url") return ImageInputs.decodeDataUrl(image.url, ADAPTER)
|
||||
return Effect.succeed(undefined)
|
||||
})
|
||||
const multipartMask =
|
||||
mask === undefined
|
||||
? undefined
|
||||
: mask.type === "bytes"
|
||||
? { data: mask.data, mediaType: mask.mediaType }
|
||||
: mask.type === "url"
|
||||
? yield* ImageInputs.decodeDataUrl(mask.url, ADAPTER)
|
||||
: undefined
|
||||
const useMultipart =
|
||||
sourceImages.length > 0 &&
|
||||
multipartImages.every((image) => image !== undefined) &&
|
||||
(mask === undefined || multipartMask !== undefined)
|
||||
const path = sourceImages.length === 0 ? PATH : EDIT_PATH
|
||||
const url = applyQuery(`${(input.baseURL ?? DEFAULT_BASE_URL).replace(/\/$/, "")}${path}`, http?.query)
|
||||
|
||||
if (useMultipart) {
|
||||
const form = new FormData()
|
||||
form.append("model", request.model.id)
|
||||
form.append("prompt", request.prompt)
|
||||
Object.entries(mergeJsonRecords(nativeOptions(request.options), http?.body) ?? {}).forEach(([key, value]) => {
|
||||
if (["model", "prompt", "image", "image[]", "images", "mask"].includes(key)) return
|
||||
form.append(key, typeof value === "string" ? value : ProviderShared.encodeJson(value))
|
||||
})
|
||||
multipartImages.forEach((image, index) => {
|
||||
if (image === undefined) return
|
||||
form.append("image[]", imageBlob(image.data, image.mediaType), `image-${index}`)
|
||||
})
|
||||
if (multipartMask !== undefined)
|
||||
form.append("mask", imageBlob(multipartMask.data, multipartMask.mediaType), "mask")
|
||||
const headers = yield* Auth.toEffect(input.auth)({
|
||||
request,
|
||||
method: "POST",
|
||||
url,
|
||||
body: "[multipart/form-data]",
|
||||
headers: Headers.remove(Headers.fromInput({ ...input.headers, ...http?.headers }), "content-type"),
|
||||
})
|
||||
const response = yield* execute(
|
||||
HttpClientRequest.post(url).pipe(HttpClientRequest.setHeaders(headers), HttpClientRequest.bodyFormData(form)),
|
||||
)
|
||||
return yield* parseResponse(response, request.options, http?.body)
|
||||
}
|
||||
|
||||
const references = sourceImages.map((image) => {
|
||||
if (image.type === "bytes") return { image_url: ImageInputs.dataUrl(image) }
|
||||
if (image.type === "url") return { image_url: image.url }
|
||||
if (image.type === "file-id") return { file_id: image.id }
|
||||
return undefined
|
||||
})
|
||||
if (references.some((image) => image === undefined))
|
||||
return yield* ImageInputs.invalid(ADAPTER, "OpenAI Images accepts image URLs, data URLs, bytes, and file IDs")
|
||||
const maskReference =
|
||||
mask === undefined
|
||||
? undefined
|
||||
: mask.type === "bytes"
|
||||
? { image_url: ImageInputs.dataUrl(mask) }
|
||||
: mask.type === "url"
|
||||
? { image_url: mask.url }
|
||||
: mask.type === "file-id"
|
||||
? { file_id: mask.id }
|
||||
: undefined
|
||||
if (mask !== undefined && maskReference === undefined)
|
||||
return yield* ImageInputs.invalid(ADAPTER, "OpenAI Images accepts masks as URLs, data URLs, bytes, or file IDs")
|
||||
const requestBody = mergeJsonRecords(
|
||||
{
|
||||
model: request.model.id,
|
||||
prompt: request.prompt,
|
||||
images: references.length === 0 ? undefined : references,
|
||||
mask: maskReference,
|
||||
},
|
||||
nativeOptions(request.options),
|
||||
http?.body,
|
||||
) as OpenAIImageBody
|
||||
const text = ProviderShared.encodeJson(requestBody)
|
||||
const headers = yield* Auth.toEffect(input.auth)({
|
||||
request,
|
||||
method: "POST",
|
||||
url,
|
||||
body: text,
|
||||
headers: Headers.fromInput({ ...input.headers, ...http?.headers }),
|
||||
})
|
||||
const response = yield* execute(
|
||||
HttpClientRequest.post(url).pipe(
|
||||
HttpClientRequest.setHeaders(headers),
|
||||
HttpClientRequest.bodyText(text, "application/json"),
|
||||
),
|
||||
)
|
||||
return yield* parseResponse(response, request.options, http?.body)
|
||||
}),
|
||||
}
|
||||
return ImageModel.make<OpenAIImageOptions>({ id: input.id, provider: "openai", route, http: input.http })
|
||||
}
|
||||
|
||||
const parseResponse = Effect.fn("OpenAIImages.parseResponse")(function* (
|
||||
response: HttpClientResponse.HttpClientResponse,
|
||||
options: OpenAIImageOptions | undefined,
|
||||
overlay: Record<string, unknown> | undefined,
|
||||
) {
|
||||
const payload = yield* response.json.pipe(
|
||||
Effect.mapError(() => invalidOutput("Failed to read the OpenAI Images response")),
|
||||
)
|
||||
const decoded = yield* Schema.decodeUnknownEffect(OpenAIImageResponse)(payload).pipe(
|
||||
Effect.mapError(() => invalidOutput("OpenAI Images returned an invalid response")),
|
||||
)
|
||||
const requestBody = mergeJsonRecords(nativeOptions(options), overlay)
|
||||
const format =
|
||||
decoded.output_format ?? (typeof requestBody?.output_format === "string" ? requestBody.output_format : "png")
|
||||
const images = yield* Effect.forEach(decoded.data, (item, index) => {
|
||||
if (item.b64_json)
|
||||
return Effect.fromResult(Encoding.decodeBase64(item.b64_json)).pipe(
|
||||
Effect.mapError(() => invalidOutput(`OpenAI Images result ${index} contains invalid base64 data`)),
|
||||
Effect.map(
|
||||
(data) =>
|
||||
new GeneratedImage({
|
||||
mediaType: `image/${format}`,
|
||||
data,
|
||||
providerMetadata:
|
||||
item.revised_prompt === undefined ? undefined : { openai: { revisedPrompt: item.revised_prompt } },
|
||||
}),
|
||||
),
|
||||
)
|
||||
if (item.url)
|
||||
return Effect.succeed(
|
||||
new GeneratedImage({
|
||||
mediaType: `image/${format}`,
|
||||
data: item.url,
|
||||
providerMetadata:
|
||||
item.revised_prompt === undefined ? undefined : { openai: { revisedPrompt: item.revised_prompt } },
|
||||
}),
|
||||
)
|
||||
return Effect.fail(invalidOutput(`OpenAI Images result ${index} has neither image data nor a URL`))
|
||||
})
|
||||
if (images.length === 0) return yield* invalidOutput("OpenAI Images returned no images")
|
||||
return new ImageResponse({
|
||||
images,
|
||||
usage:
|
||||
decoded.usage === undefined
|
||||
? undefined
|
||||
: new Usage({
|
||||
inputTokens: decoded.usage.input_tokens,
|
||||
outputTokens: decoded.usage.output_tokens,
|
||||
totalTokens: decoded.usage.total_tokens,
|
||||
providerMetadata: { openai: decoded.usage },
|
||||
}),
|
||||
providerMetadata: { openai: { outputFormat: format } },
|
||||
})
|
||||
})
|
||||
|
||||
const imageBlob = (data: Uint8Array, mediaType: string) => {
|
||||
const buffer = new ArrayBuffer(data.byteLength)
|
||||
new Uint8Array(buffer).set(data)
|
||||
return new Blob([buffer], { type: mediaType })
|
||||
}
|
||||
|
||||
export const OpenAIImages = {
|
||||
model,
|
||||
} as const
|
||||
@@ -1,278 +0,0 @@
|
||||
import { Effect, Encoding, Schema } from "effect"
|
||||
import { Route } from "../route/client"
|
||||
import { Auth } from "../route/auth"
|
||||
import { Endpoint } from "../route/endpoint"
|
||||
import { Protocol } from "../route/protocol"
|
||||
import { HttpTransport, WebSocketTransport } from "../route/transport"
|
||||
import { LLMEvent, LLMRequest, type JsonSchema, type ToolDefinition } from "../schema"
|
||||
import { OpenResponses } from "./open-responses"
|
||||
import { optionalArray, ProviderShared } from "./shared"
|
||||
import { Lifecycle } from "./utils/lifecycle"
|
||||
import { OpenAIImage } from "./utils/openai-image"
|
||||
import { ToolSchemaProjection } from "./utils/tool-schema"
|
||||
|
||||
const ADAPTER = "openai-responses"
|
||||
const NAME = "OpenAI Responses"
|
||||
export const DEFAULT_BASE_URL = "https://api.openai.com/v1"
|
||||
export const PATH = OpenResponses.PATH
|
||||
|
||||
const OpenAIResponsesImageGenerationTool = Schema.Struct({
|
||||
type: Schema.tag("image_generation"),
|
||||
action: Schema.optional(Schema.Literals(["auto", "generate", "edit"])),
|
||||
background: Schema.optional(Schema.Literals(["auto", "opaque", "transparent"])),
|
||||
input_fidelity: Schema.optional(Schema.Literals(["low", "high"])),
|
||||
output_compression: Schema.optional(Schema.Int.check(Schema.isBetween({ minimum: 0, maximum: 100 }))),
|
||||
output_format: Schema.optional(Schema.Literals(["png", "jpeg", "webp"])),
|
||||
partial_images: Schema.optional(Schema.Int.check(Schema.isGreaterThanOrEqualTo(0))),
|
||||
quality: Schema.optional(Schema.Literals(["auto", "low", "medium", "high"])),
|
||||
size: Schema.optional(OpenAIImage.Size),
|
||||
})
|
||||
|
||||
const OpenAIResponsesTools = Schema.Union([OpenResponses.Tool, OpenAIResponsesImageGenerationTool])
|
||||
|
||||
const OpenAIResponsesToolChoice = Schema.Union([
|
||||
OpenResponses.ToolChoice,
|
||||
Schema.Struct({ type: Schema.tag("image_generation") }),
|
||||
])
|
||||
|
||||
const OpenAIResponsesCoreFields = {
|
||||
...OpenResponses.coreFields,
|
||||
tools: optionalArray(OpenAIResponsesTools),
|
||||
tool_choice: Schema.optional(OpenAIResponsesToolChoice),
|
||||
}
|
||||
|
||||
const OpenAIResponsesBody = Schema.Struct({
|
||||
...OpenAIResponsesCoreFields,
|
||||
stream: Schema.Literal(true),
|
||||
})
|
||||
export type OpenAIResponsesBody = Schema.Schema.Type<typeof OpenAIResponsesBody>
|
||||
|
||||
const OpenAIResponsesWebSocketMessage = Schema.StructWithRest(
|
||||
Schema.Struct({
|
||||
type: Schema.tag("response.create"),
|
||||
...OpenAIResponsesCoreFields,
|
||||
}),
|
||||
[Schema.Record(Schema.String, Schema.Unknown)],
|
||||
)
|
||||
type OpenAIResponsesWebSocketMessage = Schema.Schema.Type<typeof OpenAIResponsesWebSocketMessage>
|
||||
const encodeWebSocketMessage = Schema.encodeSync(Schema.fromJsonString(OpenAIResponsesWebSocketMessage))
|
||||
|
||||
const extension = {
|
||||
id: ADAPTER,
|
||||
name: NAME,
|
||||
lowerMedia: ({ part, media, request }) => {
|
||||
if (request.model.provider !== "xai" || media.mime !== "application/pdf") return undefined
|
||||
return {
|
||||
type: "input_file",
|
||||
filename: part.filename ?? "document.pdf",
|
||||
file_data: media.base64,
|
||||
mime_type: media.mime,
|
||||
}
|
||||
},
|
||||
} satisfies OpenResponses.Extension
|
||||
|
||||
const nativeImageToolInput = (tool: ToolDefinition) => {
|
||||
const native = tool.native?.openai
|
||||
return ProviderShared.isRecord(native) && native.type === "image_generation" ? native : undefined
|
||||
}
|
||||
|
||||
const nativeImageTool = (tool: ToolDefinition) => {
|
||||
const native = nativeImageToolInput(tool)
|
||||
return Schema.is(OpenAIResponsesImageGenerationTool)(native) ? native : undefined
|
||||
}
|
||||
|
||||
const lowerTool = Effect.fn("OpenAIResponses.lowerTool")(function* (tool: ToolDefinition, inputSchema: JsonSchema) {
|
||||
const native = nativeImageToolInput(tool)
|
||||
if (native !== undefined) {
|
||||
if (Schema.is(OpenAIResponsesImageGenerationTool)(native)) return native
|
||||
return yield* ProviderShared.invalidRequest("OpenAI Responses image generation tool options are invalid")
|
||||
}
|
||||
return yield* OpenResponses.lowerTool(NAME, tool, inputSchema)
|
||||
})
|
||||
|
||||
const lowerToolChoice = (toolChoice: NonNullable<LLMRequest["toolChoice"]>, tools: ReadonlyArray<ToolDefinition>) =>
|
||||
ProviderShared.matchToolChoice(NAME, toolChoice, {
|
||||
auto: () => "auto" as const,
|
||||
none: () => "none" as const,
|
||||
required: () => "required" as const,
|
||||
tool: (name) =>
|
||||
tools.some((tool) => tool.name === name && nativeImageTool(tool) !== undefined)
|
||||
? ({ type: "image_generation" } as const)
|
||||
: { type: "function" as const, name },
|
||||
})
|
||||
|
||||
const fromRequest = Effect.fn("OpenAIResponses.fromRequest")(function* (request: LLMRequest) {
|
||||
const body = yield* OpenResponses.fromRequest(
|
||||
LLMRequest.update(request, { tools: [], toolChoice: undefined }),
|
||||
extension,
|
||||
)
|
||||
const toolSchemaCompatibility = request.model.compatibility?.toolSchema
|
||||
return {
|
||||
...body,
|
||||
tools:
|
||||
request.tools.length === 0
|
||||
? undefined
|
||||
: yield* Effect.forEach(request.tools, (tool) =>
|
||||
lowerTool(tool, ToolSchemaProjection.modelCompatibility(tool.inputSchema, toolSchemaCompatibility)),
|
||||
),
|
||||
tool_choice: request.toolChoice ? yield* lowerToolChoice(request.toolChoice, request.tools) : undefined,
|
||||
} satisfies OpenAIResponsesBody
|
||||
})
|
||||
|
||||
type HostedToolData = OpenResponses.StreamItem & {
|
||||
readonly id: string
|
||||
readonly status?: string
|
||||
readonly action?: unknown
|
||||
readonly queries?: unknown
|
||||
readonly results?: unknown
|
||||
readonly code?: string
|
||||
readonly container_id?: string
|
||||
readonly outputs?: unknown
|
||||
readonly server_label?: string
|
||||
readonly output?: unknown
|
||||
readonly result?: string
|
||||
readonly output_format?: "png" | "jpeg" | "webp"
|
||||
readonly error?: unknown
|
||||
}
|
||||
|
||||
const HOSTED_TOOLS = {
|
||||
web_search_call: { name: "web_search", input: (item) => item.action ?? {} },
|
||||
web_search_preview_call: { name: "web_search_preview", input: (item) => item.action ?? {} },
|
||||
file_search_call: { name: "file_search", input: (item) => ({ queries: item.queries ?? [] }) },
|
||||
code_interpreter_call: {
|
||||
name: "code_interpreter",
|
||||
input: (item) => ({ code: item.code, container_id: item.container_id }),
|
||||
},
|
||||
computer_use_call: { name: "computer_use", input: (item) => item.action ?? {} },
|
||||
image_generation_call: { name: "image_generation", input: () => ({}) },
|
||||
mcp_call: {
|
||||
name: "mcp",
|
||||
input: (item) => ({ server_label: item.server_label, name: item.name, arguments: item.arguments }),
|
||||
},
|
||||
local_shell_call: { name: "local_shell", input: (item) => item.action ?? {} },
|
||||
} as const satisfies Record<string, { readonly name: string; readonly input: (item: HostedToolData) => unknown }>
|
||||
|
||||
type HostedToolType = keyof typeof HOSTED_TOOLS
|
||||
type HostedToolItem = HostedToolData & { readonly type: HostedToolType }
|
||||
|
||||
const isHostedToolItem = (item: OpenResponses.StreamItem): item is HostedToolItem =>
|
||||
item.type in HOSTED_TOOLS && typeof item.id === "string" && item.id.length > 0
|
||||
|
||||
const hostedToolResult = Effect.fn("OpenAIResponses.hostedToolResult")(function* (item: HostedToolItem) {
|
||||
const isError = item.error !== undefined && item.error !== null
|
||||
if (item.type === "image_generation_call" && item.result) {
|
||||
yield* Effect.fromResult(Encoding.decodeBase64(item.result)).pipe(
|
||||
Effect.mapError(() => ProviderShared.eventError(ADAPTER, "OpenAI Responses returned invalid image base64")),
|
||||
)
|
||||
const format = item.output_format ?? "png"
|
||||
return {
|
||||
type: "content" as const,
|
||||
value: [
|
||||
{
|
||||
type: "file" as const,
|
||||
uri: `data:image/${format};base64,${item.result}`,
|
||||
mime: `image/${format}`,
|
||||
},
|
||||
],
|
||||
}
|
||||
}
|
||||
return isError ? { type: "error" as const, value: item.error } : { type: "json" as const, value: item }
|
||||
})
|
||||
|
||||
const onHostedToolDone = Effect.fn("OpenAIResponses.onHostedToolDone")(function* (
|
||||
state: OpenResponses.ParserState,
|
||||
item: HostedToolItem,
|
||||
) {
|
||||
const tool = HOSTED_TOOLS[item.type]
|
||||
const providerMetadata = OpenResponses.providerMetadata(state, { itemId: item.id })
|
||||
const events: LLMEvent[] = []
|
||||
const lifecycle = Lifecycle.stepStart(state.lifecycle, events)
|
||||
events.push(
|
||||
LLMEvent.toolCall({
|
||||
id: item.id,
|
||||
name: tool.name,
|
||||
input: tool.input(item),
|
||||
providerExecuted: true,
|
||||
providerMetadata,
|
||||
}),
|
||||
LLMEvent.toolResult({
|
||||
id: item.id,
|
||||
name: tool.name,
|
||||
result: yield* hostedToolResult(item),
|
||||
providerExecuted: true,
|
||||
providerMetadata,
|
||||
}),
|
||||
)
|
||||
return [{ ...state, lifecycle }, events] satisfies OpenResponses.StepResult
|
||||
})
|
||||
|
||||
const step = (state: OpenResponses.ParserState, event: OpenResponses.Event) => {
|
||||
if (event.type === "response.reasoning_text.delta" || event.type === "response.reasoning_summary.delta")
|
||||
return Effect.succeed(OpenResponses.onReasoningDelta(state, event))
|
||||
if (event.type === "response.reasoning_text.done" || event.type === "response.reasoning_summary.done")
|
||||
return Effect.succeed(OpenResponses.onReasoningDone(state, event))
|
||||
if (event.type === "response.output_item.done" && event.item && isHostedToolItem(event.item))
|
||||
return onHostedToolDone(state, event.item)
|
||||
return OpenResponses.step(state, event)
|
||||
}
|
||||
|
||||
export const protocol = Protocol.make({
|
||||
id: ADAPTER,
|
||||
body: {
|
||||
schema: OpenAIResponsesBody,
|
||||
from: fromRequest,
|
||||
},
|
||||
stream: {
|
||||
event: OpenResponses.protocol.stream.event,
|
||||
initial: (request) => OpenResponses.initial(request, extension),
|
||||
step,
|
||||
terminal: OpenResponses.terminal,
|
||||
},
|
||||
})
|
||||
|
||||
const endpoint = Endpoint.path<OpenAIResponsesBody>(PATH, { baseURL: DEFAULT_BASE_URL })
|
||||
const auth = Auth.none
|
||||
|
||||
export const httpTransport = HttpTransport.sseJson.with<OpenAIResponsesBody>()
|
||||
|
||||
export const route = Route.make({
|
||||
id: ADAPTER,
|
||||
provider: "openai",
|
||||
providerMetadataKey: "openai",
|
||||
protocol,
|
||||
endpoint,
|
||||
auth,
|
||||
transport: httpTransport,
|
||||
defaults: { providerOptions: { openai: { store: false } } },
|
||||
})
|
||||
|
||||
const decodeWebSocketMessage = ProviderShared.validateWith(Schema.decodeUnknownEffect(OpenAIResponsesWebSocketMessage))
|
||||
|
||||
const webSocketMessage = (body: OpenAIResponsesBody | Record<string, unknown>) =>
|
||||
Effect.gen(function* () {
|
||||
if (!ProviderShared.isRecord(body))
|
||||
return yield* ProviderShared.invalidRequest("OpenAI Responses WebSocket body must be a JSON object")
|
||||
const { stream: _stream, ...message } = body
|
||||
return yield* decodeWebSocketMessage({ ...message, type: "response.create" })
|
||||
})
|
||||
|
||||
export const webSocketTransport = WebSocketTransport.jsonTransport.with<
|
||||
OpenAIResponsesBody,
|
||||
OpenAIResponsesWebSocketMessage
|
||||
>({
|
||||
toMessage: webSocketMessage,
|
||||
encodeMessage: encodeWebSocketMessage,
|
||||
})
|
||||
|
||||
export const webSocketRoute = Route.make({
|
||||
id: `${ADAPTER}-websocket`,
|
||||
provider: "openai",
|
||||
providerMetadataKey: "openai",
|
||||
protocol,
|
||||
endpoint,
|
||||
auth,
|
||||
transport: webSocketTransport,
|
||||
defaults: { providerOptions: { openai: { store: false } } },
|
||||
})
|
||||
|
||||
export * as OpenAIResponses from "./openai-responses"
|
||||
@@ -1,34 +0,0 @@
|
||||
import { Effect, Encoding } from "effect"
|
||||
import type { ImageInput } from "../../image"
|
||||
import { InvalidRequestReason, LLMError } from "../../schema"
|
||||
|
||||
const invalid = (module: string, message: string) =>
|
||||
new LLMError({
|
||||
module,
|
||||
method: "generate",
|
||||
reason: new InvalidRequestReason({ message }),
|
||||
})
|
||||
|
||||
export const dataUrl = (input: Extract<ImageInput, { readonly type: "bytes" }>) =>
|
||||
`data:${input.mediaType};base64,${Encoding.encodeBase64(input.data)}`
|
||||
|
||||
export const decodeDataUrl = (
|
||||
url: string,
|
||||
module: string,
|
||||
): Effect.Effect<{ readonly mediaType: string; readonly data: Uint8Array } | undefined, LLMError> => {
|
||||
if (!url.startsWith("data:")) return Effect.succeed(undefined)
|
||||
const match = /^data:([^;,]+);base64,(.*)$/s.exec(url)
|
||||
if (!match) return Effect.fail(invalid(module, "Image data URLs must contain a MIME type and base64 data"))
|
||||
return Effect.fromResult(Encoding.decodeBase64(match[2])).pipe(
|
||||
Effect.mapError(() => invalid(module, "Image data URL contains invalid base64 data")),
|
||||
Effect.map((data) => ({ mediaType: match[1], data })),
|
||||
)
|
||||
}
|
||||
|
||||
export const invalidImageInput = invalid
|
||||
|
||||
export const ImageInputs = {
|
||||
dataUrl,
|
||||
decodeDataUrl,
|
||||
invalid: invalidImageInput,
|
||||
} as const
|
||||
@@ -1,65 +0,0 @@
|
||||
import { Schema } from "effect"
|
||||
import { TextVerbosity, type LLMRequest } from "../../schema"
|
||||
|
||||
export const ResponseIncludables = [
|
||||
"file_search_call.results",
|
||||
"web_search_call.results",
|
||||
"web_search_call.action.sources",
|
||||
"message.input_image.image_url",
|
||||
"computer_call_output.output.image_url",
|
||||
"code_interpreter_call.outputs",
|
||||
"reasoning.encrypted_content",
|
||||
"message.output_text.logprobs",
|
||||
] as const
|
||||
export type ResponseIncludable = (typeof ResponseIncludables)[number]
|
||||
|
||||
export const ServiceTiers = ["auto", "default", "flex", "priority"] as const
|
||||
export type ServiceTier = (typeof ServiceTiers)[number]
|
||||
|
||||
const TEXT_VERBOSITY = new Set<string>(["low", "medium", "high"])
|
||||
const INCLUDABLES = new Set<string>(ResponseIncludables)
|
||||
const SERVICE_TIERS = new Set<string>(ServiceTiers)
|
||||
|
||||
const isTextVerbosity = (value: unknown): value is Schema.Schema.Type<typeof TextVerbosity> =>
|
||||
typeof value === "string" && TEXT_VERBOSITY.has(value)
|
||||
|
||||
const isServiceTier = (value: unknown): value is ServiceTier => typeof value === "string" && SERVICE_TIERS.has(value)
|
||||
|
||||
export const ReasoningEffort = Schema.String
|
||||
export const TextVerbositySchema = TextVerbosity
|
||||
export const ResponseIncludableSchema = Schema.Literals(ResponseIncludables)
|
||||
export const ServiceTierSchema = Schema.Literals(ServiceTiers)
|
||||
|
||||
export interface Resolved {
|
||||
readonly instructions?: string
|
||||
readonly store?: boolean
|
||||
readonly promptCacheKey?: string
|
||||
readonly reasoningEffort?: string
|
||||
readonly reasoningSummary?: "auto" | "concise" | "detailed"
|
||||
readonly include?: ReadonlyArray<ResponseIncludable>
|
||||
readonly textVerbosity?: Schema.Schema.Type<typeof TextVerbosity>
|
||||
readonly serviceTier?: ServiceTier
|
||||
}
|
||||
|
||||
export const resolve = (request: LLMRequest): Resolved => {
|
||||
const input = request.providerOptions?.[request.model.route.providerMetadataKey ?? "openresponses"]
|
||||
const include = Array.isArray(input?.include)
|
||||
? input.include.filter((entry): entry is ResponseIncludable => INCLUDABLES.has(entry))
|
||||
: []
|
||||
const reasoningSummary = input?.reasoningSummary
|
||||
return {
|
||||
instructions: typeof input?.instructions === "string" ? input.instructions : undefined,
|
||||
store: typeof input?.store === "boolean" ? input.store : undefined,
|
||||
promptCacheKey: typeof input?.promptCacheKey === "string" ? input.promptCacheKey : undefined,
|
||||
reasoningEffort: typeof input?.reasoningEffort === "string" ? input.reasoningEffort : undefined,
|
||||
reasoningSummary:
|
||||
reasoningSummary === "auto" || reasoningSummary === "concise" || reasoningSummary === "detailed"
|
||||
? reasoningSummary
|
||||
: undefined,
|
||||
include: include.length > 0 ? include : undefined,
|
||||
textVerbosity: isTextVerbosity(input?.textVerbosity) ? input.textVerbosity : undefined,
|
||||
serviceTier: isServiceTier(input?.serviceTier) ? input.serviceTier : undefined,
|
||||
}
|
||||
}
|
||||
|
||||
export * as OpenResponsesOptions from "./open-responses-options"
|
||||
@@ -1,20 +0,0 @@
|
||||
import { Schema } from "effect"
|
||||
|
||||
const dimensions = (value: string) => {
|
||||
const match = /^(\d+)x(\d+)$/.exec(value)
|
||||
if (!match) return undefined
|
||||
return { width: Number(match[1]), height: Number(match[2]) }
|
||||
}
|
||||
|
||||
export const Size = Schema.String.check(
|
||||
Schema.makeFilter((value) => {
|
||||
if (value === "auto") return undefined
|
||||
const parsed = dimensions(value)
|
||||
if (!parsed) return "image size must be `auto` or `{width}x{height}`"
|
||||
return parsed.width > 0 && parsed.height > 0 ? undefined : "image dimensions must be positive integers"
|
||||
}),
|
||||
)
|
||||
|
||||
export const OpenAIImage = {
|
||||
Size,
|
||||
} as const
|
||||
@@ -1,23 +0,0 @@
|
||||
import { ReasoningEfforts } from "../../schema"
|
||||
import { OpenResponsesOptions } from "./open-responses-options"
|
||||
|
||||
export const OpenAIReasoningEfforts = ReasoningEfforts
|
||||
export type OpenAIReasoningEffort = string
|
||||
|
||||
// Mirrors OpenAI's `ResponseIncludable` union from the official SDK. Keep this
|
||||
// in lockstep with `openai-node/src/resources/responses/responses.ts`.
|
||||
export const OpenAIResponseIncludables = OpenResponsesOptions.ResponseIncludables
|
||||
export type OpenAIResponseIncludable = OpenResponsesOptions.ResponseIncludable
|
||||
export const OpenAIServiceTiers = OpenResponsesOptions.ServiceTiers
|
||||
export type OpenAIServiceTier = OpenResponsesOptions.ServiceTier
|
||||
|
||||
export const OpenAIReasoningEffort = OpenResponsesOptions.ReasoningEffort
|
||||
export const OpenAITextVerbosity = OpenResponsesOptions.TextVerbositySchema
|
||||
export const OpenAIResponseIncludable = OpenResponsesOptions.ResponseIncludableSchema
|
||||
export const OpenAIServiceTier = OpenResponsesOptions.ServiceTierSchema
|
||||
|
||||
export const isReasoningEffort = (effort: unknown): effort is OpenAIReasoningEffort => typeof effort === "string"
|
||||
|
||||
export const resolve = OpenResponsesOptions.resolve
|
||||
|
||||
export * as OpenAIOptions from "./openai-options"
|
||||
@@ -1,202 +0,0 @@
|
||||
import { Effect, Encoding, Schema } from "effect"
|
||||
import { Headers, HttpClientRequest } from "effect/unstable/http"
|
||||
import { GeneratedImage, ImageModel, ImageResponse, type ImageRequestFor, type ImageRoute } from "../image"
|
||||
import { Auth, type Definition as AuthDefinition } from "../route/auth"
|
||||
import {
|
||||
InvalidProviderOutputReason,
|
||||
LLMError,
|
||||
Usage,
|
||||
mergeHttpOptions,
|
||||
mergeJsonRecords,
|
||||
type HttpOptions,
|
||||
} from "../schema"
|
||||
import { ProviderShared, optionalNull } from "./shared"
|
||||
import { ImageInputs } from "./utils/image-input"
|
||||
|
||||
const ADAPTER = "xai-images"
|
||||
export const DEFAULT_BASE_URL = "https://api.x.ai/v1"
|
||||
export const PATH = "/images/generations"
|
||||
export const EDIT_PATH = "/images/edits"
|
||||
|
||||
export type XAIImageString<Known extends string> = Known | (string & {})
|
||||
|
||||
export type XAIImageOptions = {
|
||||
readonly n?: number
|
||||
readonly aspectRatio?: XAIImageString<
|
||||
| "1:1"
|
||||
| "3:4"
|
||||
| "4:3"
|
||||
| "9:16"
|
||||
| "16:9"
|
||||
| "2:3"
|
||||
| "3:2"
|
||||
| "9:19.5"
|
||||
| "19.5:9"
|
||||
| "9:20"
|
||||
| "20:9"
|
||||
| "1:2"
|
||||
| "2:1"
|
||||
| "auto"
|
||||
>
|
||||
readonly aspect_ratio?: XAIImageString<
|
||||
| "1:1"
|
||||
| "3:4"
|
||||
| "4:3"
|
||||
| "9:16"
|
||||
| "16:9"
|
||||
| "2:3"
|
||||
| "3:2"
|
||||
| "9:19.5"
|
||||
| "19.5:9"
|
||||
| "9:20"
|
||||
| "20:9"
|
||||
| "1:2"
|
||||
| "2:1"
|
||||
| "auto"
|
||||
>
|
||||
readonly resolution?: XAIImageString<"1k" | "2k">
|
||||
readonly responseFormat?: XAIImageString<"url" | "b64_json">
|
||||
readonly response_format?: XAIImageString<"url" | "b64_json">
|
||||
} & Record<string, unknown>
|
||||
|
||||
type XAIImageBody = Record<string, unknown> & {
|
||||
readonly model: string
|
||||
readonly prompt: string
|
||||
}
|
||||
|
||||
const XAIImageResponse = Schema.Struct({
|
||||
data: Schema.Array(
|
||||
Schema.Struct({
|
||||
b64_json: optionalNull(Schema.String),
|
||||
url: optionalNull(Schema.String),
|
||||
revised_prompt: optionalNull(Schema.String),
|
||||
mime_type: optionalNull(Schema.String),
|
||||
}),
|
||||
),
|
||||
usage: Schema.optional(Schema.Unknown),
|
||||
})
|
||||
|
||||
export interface ModelInput {
|
||||
readonly id: string
|
||||
readonly auth: AuthDefinition
|
||||
readonly baseURL?: string
|
||||
readonly headers?: Record<string, string>
|
||||
readonly http?: HttpOptions
|
||||
}
|
||||
|
||||
const nativeOptions = (options: XAIImageOptions | undefined) => {
|
||||
if (!options) return undefined
|
||||
const { aspectRatio, responseFormat, ...native } = options
|
||||
return {
|
||||
aspect_ratio: aspectRatio,
|
||||
response_format: responseFormat,
|
||||
...native,
|
||||
}
|
||||
}
|
||||
|
||||
const invalidOutput = (message: string) =>
|
||||
new LLMError({
|
||||
module: ADAPTER,
|
||||
method: "generate",
|
||||
reason: new InvalidProviderOutputReason({ message, route: ADAPTER }),
|
||||
})
|
||||
|
||||
const applyQuery = (url: string, query: Record<string, string> | undefined) => {
|
||||
if (!query) return url
|
||||
const next = new URL(url)
|
||||
Object.entries(query).forEach(([key, value]) => next.searchParams.set(key, value))
|
||||
return next.toString()
|
||||
}
|
||||
|
||||
export const model = (input: ModelInput) => {
|
||||
const route: ImageRoute<XAIImageOptions> = {
|
||||
id: ADAPTER,
|
||||
generate: Effect.fn("XAIImages.generate")(function* (request: ImageRequestFor<XAIImageOptions>, execute) {
|
||||
const http = mergeHttpOptions(request.model.http, request.http)
|
||||
const imageReferences = (request.images ?? []).map((image) => {
|
||||
if (image.type === "bytes") return { url: ImageInputs.dataUrl(image), type: "image_url" as const }
|
||||
if (image.type === "url") return { url: image.url, type: "image_url" as const }
|
||||
if (image.type === "file-id") return { file_id: image.id }
|
||||
return undefined
|
||||
})
|
||||
if (imageReferences.some((image) => image === undefined))
|
||||
return yield* ImageInputs.invalid(ADAPTER, "xAI Images accepts image URLs, data URLs, bytes, and file IDs")
|
||||
const requestBody = mergeJsonRecords(
|
||||
{
|
||||
model: request.model.id,
|
||||
prompt: request.prompt,
|
||||
image: imageReferences.length === 1 ? imageReferences[0] : undefined,
|
||||
images: imageReferences.length > 1 ? imageReferences : undefined,
|
||||
},
|
||||
nativeOptions(request.options),
|
||||
http?.body,
|
||||
) as XAIImageBody
|
||||
const text = ProviderShared.encodeJson(requestBody)
|
||||
const url = applyQuery(
|
||||
`${(input.baseURL ?? DEFAULT_BASE_URL).replace(/\/$/, "")}${imageReferences.length === 0 ? PATH : EDIT_PATH}`,
|
||||
http?.query,
|
||||
)
|
||||
const headers = yield* Auth.toEffect(input.auth)({
|
||||
request,
|
||||
method: "POST",
|
||||
url,
|
||||
body: text,
|
||||
headers: Headers.fromInput({ ...input.headers, ...http?.headers }),
|
||||
})
|
||||
const response = yield* execute(
|
||||
HttpClientRequest.post(url).pipe(
|
||||
HttpClientRequest.setHeaders(headers),
|
||||
HttpClientRequest.bodyText(text, "application/json"),
|
||||
),
|
||||
)
|
||||
const payload = yield* response.json.pipe(
|
||||
Effect.mapError(() => invalidOutput("Failed to read the xAI Images response")),
|
||||
)
|
||||
const decoded = yield* Schema.decodeUnknownEffect(XAIImageResponse)(payload).pipe(
|
||||
Effect.mapError(() => invalidOutput("xAI Images returned an invalid response")),
|
||||
)
|
||||
const images = yield* Effect.forEach(decoded.data, (item, index) => {
|
||||
const mediaType = item.mime_type ?? "application/octet-stream"
|
||||
if (item.b64_json)
|
||||
return Effect.fromResult(Encoding.decodeBase64(item.b64_json)).pipe(
|
||||
Effect.mapError(() => invalidOutput(`xAI Images result ${index} contains invalid base64 data`)),
|
||||
Effect.map(
|
||||
(data) =>
|
||||
new GeneratedImage({
|
||||
mediaType,
|
||||
data,
|
||||
providerMetadata:
|
||||
item.revised_prompt === undefined || item.revised_prompt === null
|
||||
? undefined
|
||||
: { xai: { revisedPrompt: item.revised_prompt } },
|
||||
}),
|
||||
),
|
||||
)
|
||||
if (item.url)
|
||||
return Effect.succeed(
|
||||
new GeneratedImage({
|
||||
mediaType,
|
||||
data: item.url,
|
||||
providerMetadata:
|
||||
item.revised_prompt === undefined || item.revised_prompt === null
|
||||
? undefined
|
||||
: { xai: { revisedPrompt: item.revised_prompt } },
|
||||
}),
|
||||
)
|
||||
return Effect.fail(invalidOutput(`xAI Images result ${index} has neither image data nor a URL`))
|
||||
})
|
||||
if (images.length === 0) return yield* invalidOutput("xAI Images returned no images")
|
||||
const usage = ProviderShared.isRecord(decoded.usage) ? decoded.usage : undefined
|
||||
return new ImageResponse({
|
||||
images,
|
||||
usage: usage === undefined ? undefined : new Usage({ providerMetadata: { xai: usage } }),
|
||||
providerMetadata: usage === undefined ? undefined : { xai: { usage } },
|
||||
})
|
||||
}),
|
||||
}
|
||||
return ImageModel.make<XAIImageOptions>({ id: input.id, provider: "xai", route, http: input.http })
|
||||
}
|
||||
|
||||
export const XAIImages = {
|
||||
model,
|
||||
} as const
|
||||
@@ -1,132 +0,0 @@
|
||||
import { Effect, Schema } from "effect"
|
||||
import { Headers, HttpClientRequest } from "effect/unstable/http"
|
||||
import { GeneratedImage, ImageModel, ImageResponse, type ImageRequestFor, type ImageRoute } from "../image"
|
||||
import { Auth, type Definition as AuthDefinition } from "../route/auth"
|
||||
import { InvalidProviderOutputReason, LLMError, mergeHttpOptions, mergeJsonRecords, type HttpOptions } from "../schema"
|
||||
import { ProviderShared } from "./shared"
|
||||
import { ImageInputs } from "./utils/image-input"
|
||||
|
||||
const ADAPTER = "zai-images"
|
||||
export const DEFAULT_BASE_URL = "https://api.z.ai/api/paas/v4"
|
||||
export const PATH = "/images/generations"
|
||||
|
||||
export type ZAIImageString<Known extends string> = Known | (string & {})
|
||||
|
||||
export type ZAIImageOptions = {
|
||||
readonly size?: ZAIImageString<
|
||||
"1024x1024" | "768x1344" | "864x1152" | "1344x768" | "1152x864" | "1440x720" | "720x1440"
|
||||
>
|
||||
readonly quality?: ZAIImageString<"hd" | "standard">
|
||||
readonly userID?: string
|
||||
} & Record<string, unknown>
|
||||
|
||||
type ZAIImageBody = Record<string, unknown> & {
|
||||
readonly model: string
|
||||
readonly prompt: string
|
||||
}
|
||||
|
||||
const ZAIImageResponse = Schema.Struct({
|
||||
created: Schema.optional(Schema.Int),
|
||||
id: Schema.optional(Schema.String),
|
||||
request_id: Schema.optional(Schema.String),
|
||||
data: Schema.Array(Schema.Struct({ url: Schema.String })),
|
||||
content_filter: Schema.optional(
|
||||
Schema.Array(
|
||||
Schema.Struct({
|
||||
role: Schema.optional(Schema.String),
|
||||
level: Schema.optional(Schema.Number),
|
||||
}),
|
||||
),
|
||||
),
|
||||
})
|
||||
|
||||
export interface ModelInput {
|
||||
readonly id: string
|
||||
readonly auth: AuthDefinition
|
||||
readonly baseURL?: string
|
||||
readonly headers?: Record<string, string>
|
||||
readonly http?: HttpOptions
|
||||
}
|
||||
|
||||
const nativeOptions = (options: ZAIImageOptions | undefined) => {
|
||||
if (!options) return undefined
|
||||
const { userID, ...native } = options
|
||||
return {
|
||||
user_id: userID,
|
||||
...native,
|
||||
}
|
||||
}
|
||||
|
||||
const invalidOutput = (message: string) =>
|
||||
new LLMError({
|
||||
module: ADAPTER,
|
||||
method: "generate",
|
||||
reason: new InvalidProviderOutputReason({ message, route: ADAPTER }),
|
||||
})
|
||||
|
||||
const applyQuery = (url: string, query: Record<string, string> | undefined) => {
|
||||
if (!query) return url
|
||||
const next = new URL(url)
|
||||
Object.entries(query).forEach(([key, value]) => next.searchParams.set(key, value))
|
||||
return next.toString()
|
||||
}
|
||||
|
||||
export const model = (input: ModelInput) => {
|
||||
const route: ImageRoute<ZAIImageOptions> = {
|
||||
id: ADAPTER,
|
||||
generate: Effect.fn("ZAIImages.generate")(function* (request: ImageRequestFor<ZAIImageOptions>, execute) {
|
||||
if ((request.images?.length ?? 0) > 0)
|
||||
return yield* ImageInputs.invalid(ADAPTER, "Z.ai hosted image generation does not support image inputs")
|
||||
const http = mergeHttpOptions(request.model.http, request.http)
|
||||
const requestBody = mergeJsonRecords(
|
||||
{ model: request.model.id, prompt: request.prompt },
|
||||
nativeOptions(request.options),
|
||||
http?.body,
|
||||
) as ZAIImageBody
|
||||
const text = ProviderShared.encodeJson(requestBody)
|
||||
const url = applyQuery(`${(input.baseURL ?? DEFAULT_BASE_URL).replace(/\/$/, "")}${PATH}`, http?.query)
|
||||
const headers = yield* Auth.toEffect(input.auth)({
|
||||
request,
|
||||
method: "POST",
|
||||
url,
|
||||
body: text,
|
||||
headers: Headers.fromInput({ ...input.headers, ...http?.headers }),
|
||||
})
|
||||
const response = yield* execute(
|
||||
HttpClientRequest.post(url).pipe(
|
||||
HttpClientRequest.setHeaders(headers),
|
||||
HttpClientRequest.bodyText(text, "application/json"),
|
||||
),
|
||||
)
|
||||
const payload = yield* response.json.pipe(
|
||||
Effect.mapError(() => invalidOutput("Failed to read the Z.ai Images response")),
|
||||
)
|
||||
const decoded = yield* Schema.decodeUnknownEffect(ZAIImageResponse)(payload).pipe(
|
||||
Effect.mapError(() => invalidOutput("Z.ai Images returned an invalid response")),
|
||||
)
|
||||
if (decoded.data.length === 0) return yield* invalidOutput("Z.ai Images returned no images")
|
||||
return new ImageResponse({
|
||||
images: decoded.data.map(
|
||||
(item) =>
|
||||
new GeneratedImage({
|
||||
mediaType: "application/octet-stream",
|
||||
data: item.url,
|
||||
}),
|
||||
),
|
||||
providerMetadata: {
|
||||
zai: {
|
||||
created: decoded.created,
|
||||
id: decoded.id,
|
||||
requestID: decoded.request_id,
|
||||
contentFilter: decoded.content_filter,
|
||||
},
|
||||
},
|
||||
})
|
||||
}),
|
||||
}
|
||||
return ImageModel.make<ZAIImageOptions>({ id: input.id, provider: "zai", route, http: input.http })
|
||||
}
|
||||
|
||||
export const ZAIImages = {
|
||||
model,
|
||||
} as const
|
||||
@@ -1 +0,0 @@
|
||||
export * from "./providers/index"
|
||||
@@ -1,116 +0,0 @@
|
||||
import { Effect, Schema, Struct } from "effect"
|
||||
import type { ProviderPackage } from "../provider-package"
|
||||
import { AnthropicMessages } from "../protocols/anthropic-messages"
|
||||
import { Auth } from "../route/auth"
|
||||
import { Route, type RouteDefaultsInput } from "../route/client"
|
||||
import { Endpoint } from "../route/endpoint"
|
||||
import { Framing } from "../route/framing"
|
||||
import { Protocol } from "../route/protocol"
|
||||
import { ProviderID, type ModelID } from "../schema"
|
||||
import { GoogleVertexShared } from "./google-vertex-shared"
|
||||
|
||||
export type AnthropicOptionsInput = AnthropicMessages.OptionsInput
|
||||
export type AnthropicProviderOptionsInput = AnthropicMessages.ProviderOptionsInput
|
||||
export type AnthropicThinkingInput = AnthropicMessages.ThinkingInput
|
||||
|
||||
const VERSION = "vertex-2023-10-16" as const
|
||||
|
||||
// models.dev uses this provider id even though the API contract is Anthropic Messages.
|
||||
export const id = ProviderID.make("google-vertex-anthropic")
|
||||
|
||||
export type Config = RouteDefaultsInput &
|
||||
GoogleVertexShared.OAuthOptions & {
|
||||
readonly baseURL?: string
|
||||
readonly location?: string
|
||||
readonly project?: string
|
||||
readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
|
||||
}
|
||||
|
||||
export interface Settings extends ProviderPackage.Settings {
|
||||
readonly accessToken?: string
|
||||
readonly apiKey?: never
|
||||
readonly baseURL?: string
|
||||
readonly location?: string
|
||||
readonly project?: string
|
||||
readonly providerOptions?: AnthropicMessages.ProviderOptionsInput
|
||||
}
|
||||
|
||||
const route = Route.make({
|
||||
id: "google-vertex-messages",
|
||||
provider: id,
|
||||
providerMetadataKey: "anthropic",
|
||||
protocol: Protocol.make({
|
||||
id: AnthropicMessages.protocol.id,
|
||||
body: {
|
||||
schema: Schema.Struct({
|
||||
...Struct.omit(AnthropicMessages.AnthropicMessagesBody.fields, ["model"]),
|
||||
anthropic_version: Schema.Literal(VERSION),
|
||||
}),
|
||||
from: (request) =>
|
||||
AnthropicMessages.protocol.body.from(request).pipe(
|
||||
Effect.map((body) => ({
|
||||
...Struct.omit(body, ["model"]),
|
||||
anthropic_version: VERSION,
|
||||
})),
|
||||
),
|
||||
},
|
||||
stream: AnthropicMessages.protocol.stream,
|
||||
}),
|
||||
endpoint: Endpoint.path(({ request }) => `/${request.model.id}:streamRawPredict`),
|
||||
auth: Auth.none,
|
||||
framing: Framing.sse,
|
||||
})
|
||||
|
||||
export const routes = [route]
|
||||
|
||||
const configuredRoute = (input: Config) => {
|
||||
if ("apiKey" in input && input.apiKey !== undefined)
|
||||
throw new Error("Google Vertex Messages does not support API keys")
|
||||
const {
|
||||
accessToken: _accessToken,
|
||||
auth: _auth,
|
||||
baseURL,
|
||||
location: inputLocation,
|
||||
project: inputProject,
|
||||
...rest
|
||||
} = input
|
||||
const location = GoogleVertexShared.location(inputLocation, "global")
|
||||
const project = GoogleVertexShared.project(inputProject)
|
||||
return route.with({
|
||||
...rest,
|
||||
endpoint: {
|
||||
baseURL:
|
||||
baseURL ??
|
||||
`https://${GoogleVertexShared.host(location)}/v1/projects/${GoogleVertexShared.requireProject(project)}/locations/${location}/publishers/anthropic/models`,
|
||||
},
|
||||
auth: GoogleVertexShared.oauth(input, project),
|
||||
})
|
||||
}
|
||||
|
||||
export const configure = (input: Config = {}) => {
|
||||
const route = configuredRoute(input)
|
||||
return {
|
||||
id,
|
||||
model: (modelID: string | ModelID) => route.model({ id: modelID }),
|
||||
configure,
|
||||
}
|
||||
}
|
||||
|
||||
export const provider = {
|
||||
id,
|
||||
configure,
|
||||
}
|
||||
|
||||
export const model: ProviderPackage.Definition<Settings>["model"] = (modelID, settings) => {
|
||||
if (settings.apiKey !== undefined) throw new Error("Google Vertex Messages does not support API keys")
|
||||
return configure({
|
||||
accessToken: settings.accessToken,
|
||||
baseURL: settings.baseURL,
|
||||
headers: settings.headers === undefined ? undefined : { ...settings.headers },
|
||||
http: settings.body === undefined ? undefined : { body: { ...settings.body } },
|
||||
limits: settings.limits,
|
||||
location: settings.location,
|
||||
project: settings.project,
|
||||
providerOptions: settings.providerOptions,
|
||||
}).model(modelID)
|
||||
}
|
||||
@@ -1,83 +0,0 @@
|
||||
import type { ProviderPackage } from "../provider-package"
|
||||
import { OpenAICompatibleResponses } from "../protocols/openai-compatible-responses"
|
||||
import type { RouteDefaultsInput } from "../route/client"
|
||||
import { ProviderID, type ModelID, type ProviderOptions } from "../schema"
|
||||
import { GoogleVertexShared } from "./google-vertex-shared"
|
||||
|
||||
export const id = ProviderID.make("google-vertex")
|
||||
|
||||
export type Config = RouteDefaultsInput &
|
||||
GoogleVertexShared.OAuthOptions & {
|
||||
readonly baseURL?: string
|
||||
readonly location?: string
|
||||
readonly project?: string
|
||||
}
|
||||
|
||||
export interface Settings extends ProviderPackage.Settings {
|
||||
readonly accessToken?: string
|
||||
readonly apiKey?: never
|
||||
readonly baseURL?: string
|
||||
readonly location?: string
|
||||
readonly project?: string
|
||||
readonly providerOptions?: ProviderOptions
|
||||
}
|
||||
|
||||
const route = OpenAICompatibleResponses.route.with({
|
||||
id: "google-vertex-responses",
|
||||
provider: id,
|
||||
providerOptions: { openresponses: { store: false } },
|
||||
})
|
||||
|
||||
export const routes = [route]
|
||||
|
||||
const configuredRoute = (input: Config) => {
|
||||
if ("apiKey" in input && input.apiKey !== undefined)
|
||||
throw new Error("Google Vertex Responses does not support API keys")
|
||||
const {
|
||||
accessToken: _accessToken,
|
||||
auth: _auth,
|
||||
baseURL,
|
||||
location: inputLocation,
|
||||
project: inputProject,
|
||||
...rest
|
||||
} = input
|
||||
const location = GoogleVertexShared.location(inputLocation, "global")
|
||||
const project = GoogleVertexShared.project(inputProject)
|
||||
return route.with({
|
||||
...rest,
|
||||
endpoint: {
|
||||
baseURL:
|
||||
baseURL ??
|
||||
`https://aiplatform.googleapis.com/v1/projects/${GoogleVertexShared.requireProject(project)}/locations/${location}/endpoints/openapi`,
|
||||
},
|
||||
auth: GoogleVertexShared.oauth(input, project),
|
||||
})
|
||||
}
|
||||
|
||||
export const configure = (input: Config = {}) => {
|
||||
const route = configuredRoute(input)
|
||||
return {
|
||||
id,
|
||||
model: (modelID: string | ModelID) => route.model({ id: modelID }),
|
||||
configure,
|
||||
}
|
||||
}
|
||||
|
||||
export const provider = {
|
||||
id,
|
||||
configure,
|
||||
}
|
||||
|
||||
export const model: ProviderPackage.Definition<Settings>["model"] = (modelID, settings) => {
|
||||
if (settings.apiKey !== undefined) throw new Error("Google Vertex Responses does not support API keys")
|
||||
return configure({
|
||||
accessToken: settings.accessToken,
|
||||
baseURL: settings.baseURL,
|
||||
headers: settings.headers === undefined ? undefined : { ...settings.headers },
|
||||
http: settings.body === undefined ? undefined : { body: { ...settings.body } },
|
||||
limits: settings.limits,
|
||||
location: settings.location,
|
||||
project: settings.project,
|
||||
providerOptions: settings.providerOptions,
|
||||
}).model(modelID)
|
||||
}
|
||||
@@ -1,2 +0,0 @@
|
||||
export { model } from "../google-vertex-chat"
|
||||
export type { Settings } from "../google-vertex-chat"
|
||||
@@ -1,2 +0,0 @@
|
||||
export { model } from "../google-vertex"
|
||||
export type { Settings } from "../google-vertex"
|
||||
@@ -1,2 +0,0 @@
|
||||
export { model } from "../google-vertex-messages"
|
||||
export type { Settings } from "../google-vertex-messages"
|
||||
@@ -1,2 +0,0 @@
|
||||
export { model } from "../google-vertex-responses"
|
||||
export type { Settings } from "../google-vertex-responses"
|
||||
@@ -1,20 +0,0 @@
|
||||
import type { ResponseIncludable, ServiceTier } from "../protocols/utils/open-responses-options"
|
||||
import type { ProviderOptions, ReasoningEffort, TextVerbosity } from "../schema"
|
||||
|
||||
export interface OpenResponsesOptionsInput {
|
||||
readonly [key: string]: unknown
|
||||
readonly instructions?: string
|
||||
readonly store?: boolean
|
||||
readonly promptCacheKey?: string
|
||||
readonly reasoningEffort?: ReasoningEffort
|
||||
readonly reasoningSummary?: "auto" | "concise" | "detailed"
|
||||
readonly include?: ReadonlyArray<ResponseIncludable>
|
||||
readonly textVerbosity?: TextVerbosity
|
||||
readonly serviceTier?: ServiceTier
|
||||
}
|
||||
|
||||
export type OpenResponsesProviderOptionsInput = ProviderOptions & {
|
||||
readonly openresponses?: OpenResponsesOptionsInput
|
||||
}
|
||||
|
||||
export * as OpenResponsesProviderOptions from "./open-responses-options"
|
||||
@@ -1 +0,0 @@
|
||||
export * from "../openai-compatible-responses"
|
||||
@@ -1,35 +0,0 @@
|
||||
import { ZAIImages } from "../protocols/zai-images"
|
||||
import { AuthOptions, type ProviderAuthOption } from "../route/auth-options"
|
||||
import { HttpOptions, ProviderID, type ModelID } from "../schema"
|
||||
|
||||
export const id = ProviderID.make("zai")
|
||||
|
||||
export type Config = ProviderAuthOption<"optional"> & {
|
||||
readonly baseURL?: string
|
||||
readonly headers?: Record<string, string>
|
||||
readonly http?: HttpOptions.Input
|
||||
}
|
||||
|
||||
export type { ZAIImageOptions } from "../protocols/zai-images"
|
||||
|
||||
const auth = (options: ProviderAuthOption<"optional">) => AuthOptions.bearer(options, "ZAI_API_KEY")
|
||||
|
||||
export const configure = (input: Config = {}) => {
|
||||
const image = (modelID: string | ModelID) =>
|
||||
ZAIImages.model({
|
||||
id: modelID,
|
||||
auth: auth(input),
|
||||
baseURL: input.baseURL,
|
||||
headers: input.headers,
|
||||
http: input.http === undefined ? undefined : HttpOptions.make(input.http),
|
||||
})
|
||||
|
||||
return {
|
||||
id,
|
||||
image,
|
||||
configure,
|
||||
}
|
||||
}
|
||||
|
||||
export const provider = configure()
|
||||
export const image = provider.image
|
||||
@@ -1 +0,0 @@
|
||||
export * from "./route/index"
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 896 B |
-40
@@ -1,40 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"provider": "minimax",
|
||||
"protocol": "anthropic-messages",
|
||||
"route": "anthropic-messages",
|
||||
"transport": "http",
|
||||
"model": "MiniMax-M3",
|
||||
"tags": [
|
||||
"prefix:anthropic-compatible-messages",
|
||||
"provider:minimax",
|
||||
"protocol:anthropic-messages",
|
||||
"text",
|
||||
"golden"
|
||||
],
|
||||
"name": "anthropic-compatible-messages/minimax-m3-anthropic-compatible-text",
|
||||
"recordedAt": "2026-07-18T03:42:22.893Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://api.minimax.io/anthropic/v1/messages",
|
||||
"headers": {
|
||||
"anthropic-version": "2023-06-01",
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"model\":\"MiniMax-M3\",\"system\":[{\"type\":\"text\",\"text\":\"You are concise.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Reply exactly with: Hello!\"}]}],\"stream\":true,\"max_tokens\":40,\"temperature\":0}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "text/event-stream; charset=utf-8"
|
||||
},
|
||||
"body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"1a0b363d0882af316faebcec4d4855a8\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":53,\"output_tokens\":0,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":114,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"Hello\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"!\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\"},\"usage\":{\"input_tokens\":53,\"output_tokens\":2,\"cache_read_input_tokens\":114,\"service_tier\":\"standard\"}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
-41
@@ -1,41 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"provider": "minimax",
|
||||
"protocol": "anthropic-messages",
|
||||
"route": "anthropic-messages",
|
||||
"transport": "http",
|
||||
"model": "MiniMax-M3",
|
||||
"tags": [
|
||||
"prefix:anthropic-compatible-messages",
|
||||
"provider:minimax",
|
||||
"protocol:anthropic-messages",
|
||||
"tool",
|
||||
"tool-call",
|
||||
"golden"
|
||||
],
|
||||
"name": "anthropic-compatible-messages/minimax-m3-anthropic-compatible-tool-call",
|
||||
"recordedAt": "2026-07-18T03:42:23.876Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://api.minimax.io/anthropic/v1/messages",
|
||||
"headers": {
|
||||
"anthropic-version": "2023-06-01",
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"model\":\"MiniMax-M3\",\"system\":[{\"type\":\"text\",\"text\":\"Call tools exactly as requested.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Call get_weather with city exactly Paris.\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"tool_choice\":{\"type\":\"tool\",\"name\":\"get_weather\"},\"stream\":true,\"max_tokens\":80,\"temperature\":0}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "text/event-stream; charset=utf-8"
|
||||
},
|
||||
"body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"6731ecc323233459d1792df9a733dd98\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":0,\"output_tokens\":0,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":404,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"tool_use\",\"id\":\"call_function_vkxtif4epmvm_1\",\"name\":\"get_weather\",\"input\":{}}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\\\"city\\\": \\\"Paris\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"\\\"}\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\"},\"usage\":{\"input_tokens\":290,\"output_tokens\":27,\"cache_read_input_tokens\":114,\"service_tier\":\"standard\"}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
-60
@@ -1,60 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"provider": "minimax",
|
||||
"protocol": "anthropic-messages",
|
||||
"route": "anthropic-messages",
|
||||
"transport": "http",
|
||||
"model": "MiniMax-M3",
|
||||
"tags": [
|
||||
"prefix:anthropic-compatible-messages",
|
||||
"provider:minimax",
|
||||
"protocol:anthropic-messages",
|
||||
"tool",
|
||||
"tool-loop",
|
||||
"golden"
|
||||
],
|
||||
"name": "anthropic-compatible-messages/minimax-m3-anthropic-compatible-tool-loop",
|
||||
"recordedAt": "2026-07-18T03:42:25.248Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://api.minimax.io/anthropic/v1/messages",
|
||||
"headers": {
|
||||
"anthropic-version": "2023-06-01",
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"model\":\"MiniMax-M3\",\"system\":[{\"type\":\"text\",\"text\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is the weather in Paris?\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":80,\"temperature\":0}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "text/event-stream; charset=utf-8"
|
||||
},
|
||||
"body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"3807fa12f9ecb9357df511e099da6da0\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":0,\"output_tokens\":0,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":417,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"tool_use\",\"id\":\"call_function_yr64rwmre4gr_1\",\"name\":\"get_weather\",\"input\":{}}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\\\"city\\\": \\\"Paris\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"\\\"}\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\"},\"usage\":{\"input_tokens\":303,\"output_tokens\":27,\"cache_read_input_tokens\":114,\"service_tier\":\"standard\"}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
|
||||
}
|
||||
},
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://api.minimax.io/anthropic/v1/messages",
|
||||
"headers": {
|
||||
"anthropic-version": "2023-06-01",
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"model\":\"MiniMax-M3\",\"system\":[{\"type\":\"text\",\"text\":\"Use the get_weather tool exactly once. After the tool result, reply exactly: Paris is sunny.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"What is the weather in Paris?\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"tool_use\",\"id\":\"call_function_yr64rwmre4gr_1\",\"name\":\"get_weather\",\"input\":{\"city\":\"Paris\"}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_function_yr64rwmre4gr_1\",\"content\":\"{\\\"temperature\\\":22,\\\"condition\\\":\\\"sunny\\\"}\"}]}],\"tools\":[{\"name\":\"get_weather\",\"description\":\"Get current weather for a city.\",\"input_schema\":{\"type\":\"object\",\"properties\":{\"city\":{\"type\":\"string\"}},\"required\":[\"city\"],\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":80,\"temperature\":0}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "text/event-stream; charset=utf-8"
|
||||
},
|
||||
"body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"92f8a1e86f29946eb2699d40a088fc08\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"MiniMax-M3\",\"stop_reason\":null,\"stop_sequence\":null,\"usage\":{\"input_tokens\":41,\"output_tokens\":0,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":430,\"service_tier\":\"standard\"},\"service_tier\":\"standard\"}}\n\nevent: ping\ndata: {\"type\":\"ping\"}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"Paris\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" is sunny.\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\"},\"usage\":{\"input_tokens\":41,\"output_tokens\":4,\"cache_read_input_tokens\":430,\"service_tier\":\"standard\"}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
-54
File diff suppressed because one or more lines are too long
-53
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
-50
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -1,34 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"model": "anthropic/claude-sonnet-4.6",
|
||||
"tags": [
|
||||
"prefix:openai-compatible-chat",
|
||||
"provider:openrouter",
|
||||
"protocol:openai-chat",
|
||||
"reasoning"
|
||||
],
|
||||
"name": "openrouter-reasoning",
|
||||
"recordedAt": "2026-07-18T11:28:39.267Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://openrouter.ai/api/v1/chat/completions",
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"model\":\"anthropic/claude-sonnet-4.6\",\"messages\":[{\"role\":\"system\",\"content\":\"Think through the arithmetic, then reply with only the final integer.\"},{\"role\":\"user\",\"content\":\"What is 173 multiplied by 219?\"}],\"stream\":true,\"stream_options\":{\"include_usage\":true},\"max_tokens\":1536,\"temperature\":0,\"reasoning\":{\"max_tokens\":1024}}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "text/event-stream"
|
||||
},
|
||||
"body": ": OPENROUTER PROCESSING\n\n: OPENROUTER PROCESSING\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning\":\"173\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"text\":\"173\",\"format\":\"anthropic-claude-v1\",\"index\":0}]},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\n: OPENROUTER PROCESSING\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning\":\" × 219\\n\\n173 × 200 = 34,600\\n173 × 19 = 173 × 20 - 173 = 3,460 - 173 = 3,287\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"text\":\" × 219\\n\\n173 × 200 = 34,600\\n173 × 19 = 173 × 20 - 173 = 3,460 - 173 = 3,287\",\"format\":\"anthropic-claude-v1\",\"index\":0}]},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning\":\"\\n\\n34,600 + 3,287 = 37,887\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"text\":\"\\n\\n34,600 + 3,287 = 37,887\",\"format\":\"anthropic-claude-v1\",\"index\":0}]},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning_details\":[{\"type\":\"reasoning.text\",\"signature\":\"EtgCCosBCA8YAipA0W4viH3kgBs43Cl5ewwVBPXTQElvzfbA2TLF4iSbKy9ZZDCSDjjAlF3Bs4ELEnP3vrrTuTioC6OB380lXQdyIDIRY2xhdWRlLXNvbm5ldC00LTY4AEIIdGhpbmtpbmdaJDRjMGYwNDZmLTI1ZmQtNDVmYi1iZmIzLWEwOGE4ZTI0OWNhNxIMMiUlJC3x/5p5PuTwGgwlc8eipZyoM94BHwMiMO45uQx/ymeOjbugi7RDVPZ4jZXSIiEbVi2CD7zPjAK5fFQoVGP1HD55v9CER823JCp6Dg5Xb7Lrk6NUd1XN2KTKrttK7mATE+IBrDTFmor/1cNeg+9gjIbxM/jn/6L5HPmh3/esEVu24Q0IGLZVoE7cTgGgxsrceKMD71Jp2XQgIWD8ltsPfWw3gSc4p+z18UuPN6LuR0mHHENTnClHrAPnOrxbDIl4ZwZgMX8YAQ==\",\"format\":\"anthropic-claude-v1\",\"index\":0}]},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"37887\",\"role\":\"assistant\"},\"finish_reason\":null,\"native_finish_reason\":null}]}\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\",\"reasoning\":null},\"finish_reason\":\"stop\",\"native_finish_reason\":\"end_turn\"}]}\n\ndata: {\"id\":\"gen-1784374117-AXXPsQRoclZeQGx2uHeK\",\"object\":\"chat.completion.chunk\",\"created\":1784374117,\"model\":\"anthropic/claude-sonnet-4.6\",\"provider\":\"Anthropic\",\"service_tier\":\"default\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"\",\"role\":\"assistant\"},\"finish_reason\":\"stop\",\"native_finish_reason\":\"end_turn\"}],\"usage\":{\"prompt_tokens\":61,\"completion_tokens\":80,\"total_tokens\":141,\"cost\":0.001383,\"is_byok\":false,\"prompt_tokens_details\":{\"cached_tokens\":0,\"cache_write_tokens\":0,\"audio_tokens\":0,\"video_tokens\":0},\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"cost_details\":{\"upstream_inference_cost\":0.001383,\"upstream_inference_prompt_cost\":0.000183,\"upstream_inference_completions_cost\":0.0012},\"completion_tokens_details\":{\"reasoning_tokens\":29,\"image_tokens\":0,\"audio_tokens\":0}}}\n\ndata: [DONE]\n\n"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,35 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"prefix:pdf",
|
||||
"pdf",
|
||||
"provider:anthropic",
|
||||
"protocol:anthropic-messages",
|
||||
"tool",
|
||||
"tool-result"
|
||||
],
|
||||
"name": "pdf/anthropic-tool-result",
|
||||
"recordedAt": "2026-07-22T18:15:39.002Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://api.anthropic.com/v1/messages",
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"model\":\"claude-haiku-4-5-20251001\",\"system\":[{\"type\":\"text\",\"text\":\"Read the PDF returned by the tool and follow the user's response format exactly.\"}],\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"Return only the verification code from the PDF.\"}]},{\"role\":\"assistant\",\"content\":[{\"type\":\"tool_use\",\"id\":\"call_pdf_1\",\"name\":\"read_pdf\",\"input\":{}}]},{\"role\":\"user\",\"content\":[{\"type\":\"tool_result\",\"tool_use_id\":\"call_pdf_1\",\"content\":[{\"type\":\"text\",\"text\":\"PDF read successfully\"},{\"type\":\"document\",\"source\":{\"type\":\"base64\",\"media_type\":\"application/pdf\",\"data\":\"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\"}}]}]}],\"tools\":[{\"name\":\"read_pdf\",\"description\":\"Read the attached PDF.\",\"input_schema\":{\"type\":\"object\",\"properties\":{},\"additionalProperties\":false}}],\"stream\":true,\"max_tokens\":40,\"temperature\":0}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "text/event-stream; charset=utf-8"
|
||||
},
|
||||
"body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"model\":\"claude-haiku-4-5-20251001\",\"id\":\"msg_011CdHYzxyRpSVFgwTm6ccUr\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"stop_reason\":null,\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":2229,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":2,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\"}} }\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"} }\n\nevent: ping\ndata: {\"type\": \"ping\"}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"ORCH\"} }\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"ID-7391\"} }\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0 }\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"stop_details\":null},\"usage\":{\"input_tokens\":2229,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"output_tokens\":9} }\n\nevent: message_stop\ndata: {\"type\":\"message_stop\" }\n\n"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,34 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"prefix:pdf",
|
||||
"pdf",
|
||||
"provider:anthropic",
|
||||
"protocol:anthropic-messages",
|
||||
"user-input"
|
||||
],
|
||||
"name": "pdf/anthropic-user-input",
|
||||
"recordedAt": "2026-07-22T18:15:37.979Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://api.anthropic.com/v1/messages",
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"model\":\"claude-haiku-4-5-20251001\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"document\",\"source\":{\"type\":\"base64\",\"media_type\":\"application/pdf\",\"data\":\"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\"}},{\"type\":\"text\",\"text\":\"Return only the verification code from the PDF.\"}]}],\"stream\":true,\"max_tokens\":40,\"temperature\":0}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "text/event-stream; charset=utf-8"
|
||||
},
|
||||
"body": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"model\":\"claude-haiku-4-5-20251001\",\"id\":\"msg_011CdHYzsayb45rgfamcjFt3\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"stop_reason\":null,\"stop_sequence\":null,\"stop_details\":null,\"usage\":{\"input_tokens\":1602,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"cache_creation\":{\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_tokens\":2,\"service_tier\":\"standard\",\"inference_geo\":\"not_available\"}} }\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"} }\n\nevent: ping\ndata: {\"type\": \"ping\"}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"ORCH\"} }\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"ID-7391\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0 }\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null,\"stop_details\":null},\"usage\":{\"input_tokens\":1602,\"cache_creation_input_tokens\":0,\"cache_read_input_tokens\":0,\"output_tokens\":9} }\n\nevent: message_stop\ndata: {\"type\":\"message_stop\" }\n\n"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,36 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"prefix:pdf",
|
||||
"pdf",
|
||||
"provider:amazon-bedrock",
|
||||
"protocol:bedrock-converse",
|
||||
"tool",
|
||||
"tool-result"
|
||||
],
|
||||
"name": "pdf/bedrock-tool-result",
|
||||
"recordedAt": "2026-07-22T18:15:52.400Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://bedrock-runtime.us-east-1.amazonaws.com/model/us.anthropic.claude-haiku-4-5-20251001-v1%3A0/converse-stream",
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"modelId\":\"us.anthropic.claude-haiku-4-5-20251001-v1:0\",\"messages\":[{\"role\":\"user\",\"content\":[{\"text\":\"Return only the verification code from the PDF.\"}]},{\"role\":\"assistant\",\"content\":[{\"toolUse\":{\"toolUseId\":\"call_pdf_1\",\"name\":\"read_pdf\",\"input\":{}}}]},{\"role\":\"user\",\"content\":[{\"toolResult\":{\"toolUseId\":\"call_pdf_1\",\"content\":[{\"text\":\"PDF read successfully\"},{\"document\":{\"format\":\"pdf\",\"name\":\"verification\",\"source\":{\"bytes\":\"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\"}}}],\"status\":\"success\"}}]}],\"system\":[{\"text\":\"Read the PDF returned by the tool and follow the user's response format exactly.\"}],\"inferenceConfig\":{\"maxTokens\":40,\"temperature\":0},\"toolConfig\":{\"tools\":[{\"toolSpec\":{\"name\":\"read_pdf\",\"description\":\"Read the attached PDF.\",\"inputSchema\":{\"json\":{\"type\":\"object\",\"properties\":{},\"additionalProperties\":false}}}}]}}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "application/vnd.amazon.eventstream"
|
||||
},
|
||||
"body": "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",
|
||||
"bodyEncoding": "base64"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,35 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"prefix:pdf",
|
||||
"pdf",
|
||||
"provider:amazon-bedrock",
|
||||
"protocol:bedrock-converse",
|
||||
"user-input"
|
||||
],
|
||||
"name": "pdf/bedrock-user-input",
|
||||
"recordedAt": "2026-07-22T18:15:48.408Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://bedrock-runtime.us-east-1.amazonaws.com/model/us.anthropic.claude-haiku-4-5-20251001-v1%3A0/converse-stream",
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"modelId\":\"us.anthropic.claude-haiku-4-5-20251001-v1:0\",\"messages\":[{\"role\":\"user\",\"content\":[{\"document\":{\"format\":\"pdf\",\"name\":\"verification\",\"source\":{\"bytes\":\"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\"}}},{\"text\":\"Return only the verification code from the PDF.\"}]}],\"inferenceConfig\":{\"maxTokens\":40,\"temperature\":0}}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "application/vnd.amazon.eventstream"
|
||||
},
|
||||
"body": "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",
|
||||
"bodyEncoding": "base64"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,53 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"prefix:pdf",
|
||||
"pdf",
|
||||
"provider:google",
|
||||
"protocol:gemini",
|
||||
"tool",
|
||||
"tool-result"
|
||||
],
|
||||
"name": "pdf/gemini-tool-result",
|
||||
"recordedAt": "2026-07-22T18:21:59.606Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:streamGenerateContent?alt=sse",
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"contents\":[{\"role\":\"user\",\"parts\":[{\"text\":\"Use read_pdf with path verification.pdf and return the verification code.\"}]}],\"systemInstruction\":{\"parts\":[{\"text\":\"Call read_pdf exactly once with path verification.pdf, then reply only with the verification code from its PDF.\"}]},\"tools\":[{\"functionDeclarations\":[{\"name\":\"read_pdf\",\"description\":\"Read the attached PDF.\",\"parameters\":{\"required\":[\"path\"],\"type\":\"object\",\"properties\":{\"path\":{\"type\":\"string\"}}}}]}],\"generationConfig\":{\"maxOutputTokens\":256,\"temperature\":0}}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "text/event-stream"
|
||||
},
|
||||
"body": "data: {\"candidates\": [{\"content\": {\"parts\": [{\"functionCall\": {\"name\": \"read_pdf\",\"args\": {\"path\": \"verification.pdf\"},\"id\": \"58shgmez\"},\"thoughtSignature\": \"EqkCCqYCARFNMg/JrCTv5i3zYENFBVpZNFL3pbzJmi5Eu387ncF703xFMB4pwyaP7a1gi49EqBhCI2hWOpesU5nZQOLAhGgExKGa2GM+HzpEB5g62r0NFblm/BGkVZaImTuHR7bytfRC5jHQlHKo4OS27OLUVjvkMkBIYsvjhDErY7niERbXJVpyxTVqUf1GgZMSu8kC9/5WDlMs9xVKNT/6KMW4PhhSR9nXg4KZUa+bC03/ydhsWWgBa5aLCgvTq7WPj217xIsmUkSiRedIffPsUSNjYdMHUvWi8bOlvM1veEEP6GIfv5h9gXXzjnHbEHfQxV8PZuBAyY7iM6nqyfkJNdkZ1HdB7DXMBsMsRN6SgrIrFoXX2WaGrkoEI5tdZx1t/gdwF1jEVT6k\"}],\"role\": \"model\"},\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 81,\"candidatesTokenCount\": 18,\"totalTokenCount\": 151,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 81}],\"thoughtsTokenCount\": 52,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"RAphaui3OaSHz7IPy8Kb4Ak\"}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"\"}],\"role\": \"model\"},\"finishReason\": \"STOP\",\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 81,\"candidatesTokenCount\": 18,\"totalTokenCount\": 151,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 81}],\"thoughtsTokenCount\": 52,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"RAphaui3OaSHz7IPy8Kb4Ak\"}\r\n\r\n"
|
||||
}
|
||||
},
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:streamGenerateContent?alt=sse",
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"contents\":[{\"role\":\"user\",\"parts\":[{\"text\":\"Use read_pdf with path verification.pdf and return the verification code.\"}]},{\"role\":\"model\",\"parts\":[{\"functionCall\":{\"id\":\"58shgmez\",\"name\":\"read_pdf\",\"args\":{\"path\":\"verification.pdf\"}},\"thoughtSignature\":\"EqkCCqYCARFNMg/JrCTv5i3zYENFBVpZNFL3pbzJmi5Eu387ncF703xFMB4pwyaP7a1gi49EqBhCI2hWOpesU5nZQOLAhGgExKGa2GM+HzpEB5g62r0NFblm/BGkVZaImTuHR7bytfRC5jHQlHKo4OS27OLUVjvkMkBIYsvjhDErY7niERbXJVpyxTVqUf1GgZMSu8kC9/5WDlMs9xVKNT/6KMW4PhhSR9nXg4KZUa+bC03/ydhsWWgBa5aLCgvTq7WPj217xIsmUkSiRedIffPsUSNjYdMHUvWi8bOlvM1veEEP6GIfv5h9gXXzjnHbEHfQxV8PZuBAyY7iM6nqyfkJNdkZ1HdB7DXMBsMsRN6SgrIrFoXX2WaGrkoEI5tdZx1t/gdwF1jEVT6k\"}]},{\"role\":\"user\",\"parts\":[{\"functionResponse\":{\"id\":\"58shgmez\",\"name\":\"read_pdf\",\"response\":{\"name\":\"read_pdf\",\"content\":\"PDF read successfully\"},\"parts\":[{\"inlineData\":{\"mimeType\":\"application/pdf\",\"data\":\"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\"}}]}}]}],\"systemInstruction\":{\"parts\":[{\"text\":\"Call read_pdf exactly once with path verification.pdf, then reply only with the verification code from its PDF.\"}]},\"tools\":[{\"functionDeclarations\":[{\"name\":\"read_pdf\",\"description\":\"Read the attached PDF.\",\"parameters\":{\"required\":[\"path\"],\"type\":\"object\",\"properties\":{\"path\":{\"type\":\"string\"}}}}]}],\"generationConfig\":{\"maxOutputTokens\":256,\"temperature\":0}}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "text/event-stream"
|
||||
},
|
||||
"body": "data: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"ORCHID-7391\"}],\"role\": \"model\"},\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 123,\"candidatesTokenCount\": 8,\"totalTokenCount\": 184,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 123}],\"thoughtsTokenCount\": 53,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"RgphaoL6CMjQz7IPjOnEmQI\"}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"\",\"thoughtSignature\": \"EqECCp4CARFNMg9obBl8O6iU9lawUIWiE+1vztZm9NtaT9FuyJz343hd9ruz+xPco4Q1DY1GF81ZiSI2ElBkt8Wfwsqtix9LNGSMvbZhhk/ZnB54t05M/Dft1kujcMvEdZUWUI/jWaJ349tO1bKVH9MacG5+gl0n4y8DwyQZSV3xIcet547drSkcA/TM03RB+yj1/dcLHsvUjmv9EnO897vZgO2Dk4tbZ2NyCtOeQ3JKVhUTLg2pjkGk+POCNiOdESWiUzxdQKw9LiV6nnzi071tXNiMeVimq6d7xAzRVNapI2uXynvn9Uk3eyn85purOFa8cKriK9oD6vcyGMqgd9+gu2m3to0IHqd7o+2YSr1m5qV1xT1R2/WRQEtb1b1AuOAU6w==\"}],\"role\": \"model\"},\"finishReason\": \"STOP\",\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 1277,\"candidatesTokenCount\": 8,\"totalTokenCount\": 1338,\"promptTokensDetails\": [{\"modality\": \"IMAGE\",\"tokenCount\": 1102},{\"modality\": \"TEXT\",\"tokenCount\": 175}],\"thoughtsTokenCount\": 53,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"RgphaoL6CMjQz7IPjOnEmQI\"}\r\n\r\n"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,34 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"prefix:pdf",
|
||||
"pdf",
|
||||
"provider:google",
|
||||
"protocol:gemini",
|
||||
"user-input"
|
||||
],
|
||||
"name": "pdf/gemini-user-input",
|
||||
"recordedAt": "2026-07-22T18:20:55.140Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://generativelanguage.googleapis.com/v1beta/models/gemini-3.5-flash:streamGenerateContent?alt=sse",
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"contents\":[{\"role\":\"user\",\"parts\":[{\"inlineData\":{\"mimeType\":\"application/pdf\",\"data\":\"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\"}},{\"text\":\"Return only the verification code from the PDF.\"}]}],\"generationConfig\":{\"maxOutputTokens\":256,\"temperature\":0}}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "text/event-stream"
|
||||
},
|
||||
"body": "data: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"ORCH\"}],\"role\": \"model\"},\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 10,\"candidatesTokenCount\": 2,\"totalTokenCount\": 127,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 10}],\"thoughtsTokenCount\": 115,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"BQpharW2KaPgz7IP6uSLiAw\"}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"ID-7391\"}],\"role\": \"model\"},\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 10,\"candidatesTokenCount\": 8,\"totalTokenCount\": 133,\"promptTokensDetails\": [{\"modality\": \"TEXT\",\"tokenCount\": 10}],\"thoughtsTokenCount\": 115,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"BQpharW2KaPgz7IP6uSLiAw\"}\r\n\r\ndata: {\"candidates\": [{\"content\": {\"parts\": [{\"text\": \"\",\"thoughtSignature\": \"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\"}],\"role\": \"model\"},\"finishReason\": \"STOP\",\"index\": 0}],\"usageMetadata\": {\"promptTokenCount\": 530,\"candidatesTokenCount\": 8,\"totalTokenCount\": 653,\"promptTokensDetails\": [{\"modality\": \"IMAGE\",\"tokenCount\": 520},{\"modality\": \"TEXT\",\"tokenCount\": 10}],\"thoughtsTokenCount\": 115,\"serviceTier\": \"standard\"},\"modelVersion\": \"gemini-3.5-flash\",\"responseId\": \"BQpharW2KaPgz7IP6uSLiAw\"}\r\n\r\n"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
-55
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -1,28 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"metadata": {
|
||||
"tags": ["prefix:zai-images", "provider:zai", "protocol:zai-images"],
|
||||
"name": "zai-images/generates-an-image",
|
||||
"recordedAt": "2026-07-19T16:03:55.761Z"
|
||||
},
|
||||
"interactions": [
|
||||
{
|
||||
"transport": "http",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "https://api.z.ai/api/paas/v4/images/generations",
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": "{\"model\":\"cogview-4-250304\",\"prompt\":\"A simple flat red circle centered on a plain white background.\",\"size\":\"1024x1024\",\"quality\":\"standard\",\"user_id\":\"opencode-image-test\"}"
|
||||
},
|
||||
"response": {
|
||||
"status": 200,
|
||||
"headers": {
|
||||
"content-type": "application/json; charset=UTF-8"
|
||||
},
|
||||
"body": "{\"created\":1784477028,\"data\":[{\"url\":\"https://mfile.z.ai/1784477035500-43574eab2b6e402da9063d6ac22dfefb.png?ufileattname=202607200003482062c3bba9b04f7d_watermark.png\"}],\"id\":\"202607200003482062c3bba9b04f7d\",\"request_id\":\"202607200003482062c3bba9b04f7d\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,578 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect, Layer } from "effect"
|
||||
import { HttpClientRequest } from "effect/unstable/http"
|
||||
import { Image, ImageClient, ImageInput } from "../src"
|
||||
import { Google, OpenAI, XAI, ZAI } from "../src/providers"
|
||||
import { it } from "./lib/effect"
|
||||
import { dynamicResponse } from "./lib/http"
|
||||
|
||||
describe("Image", () => {
|
||||
it.effect("generates images through the OpenAI Images API", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model: OpenAI.configure({
|
||||
apiKey: "test",
|
||||
baseURL: "https://api.openai.test/v1",
|
||||
queryParams: { "api-version": "v1" },
|
||||
http: { body: { deployment: "test" }, headers: { "x-default": "yes" } },
|
||||
}).image("gpt-image-2"),
|
||||
prompt: "A robot tending a rooftop garden",
|
||||
options: {
|
||||
n: 2,
|
||||
size: "2048x2048",
|
||||
quality: "future-quality",
|
||||
outputFormat: "jpeg",
|
||||
output_format: "avif",
|
||||
outputCompression: 30,
|
||||
output_compression: 40,
|
||||
background: "opaque",
|
||||
native_default: true,
|
||||
future_option: true,
|
||||
},
|
||||
http: {
|
||||
body: { output_format: "webp", output_compression: 50, future_option: "http", request_metadata: "value" },
|
||||
headers: { "x-request": "yes" },
|
||||
query: { trace: "1" },
|
||||
},
|
||||
})
|
||||
|
||||
expect(response.images).toHaveLength(2)
|
||||
expect(response.image?.mediaType).toBe("image/webp")
|
||||
expect(response.image?.data).toEqual(Uint8Array.from([1, 2, 3]))
|
||||
expect(response.image?.providerMetadata).toEqual({ openai: { revisedPrompt: "A precise robot" } })
|
||||
expect(response.usage?.totalTokens).toBe(12)
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
const request = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
|
||||
expect(request.url).toBe("https://api.openai.test/v1/images/generations?api-version=v1&trace=1")
|
||||
expect(request.headers.get("authorization")).toBe("Bearer test")
|
||||
expect(request.headers.get("x-default")).toBe("yes")
|
||||
expect(request.headers.get("x-request")).toBe("yes")
|
||||
expect(JSON.parse(input.text)).toEqual({
|
||||
model: "gpt-image-2",
|
||||
prompt: "A robot tending a rooftop garden",
|
||||
n: 2,
|
||||
size: "2048x2048",
|
||||
quality: "future-quality",
|
||||
background: "opaque",
|
||||
output_format: "webp",
|
||||
output_compression: 50,
|
||||
native_default: true,
|
||||
future_option: "http",
|
||||
deployment: "test",
|
||||
request_metadata: "value",
|
||||
})
|
||||
return input.respond(
|
||||
JSON.stringify({
|
||||
data: [{ b64_json: "AQID", revised_prompt: "A precise robot" }, { b64_json: "BAUG" }],
|
||||
output_format: "webp",
|
||||
usage: { input_tokens: 4, output_tokens: 8, total_tokens: 12 },
|
||||
}),
|
||||
{ headers: { "content-type": "application/json" } },
|
||||
)
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("preserves native snake_case and unknown request options", () =>
|
||||
Image.generate({
|
||||
model: OpenAI.configure({
|
||||
apiKey: "test",
|
||||
baseURL: "https://api.openai.test/v1",
|
||||
}).image("future-image-model"),
|
||||
prompt: "A lighthouse in fog",
|
||||
options: {
|
||||
outputFormat: "jpeg",
|
||||
output_format: "avif",
|
||||
outputCompression: 30,
|
||||
output_compression: 40,
|
||||
provider_future_option: { enabled: true },
|
||||
},
|
||||
}).pipe(
|
||||
Effect.tap((response) =>
|
||||
Effect.sync(() => {
|
||||
expect(response.image?.mediaType).toBe("image/avif")
|
||||
}),
|
||||
),
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) => {
|
||||
expect(JSON.parse(input.text)).toEqual({
|
||||
model: "future-image-model",
|
||||
prompt: "A lighthouse in fog",
|
||||
output_format: "avif",
|
||||
output_compression: 40,
|
||||
provider_future_option: { enabled: true },
|
||||
})
|
||||
return Effect.succeed(
|
||||
input.respond(JSON.stringify({ data: [{ b64_json: "AQID" }] }), {
|
||||
headers: { "content-type": "application/json" },
|
||||
}),
|
||||
)
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("routes OpenAI byte inputs and masks through multipart edits", () =>
|
||||
Image.generate({
|
||||
model: OpenAI.configure({ apiKey: "test", baseURL: "https://api.openai.test/v1" }).image("future-model"),
|
||||
prompt: "Combine these images",
|
||||
images: [
|
||||
ImageInput.bytes(Uint8Array.from([1, 2, 3]), "image/png"),
|
||||
ImageInput.url("data:image/jpeg;base64,BAUG"),
|
||||
],
|
||||
options: {
|
||||
mask: ImageInput.bytes(Uint8Array.from([7, 8, 9]), "image/png"),
|
||||
quality: "high",
|
||||
future_option: true,
|
||||
},
|
||||
http: {
|
||||
body: { quality: "low", model: "corrupt", prompt: "corrupt", image: "corrupt", "image[]": "corrupt" },
|
||||
headers: { "content-type": "application/json" },
|
||||
},
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
const request = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
|
||||
expect(request.url).toBe("https://api.openai.test/v1/images/edits")
|
||||
expect(request.headers.get("content-type")).toStartWith("multipart/form-data; boundary=")
|
||||
expect(input.text).toContain('name="model"\r\n\r\nfuture-model')
|
||||
expect(input.text).toContain('name="prompt"\r\n\r\nCombine these images')
|
||||
expect(input.text.match(/name="image\[\]"/g)).toHaveLength(2)
|
||||
expect(input.text).toContain('name="mask"')
|
||||
expect(input.text).toContain('name="quality"\r\n\r\nlow')
|
||||
expect(input.text).not.toContain("corrupt")
|
||||
return input.respond(JSON.stringify({ data: [{ b64_json: "AQID" }] }), {
|
||||
headers: { "content-type": "application/json" },
|
||||
})
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("routes OpenAI URL and file inputs through JSON edits", () =>
|
||||
Image.generate({
|
||||
model: OpenAI.configure({ apiKey: "test", baseURL: "https://api.openai.test/v1" }).image("future-model"),
|
||||
prompt: "Combine these images",
|
||||
images: [ImageInput.url("https://example.test/source.png"), ImageInput.file("file_123")],
|
||||
options: { mask: ImageInput.file("file_mask") },
|
||||
http: { body: { future_option: true } },
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) => {
|
||||
expect(JSON.parse(input.text)).toEqual({
|
||||
model: "future-model",
|
||||
prompt: "Combine these images",
|
||||
images: [{ image_url: "https://example.test/source.png" }, { file_id: "file_123" }],
|
||||
mask: { file_id: "file_mask" },
|
||||
future_option: true,
|
||||
})
|
||||
return Effect.succeed(
|
||||
input.respond(JSON.stringify({ data: [{ b64_json: "AQID" }] }), {
|
||||
headers: { "content-type": "application/json" },
|
||||
}),
|
||||
)
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("routes ordered xAI image inputs through JSON edits", () =>
|
||||
Image.generate({
|
||||
model: XAI.configure({ apiKey: "test", baseURL: "https://api.xai.test/v1" }).image("future-model"),
|
||||
prompt: "Combine these images",
|
||||
images: [
|
||||
ImageInput.bytes(Uint8Array.from([1, 2, 3]), "image/png"),
|
||||
ImageInput.url("https://example.test/source.jpg"),
|
||||
ImageInput.file("file_123"),
|
||||
],
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) => {
|
||||
expect(JSON.parse(input.text)).toEqual({
|
||||
model: "future-model",
|
||||
prompt: "Combine these images",
|
||||
images: [
|
||||
{ url: "data:image/png;base64,AQID", type: "image_url" },
|
||||
{ url: "https://example.test/source.jpg", type: "image_url" },
|
||||
{ file_id: "file_123" },
|
||||
],
|
||||
})
|
||||
return Effect.succeed(
|
||||
input.respond(JSON.stringify({ data: [{ b64_json: "AQID", mime_type: "image/png" }] }), {
|
||||
headers: { "content-type": "application/json" },
|
||||
}),
|
||||
)
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("uses xAI's singular image field for one input", () =>
|
||||
Image.generate({
|
||||
model: XAI.configure({ apiKey: "test", baseURL: "https://api.xai.test/v1" }).image("future-model"),
|
||||
prompt: "Edit this image",
|
||||
images: [ImageInput.file("file_123")],
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) => {
|
||||
expect(JSON.parse(input.text)).toEqual({
|
||||
model: "future-model",
|
||||
prompt: "Edit this image",
|
||||
image: { file_id: "file_123" },
|
||||
})
|
||||
return Effect.succeed(
|
||||
input.respond(JSON.stringify({ data: [{ b64_json: "AQID", mime_type: "image/png" }] }), {
|
||||
headers: { "content-type": "application/json" },
|
||||
}),
|
||||
)
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("lowers ordered Google image inputs into generateContent parts", () =>
|
||||
Image.generate({
|
||||
model: Google.configure({ apiKey: "test", baseURL: "https://google.test/v1beta" }).image("future-model"),
|
||||
prompt: "Combine these images",
|
||||
images: [
|
||||
ImageInput.bytes(Uint8Array.from([1, 2, 3]), "image/png"),
|
||||
ImageInput.url("data:image/jpeg;base64,BAUG"),
|
||||
ImageInput.fileUri("https://generativelanguage.googleapis.com/v1beta/files/123", "image/webp"),
|
||||
],
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) => {
|
||||
expect(JSON.parse(input.text).contents[0].parts).toEqual([
|
||||
{ text: "Combine these images" },
|
||||
{ inlineData: { mimeType: "image/png", data: "AQID" } },
|
||||
{ inlineData: { mimeType: "image/jpeg", data: "BAUG" } },
|
||||
{
|
||||
fileData: {
|
||||
mimeType: "image/webp",
|
||||
fileUri: "https://generativelanguage.googleapis.com/v1beta/files/123",
|
||||
},
|
||||
},
|
||||
])
|
||||
return Effect.succeed(
|
||||
input.respond(
|
||||
JSON.stringify({
|
||||
candidates: [{ content: { parts: [{ inlineData: { mimeType: "image/png", data: "AQID" } }] } }],
|
||||
}),
|
||||
{ headers: { "content-type": "application/json" } },
|
||||
),
|
||||
)
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("rejects unsupported provider inputs before sending", () =>
|
||||
Effect.gen(function* () {
|
||||
const cases = [
|
||||
Image.generate({
|
||||
model: Google.configure({ apiKey: "test" }).image("model"),
|
||||
prompt: "edit",
|
||||
images: [ImageInput.url("https://example.test/image.png")],
|
||||
}),
|
||||
Image.generate({
|
||||
model: ZAI.configure({ apiKey: "test" }).image("model"),
|
||||
prompt: "edit",
|
||||
images: [ImageInput.bytes(Uint8Array.from([1]), "image/png")],
|
||||
}),
|
||||
]
|
||||
yield* Effect.forEach(cases, (program) =>
|
||||
program.pipe(
|
||||
Effect.flip,
|
||||
Effect.tap((error) => Effect.sync(() => expect(error.reason._tag).toBe("InvalidRequest"))),
|
||||
),
|
||||
)
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(dynamicResponse(() => Effect.die("unsupported input reached the network"))),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("generates images through the Google generateContent API", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model: Google.configure({
|
||||
apiKey: "test",
|
||||
baseURL: "https://generativelanguage.test/v1beta/",
|
||||
headers: { "x-default": "yes" },
|
||||
http: { body: { labels: { deployment: "test" } }, query: { api: "v1" } },
|
||||
}).image("any-model-id"),
|
||||
prompt: "A robot tending a rooftop garden",
|
||||
options: {
|
||||
aspectRatio: "16:9",
|
||||
imageSize: "2K",
|
||||
seed: 42,
|
||||
thinkingLevel: "HIGH",
|
||||
includeThoughts: true,
|
||||
futureOption: true,
|
||||
imageConfig: { aspectRatio: "4:3", nativeImageOption: true },
|
||||
thinkingConfig: { thinkingLevel: "LOW", nativeThinkingOption: true },
|
||||
},
|
||||
http: {
|
||||
body: {
|
||||
safetySettings: [],
|
||||
generationConfig: {
|
||||
imageConfig: { aspectRatio: "3:2", httpImageOption: true },
|
||||
thinkingConfig: { includeThoughts: false, httpThinkingOption: true },
|
||||
futureOption: "http",
|
||||
httpOption: true,
|
||||
},
|
||||
},
|
||||
headers: { "x-request": "yes" },
|
||||
query: { trace: "1" },
|
||||
},
|
||||
})
|
||||
|
||||
expect(response.images).toHaveLength(3)
|
||||
expect(response.images.map((image) => image.data)).toEqual([
|
||||
Uint8Array.from([1, 2, 3]),
|
||||
Uint8Array.from([4, 5, 6]),
|
||||
Uint8Array.from([7, 8, 9]),
|
||||
])
|
||||
expect(response.images.map((image) => image.mediaType)).toEqual(["image/png", "image/jpeg", "image/webp"])
|
||||
expect(response.images[0].providerMetadata).toMatchObject({ google: { thoughtSignature: "signature-1" } })
|
||||
expect(response.images[1].providerMetadata).toMatchObject({
|
||||
google: { candidateIndex: 0, partIndex: 3, finishReason: "STOP" },
|
||||
})
|
||||
expect(response.images[2].providerMetadata).toMatchObject({ google: { candidateIndex: 7, partIndex: 0 } })
|
||||
expect(response.usage?.inputTokens).toBe(5)
|
||||
expect(response.usage?.outputTokens).toBe(10)
|
||||
expect(response.usage?.reasoningTokens).toBe(3)
|
||||
expect(response.usage?.providerMetadata).toMatchObject({ google: { serviceTier: "STANDARD" } })
|
||||
expect(response.providerMetadata).toEqual({
|
||||
google: {
|
||||
modelVersion: "gemini-3.1-flash-image",
|
||||
responseId: "response-1",
|
||||
promptFeedback: undefined,
|
||||
candidates: [
|
||||
{
|
||||
index: 0,
|
||||
finishReason: "STOP",
|
||||
finishMessage: undefined,
|
||||
safetyRatings: [{ category: "safe" }],
|
||||
citationMetadata: undefined,
|
||||
groundingMetadata: undefined,
|
||||
parts: [
|
||||
{
|
||||
type: "inlineData",
|
||||
mediaType: "image/png",
|
||||
thought: undefined,
|
||||
thoughtSignature: "signature-1",
|
||||
},
|
||||
{ type: "text", text: "planning", thought: true, thoughtSignature: "text-signature" },
|
||||
{
|
||||
type: "inlineData",
|
||||
mediaType: "image/png",
|
||||
thought: true,
|
||||
thoughtSignature: "draft-signature",
|
||||
},
|
||||
{
|
||||
type: "inlineData",
|
||||
mediaType: "image/jpeg",
|
||||
thought: undefined,
|
||||
thoughtSignature: undefined,
|
||||
},
|
||||
],
|
||||
},
|
||||
{
|
||||
index: 7,
|
||||
finishReason: undefined,
|
||||
finishMessage: undefined,
|
||||
safetyRatings: undefined,
|
||||
citationMetadata: undefined,
|
||||
groundingMetadata: undefined,
|
||||
parts: [
|
||||
{
|
||||
type: "inlineData",
|
||||
mediaType: "image/webp",
|
||||
thought: undefined,
|
||||
thoughtSignature: undefined,
|
||||
},
|
||||
],
|
||||
},
|
||||
],
|
||||
},
|
||||
})
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
const request = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
|
||||
expect(request.url).toBe(
|
||||
"https://generativelanguage.test/v1beta/models/any-model-id:generateContent?api=v1&trace=1",
|
||||
)
|
||||
expect(request.headers.get("x-goog-api-key")).toBe("test")
|
||||
expect(request.headers.get("x-default")).toBe("yes")
|
||||
expect(request.headers.get("x-request")).toBe("yes")
|
||||
expect(JSON.parse(input.text)).toEqual({
|
||||
contents: [{ role: "user", parts: [{ text: "A robot tending a rooftop garden" }] }],
|
||||
generationConfig: {
|
||||
responseModalities: ["IMAGE"],
|
||||
imageConfig: {
|
||||
aspectRatio: "3:2",
|
||||
imageSize: "2K",
|
||||
nativeImageOption: true,
|
||||
httpImageOption: true,
|
||||
},
|
||||
seed: 42,
|
||||
thinkingConfig: {
|
||||
thinkingLevel: "LOW",
|
||||
includeThoughts: false,
|
||||
nativeThinkingOption: true,
|
||||
httpThinkingOption: true,
|
||||
},
|
||||
futureOption: "http",
|
||||
httpOption: true,
|
||||
},
|
||||
labels: { deployment: "test" },
|
||||
safetySettings: [],
|
||||
})
|
||||
return input.respond(
|
||||
JSON.stringify({
|
||||
candidates: [
|
||||
{
|
||||
content: {
|
||||
parts: [
|
||||
{
|
||||
inlineData: { mimeType: "image/png", data: "AQID" },
|
||||
thoughtSignature: "signature-1",
|
||||
},
|
||||
{ text: "planning", thought: true, thoughtSignature: "text-signature" },
|
||||
{
|
||||
inlineData: { mimeType: "image/png", data: "CgsM" },
|
||||
thought: true,
|
||||
thoughtSignature: "draft-signature",
|
||||
},
|
||||
{ inlineData: { mimeType: "image/jpeg", data: "BAUG" } },
|
||||
],
|
||||
},
|
||||
finishReason: "STOP",
|
||||
safetyRatings: [{ category: "safe" }],
|
||||
},
|
||||
{
|
||||
index: 7,
|
||||
content: { parts: [{ inlineData: { mimeType: "image/webp", data: "BwgJ" } }] },
|
||||
},
|
||||
],
|
||||
usageMetadata: {
|
||||
promptTokenCount: 5,
|
||||
candidatesTokenCount: 7,
|
||||
thoughtsTokenCount: 3,
|
||||
totalTokenCount: 15,
|
||||
serviceTier: "STANDARD",
|
||||
},
|
||||
modelVersion: "gemini-3.1-flash-image",
|
||||
responseId: "response-1",
|
||||
}),
|
||||
{ headers: { "content-type": "application/json" } },
|
||||
)
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("includes Google diagnostics when no final image is returned", () =>
|
||||
Image.generate({
|
||||
model: Google.configure({ apiKey: "test", baseURL: "https://generativelanguage.test/v1beta" }).image(
|
||||
"gemini-3.1-flash-image",
|
||||
),
|
||||
prompt: "A robot tending a rooftop garden",
|
||||
}).pipe(
|
||||
Effect.flip,
|
||||
Effect.tap((error) =>
|
||||
Effect.sync(() => {
|
||||
expect(error.reason._tag).toBe("InvalidProviderOutput")
|
||||
if (error.reason._tag !== "InvalidProviderOutput") return
|
||||
expect(error.reason.message).toContain("finish reasons: IMAGE_SAFETY")
|
||||
expect(error.reason.providerMetadata).toEqual({
|
||||
google: {
|
||||
promptFeedback: { blockReason: "SAFETY" },
|
||||
candidates: [
|
||||
{
|
||||
index: 0,
|
||||
finishReason: "IMAGE_SAFETY",
|
||||
finishMessage: "The generated image was blocked by safety filters.",
|
||||
safetyRatings: [{ category: "HARM_CATEGORY_DANGEROUS_CONTENT", blocked: true }],
|
||||
citationMetadata: undefined,
|
||||
groundingMetadata: undefined,
|
||||
parts: [{ type: "text", text: "blocked", thought: false, thoughtSignature: undefined }],
|
||||
},
|
||||
],
|
||||
},
|
||||
})
|
||||
}),
|
||||
),
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.succeed(
|
||||
input.respond(
|
||||
JSON.stringify({
|
||||
candidates: [
|
||||
{
|
||||
content: { parts: [{ text: "blocked", thought: false }] },
|
||||
finishReason: "IMAGE_SAFETY",
|
||||
finishMessage: "The generated image was blocked by safety filters.",
|
||||
safetyRatings: [{ category: "HARM_CATEGORY_DANGEROUS_CONTENT", blocked: true }],
|
||||
},
|
||||
],
|
||||
promptFeedback: { blockReason: "SAFETY" },
|
||||
}),
|
||||
{ headers: { "content-type": "application/json" } },
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
})
|
||||
@@ -1,161 +0,0 @@
|
||||
import {
|
||||
Image,
|
||||
ImageInput,
|
||||
ImageModel,
|
||||
type ImageModelOptions,
|
||||
type ImageOptions,
|
||||
type ImageRequestFor,
|
||||
type ImageRoute,
|
||||
} from "../src"
|
||||
import { Google, OpenAI, XAI, ZAI } from "../src/providers"
|
||||
|
||||
type GoogleLikeOptions = {
|
||||
readonly aspectRatio?: "1:1" | "16:9"
|
||||
readonly imageSize?: "1K" | "2K"
|
||||
} & Record<string, unknown>
|
||||
|
||||
declare const route: ImageRoute<GoogleLikeOptions>
|
||||
const google = ImageModel.make<GoogleLikeOptions>({ id: "gemini-image", provider: "google", route })
|
||||
// @ts-expect-error Extracted model options retain known provider fields.
|
||||
const invalidGoogleOptions: ImageModelOptions<typeof google> = { aspectRatio: "wide" }
|
||||
void invalidGoogleOptions
|
||||
|
||||
Image.generate({
|
||||
model: google,
|
||||
prompt: "A lighthouse",
|
||||
images: [
|
||||
ImageInput.bytes(Uint8Array.from([1, 2, 3]), "image/png"),
|
||||
ImageInput.url("data:image/jpeg;base64,AQID"),
|
||||
ImageInput.fileUri("https://generativelanguage.googleapis.com/v1beta/files/example", "image/webp"),
|
||||
],
|
||||
options: { aspectRatio: "16:9", imageSize: "2K", futureOption: true },
|
||||
})
|
||||
|
||||
const googleProvider = Google.configure({ apiKey: "test" }).image("any-model-id")
|
||||
Image.generate({
|
||||
model: googleProvider,
|
||||
prompt: "A lighthouse",
|
||||
options: {
|
||||
aspectRatio: "16:9",
|
||||
imageSize: "2K",
|
||||
seed: 42,
|
||||
thinkingLevel: "HIGH",
|
||||
includeThoughts: true,
|
||||
futureOption: true,
|
||||
},
|
||||
})
|
||||
Image.generate({
|
||||
model: googleProvider,
|
||||
prompt: "A lighthouse",
|
||||
options: { aspectRatio: "future-ratio", imageSize: "8K", thinkingLevel: "FUTURE" },
|
||||
})
|
||||
// @ts-expect-error Image generation options are request-scoped, not provider configuration.
|
||||
Google.configure({ image: { providerOptions: { imageSize: "2K" } } })
|
||||
// @ts-expect-error Known Google string options retain their value kind.
|
||||
Image.generate({ model: googleProvider, prompt: "A lighthouse", options: { imageSize: 2 } })
|
||||
// @ts-expect-error Known Google numeric options retain their value kind.
|
||||
Image.generate({ model: googleProvider, prompt: "A lighthouse", options: { seed: "42" } })
|
||||
// @ts-expect-error Known Google boolean options retain their value kind.
|
||||
Image.generate({ model: googleProvider, prompt: "A lighthouse", options: { includeThoughts: "yes" } })
|
||||
|
||||
const openai = OpenAI.image("gpt-image-2")
|
||||
// @ts-expect-error Image generation options are request-scoped, not provider configuration.
|
||||
OpenAI.configure({ image: { options: { quality: "medium" } } })
|
||||
const futureOpenAIOptions: ImageModelOptions<typeof openai> = { quality: "future-quality" }
|
||||
void futureOpenAIOptions
|
||||
Image.generate({
|
||||
model: openai,
|
||||
prompt: "A lighthouse",
|
||||
images: [ImageInput.url("https://example.com/source.png"), ImageInput.file("file_123")],
|
||||
options: {
|
||||
mask: ImageInput.bytes(Uint8Array.from([1]), "image/png"),
|
||||
quality: "hd",
|
||||
outputFormat: "webp",
|
||||
size: "2048x2048",
|
||||
future_option: true,
|
||||
},
|
||||
})
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", options: { quality: "future-quality", size: "256x256" } })
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", options: { size: "1792x1024" } })
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", options: { native_future_option: true } })
|
||||
// @ts-expect-error Known OpenAI string options retain their value kind.
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", options: { quality: 1 } })
|
||||
// @ts-expect-error Known OpenAI numeric options retain their value kind.
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", options: { outputCompression: "80" } })
|
||||
OpenAI.imageGeneration({ action: "future-action", quality: "future-quality", size: "2048x2048" })
|
||||
// @ts-expect-error Hosted image generation numeric options retain their value kind.
|
||||
OpenAI.imageGeneration({ partialImages: "2" })
|
||||
// @ts-expect-error Known Google-like options are inferred from the selected model.
|
||||
Image.generate({ model: google, prompt: "A lighthouse", options: { aspectRatio: "wide" } })
|
||||
|
||||
const xai = XAI.configure({ apiKey: "test" }).image("any-model-id")
|
||||
// @ts-expect-error Image generation options are request-scoped, not provider configuration.
|
||||
XAI.configure({ image: { options: { resolution: "1k" } } })
|
||||
Image.generate({
|
||||
model: xai,
|
||||
prompt: "A lighthouse",
|
||||
images: [ImageInput.url("data:image/png;base64,AQID"), ImageInput.file("file_123")],
|
||||
options: {
|
||||
n: 2,
|
||||
aspectRatio: "future-ratio",
|
||||
resolution: "future-resolution",
|
||||
responseFormat: "future-format",
|
||||
future_option: true,
|
||||
},
|
||||
})
|
||||
Image.generate({
|
||||
model: xai,
|
||||
prompt: "A lighthouse",
|
||||
options: { aspect_ratio: "16:9", response_format: "b64_json", native_future_option: true },
|
||||
})
|
||||
// @ts-expect-error Known xAI numeric options retain their value kind.
|
||||
Image.generate({ model: xai, prompt: "A lighthouse", options: { n: "2" } })
|
||||
// @ts-expect-error Known xAI string options retain their value kind.
|
||||
Image.generate({ model: xai, prompt: "A lighthouse", options: { resolution: 2 } })
|
||||
|
||||
const zai = ZAI.configure({ apiKey: "test" }).image("any-model-id")
|
||||
// @ts-expect-error Image generation options are request-scoped, not provider configuration.
|
||||
ZAI.configure({ image: { options: { quality: "hd" } } })
|
||||
Image.generate({
|
||||
model: zai,
|
||||
prompt: "A lighthouse",
|
||||
options: { quality: "future-quality", userID: "user-123", future_option: true },
|
||||
})
|
||||
Image.generate({ model: zai, prompt: "A lighthouse", options: { user_id: "raw-user" } })
|
||||
// @ts-expect-error Known Z.ai string options retain their value kind.
|
||||
Image.generate({ model: zai, prompt: "A lighthouse", options: { quality: 1 } })
|
||||
// @ts-expect-error Known Z.ai user IDs retain their value kind.
|
||||
Image.generate({ model: zai, prompt: "A lighthouse", options: { userID: 1 } })
|
||||
|
||||
declare const generic: ImageModel<ImageOptions>
|
||||
Image.generate({ model: generic, prompt: "A lighthouse", options: { arbitrary: true } })
|
||||
const explicitImageInput: ImageInput = ImageInput.url("https://example.com/image.png")
|
||||
void explicitImageInput
|
||||
|
||||
// @ts-expect-error Raw strings are ambiguous and are not image inputs.
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", images: ["AQID"] })
|
||||
// @ts-expect-error Byte image inputs require an explicit MIME type.
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", images: [{ type: "bytes", data: new Uint8Array() }] })
|
||||
// @ts-expect-error File URIs require an explicit MIME type for Gemini fileData.
|
||||
Image.generate({ model: google, prompt: "A lighthouse", images: [{ type: "file-uri", uri: "files/123" }] })
|
||||
|
||||
const request = Image.request({
|
||||
model: google,
|
||||
prompt: "A lighthouse",
|
||||
options: { aspectRatio: "1:1", futureOption: true },
|
||||
})
|
||||
const typedRequest: ImageRequestFor<GoogleLikeOptions> = request
|
||||
void typedRequest
|
||||
|
||||
// @ts-expect-error Image requests no longer expose a common count option.
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", count: 2 })
|
||||
// @ts-expect-error Image requests no longer expose a common size option.
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", size: { width: 1024, height: 1024 } })
|
||||
// @ts-expect-error Image requests no longer expose a common aspectRatio option.
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", aspectRatio: "16:9" })
|
||||
// @ts-expect-error Image requests no longer expose a common seed option.
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", seed: 1 })
|
||||
// @ts-expect-error Image requests do not expose metadata.
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", metadata: { trace: true } })
|
||||
// @ts-expect-error Masks are provider options, not a common image request field.
|
||||
Image.generate({ model: openai, prompt: "A lighthouse", mask: ImageInput.url("https://example.com/mask.png") })
|
||||
@@ -1,29 +0,0 @@
|
||||
export const dimensions = (data: Uint8Array) => {
|
||||
if (data[0] === 0x89 && data[1] === 0x50 && data[2] === 0x4e && data[3] === 0x47)
|
||||
return {
|
||||
width: readUint32(data, 16),
|
||||
height: readUint32(data, 20),
|
||||
}
|
||||
if (data[0] === 0xff && data[1] === 0xd8) {
|
||||
for (let offset = 2; offset + 8 < data.length; ) {
|
||||
if (data[offset] !== 0xff) {
|
||||
offset++
|
||||
continue
|
||||
}
|
||||
const marker = data[offset + 1]
|
||||
if (
|
||||
marker !== undefined &&
|
||||
[0xc0, 0xc1, 0xc2, 0xc3, 0xc5, 0xc6, 0xc7, 0xc9, 0xca, 0xcb, 0xcd, 0xce, 0xcf].includes(marker)
|
||||
)
|
||||
return {
|
||||
width: (data[offset + 7] << 8) | data[offset + 8],
|
||||
height: (data[offset + 5] << 8) | data[offset + 6],
|
||||
}
|
||||
offset += 2 + ((data[offset + 2] << 8) | data[offset + 3])
|
||||
}
|
||||
}
|
||||
throw new Error("Unsupported image fixture format")
|
||||
}
|
||||
|
||||
const readUint32 = (data: Uint8Array, offset: number) =>
|
||||
((data[offset] << 24) | (data[offset + 1] << 16) | (data[offset + 2] << 8) | data[offset + 3]) >>> 0
|
||||
@@ -1,56 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { Image, ImageInput } from "../../src"
|
||||
import { Google } from "../../src/providers"
|
||||
import { dimensions } from "../lib/image"
|
||||
import { recordedTests } from "../recorded-test"
|
||||
|
||||
const model = Google.configure({
|
||||
apiKey: process.env.GOOGLE_GENERATIVE_AI_API_KEY ?? "fixture",
|
||||
}).image("gemini-3.1-flash-image")
|
||||
|
||||
const recorded = recordedTests({
|
||||
prefix: "google-images",
|
||||
provider: "google",
|
||||
protocol: "google-images",
|
||||
requires: ["GOOGLE_GENERATIVE_AI_API_KEY"],
|
||||
})
|
||||
|
||||
describe("Google Images recorded", () => {
|
||||
recorded.effect("generates an image", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model,
|
||||
prompt: "A simple flat blue circle centered on a plain white background.",
|
||||
options: { aspectRatio: "1:1" },
|
||||
})
|
||||
|
||||
expect(response.images).toHaveLength(1)
|
||||
expect(response.image?.mediaType).toMatch(/^image\//)
|
||||
expect(response.image?.data).toBeInstanceOf(Uint8Array)
|
||||
expect(response.image?.data.length).toBeGreaterThan(0)
|
||||
}),
|
||||
)
|
||||
|
||||
recorded.effect("edits an image", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model,
|
||||
prompt:
|
||||
"Transform this minimal source into a bright orange sun icon with eight rounded rays on a pale blue background.",
|
||||
images: [
|
||||
ImageInput.bytes(
|
||||
yield* Effect.promise(() => Bun.file("test/fixtures/images/edit-source.jpg").bytes()),
|
||||
"image/jpeg",
|
||||
),
|
||||
],
|
||||
options: { aspectRatio: "1:1" },
|
||||
})
|
||||
|
||||
expect(response.image?.mediaType).toBe("image/jpeg")
|
||||
expect(response.image?.data).toBeInstanceOf(Uint8Array)
|
||||
if (!(response.image?.data instanceof Uint8Array)) throw new Error("Expected owned Google image bytes")
|
||||
expect(dimensions(response.image.data)).toEqual({ width: 1024, height: 1024 })
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -1,148 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { LLM, LLMEvent, LLMResponse, Model } from "../../src"
|
||||
import { OpenAIChat } from "../../src/protocols/openai-chat"
|
||||
import * as OpenAICompatible from "../../src/providers/openai-compatible"
|
||||
import * as OpenRouter from "../../src/providers/openrouter"
|
||||
import { LLMClient } from "../../src/route"
|
||||
import { recordedTests } from "../recorded-test"
|
||||
import { expectWeatherToolLoop, goldenWeatherToolLoopRequest, runWeatherToolLoop } from "../recorded-scenarios"
|
||||
|
||||
const cases = [
|
||||
{
|
||||
name: "OpenRouter",
|
||||
model: Model.update(
|
||||
OpenRouter.configure({
|
||||
apiKey: process.env.OPENROUTER_API_KEY ?? "fixture",
|
||||
providerOptions: { openrouter: { reasoning: { max_tokens: 1024 } } },
|
||||
}).model("anthropic/claude-sonnet-4.6"),
|
||||
{ compatibility: { reasoningField: "reasoning" } },
|
||||
),
|
||||
requires: ["OPENROUTER_API_KEY"],
|
||||
cassette: "openrouter-reasoning",
|
||||
structured: true,
|
||||
},
|
||||
{
|
||||
name: "Vercel AI Gateway",
|
||||
model: Model.update(
|
||||
OpenAICompatible.configure({
|
||||
provider: "vercel-ai-gateway",
|
||||
baseURL: "https://ai-gateway.vercel.sh/v1",
|
||||
apiKey: process.env.AI_GATEWAY_API_KEY ?? "fixture",
|
||||
http: { body: { reasoning: { enabled: true, max_tokens: 1024 } } },
|
||||
}).model("anthropic/claude-sonnet-4.6"),
|
||||
{ compatibility: { reasoningField: "reasoning" } },
|
||||
),
|
||||
requires: ["AI_GATEWAY_API_KEY"],
|
||||
cassette: "vercel-ai-gateway-reasoning",
|
||||
structured: true,
|
||||
},
|
||||
] as const
|
||||
|
||||
for (const item of cases) {
|
||||
const recorded = recordedTests({
|
||||
prefix: "openai-compatible-chat",
|
||||
provider: item.model.provider,
|
||||
protocol: "openai-chat",
|
||||
requires: item.requires,
|
||||
tags: ["reasoning"],
|
||||
metadata: { model: item.model.id },
|
||||
})
|
||||
|
||||
describe(`${item.name} reasoning recorded`, () => {
|
||||
recorded.effect.with(
|
||||
"streams scalar reasoning",
|
||||
{ cassette: item.cassette },
|
||||
() =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* LLMClient.generate(
|
||||
LLM.request({
|
||||
model: item.model,
|
||||
system: "Think through the arithmetic, then reply with only the final integer.",
|
||||
prompt: "What is 173 multiplied by 219?",
|
||||
generation: { maxTokens: 1536, temperature: 0 },
|
||||
}),
|
||||
)
|
||||
|
||||
expect(response.text.replaceAll(",", "").trim()).toBe("37887")
|
||||
expect(response.reasoning.length).toBeGreaterThan(0)
|
||||
expect(response.events.some(LLMEvent.is.reasoningDelta)).toBe(true)
|
||||
const metadata = response.message.content.find((part) => part.type === "reasoning")?.providerMetadata
|
||||
expect(metadata?.openai?.reasoningField).toBe(item.structured ? "reasoning" : "reasoning_content")
|
||||
expect(Array.isArray(metadata?.openai?.reasoningDetails)).toBe(item.structured)
|
||||
if (!item.structured) return
|
||||
const details = metadata?.openai?.reasoningDetails
|
||||
if (!Array.isArray(details)) return
|
||||
expect(
|
||||
details.some(
|
||||
(detail) =>
|
||||
typeof detail === "object" &&
|
||||
detail !== null &&
|
||||
"signature" in detail &&
|
||||
typeof detail.signature === "string" &&
|
||||
detail.signature.length > 0,
|
||||
),
|
||||
).toBe(true)
|
||||
|
||||
const replay = yield* LLMClient.prepare<OpenAIChat.OpenAIChatBody>(
|
||||
LLM.request({ model: item.model, messages: [response.message] }),
|
||||
)
|
||||
expect(replay.body.messages).toMatchObject([
|
||||
{ role: "assistant", content: response.text, reasoning: response.reasoning },
|
||||
])
|
||||
const replayDetails =
|
||||
replay.body.messages[0]?.role === "assistant" ? replay.body.messages[0].reasoning_details : undefined
|
||||
expect(Array.isArray(replayDetails)).toBe(true)
|
||||
if (!Array.isArray(replayDetails)) return
|
||||
expect(replayDetails).toEqual(details)
|
||||
expect(replayDetails).toHaveLength(1)
|
||||
expect(replayDetails[0]).toMatchObject({
|
||||
type: "reasoning.text",
|
||||
text: response.reasoning,
|
||||
signature: expect.any(String),
|
||||
})
|
||||
}),
|
||||
30_000,
|
||||
)
|
||||
|
||||
recorded.effect.with(
|
||||
"continues signed reasoning through a tool loop",
|
||||
{ cassette: `${item.cassette}-tool-loop`, tags: ["continuation", "tool", "tool-loop"] },
|
||||
() =>
|
||||
Effect.gen(function* () {
|
||||
const events = yield* runWeatherToolLoop(
|
||||
goldenWeatherToolLoopRequest({
|
||||
id: `${item.cassette}-tool-loop`,
|
||||
model: item.model,
|
||||
maxTokens: 1536,
|
||||
temperature: false,
|
||||
}),
|
||||
)
|
||||
|
||||
expectWeatherToolLoop(events)
|
||||
expect(
|
||||
LLMResponse.text({
|
||||
events: events.slice(events.findIndex(LLMEvent.is.stepFinish) + 1),
|
||||
}).trim(),
|
||||
).toMatch(/^Paris is sunny\.?$/)
|
||||
const details = events
|
||||
.filter(LLMEvent.is.reasoningEnd)
|
||||
.map((event) => event.providerMetadata?.openai?.reasoningDetails)
|
||||
.find(Array.isArray)
|
||||
expect(Array.isArray(details)).toBe(item.structured)
|
||||
if (!item.structured || !Array.isArray(details)) return
|
||||
expect(
|
||||
details.some(
|
||||
(detail) =>
|
||||
typeof detail === "object" &&
|
||||
detail !== null &&
|
||||
"signature" in detail &&
|
||||
typeof detail.signature === "string" &&
|
||||
detail.signature.length > 0,
|
||||
),
|
||||
).toBe(true)
|
||||
}),
|
||||
60_000,
|
||||
)
|
||||
})
|
||||
}
|
||||
@@ -1,116 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { LLM, LLMEvent } from "../../src"
|
||||
import { configure } from "../../src/providers/openai-compatible-responses"
|
||||
import { OpenAI } from "../../src/providers"
|
||||
import { OpenResponses } from "../../src/protocols/open-responses"
|
||||
import { OpenAICompatibleResponses } from "../../src/protocols/openai-compatible-responses"
|
||||
import { OpenAIResponses } from "../../src/protocols/openai-responses"
|
||||
import { LLMClient } from "../../src/route"
|
||||
import { it } from "../lib/effect"
|
||||
import { fixedResponse } from "../lib/http"
|
||||
import { sseEvents } from "../lib/sse"
|
||||
|
||||
describe("Open Responses-compatible route", () => {
|
||||
it.effect("uses the Open Responses baseline for a configured deployment", () =>
|
||||
Effect.gen(function* () {
|
||||
expect(OpenAICompatibleResponses.route.body).toBe(OpenResponses.protocol.body)
|
||||
expect(OpenAICompatibleResponses.route.transport).toBe(OpenResponses.httpTransport)
|
||||
expect(OpenAICompatibleResponses.route.body).not.toBe(OpenAIResponses.protocol.body)
|
||||
|
||||
const model = configure({
|
||||
apiKey: "test-key",
|
||||
baseURL: "https://responses.example.test/v1",
|
||||
provider: "example",
|
||||
}).model("example-model")
|
||||
const prepared = yield* LLMClient.prepare(
|
||||
LLM.request({
|
||||
model,
|
||||
system: "You are concise.",
|
||||
prompt: "Say hello.",
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.route).toBe("openai-compatible-responses")
|
||||
expect(prepared.protocol).toBe("open-responses")
|
||||
expect(prepared.model).toMatchObject({
|
||||
id: "example-model",
|
||||
provider: "example",
|
||||
route: {
|
||||
id: "openai-compatible-responses",
|
||||
endpoint: {
|
||||
baseURL: "https://responses.example.test/v1",
|
||||
path: "/responses",
|
||||
},
|
||||
},
|
||||
})
|
||||
expect(prepared.body).toEqual({
|
||||
model: "example-model",
|
||||
input: [
|
||||
{ role: "system", content: "You are concise." },
|
||||
{ role: "user", content: [{ type: "input_text", text: "Say hello." }] },
|
||||
],
|
||||
stream: true,
|
||||
})
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("rejects OpenAI-native tools", () =>
|
||||
Effect.gen(function* () {
|
||||
const model = configure({
|
||||
apiKey: "test-key",
|
||||
baseURL: "https://responses.example.test/v1",
|
||||
}).model("example-model")
|
||||
const error = yield* LLMClient.prepare(
|
||||
LLM.request({ model, prompt: "Draw.", tools: [OpenAI.imageGeneration()] }),
|
||||
).pipe(Effect.flip)
|
||||
|
||||
expect(error.reason._tag).toBe("InvalidRequest")
|
||||
expect(error.message).toContain("Open Responses does not support provider-native tool image_generation")
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("reads standard options from the Open Responses namespace", () =>
|
||||
Effect.gen(function* () {
|
||||
const model = configure({
|
||||
apiKey: "test-key",
|
||||
baseURL: "https://responses.example.test/v1",
|
||||
providerOptions: { openresponses: { reasoningEffort: "low", store: true } },
|
||||
}).model("example-model")
|
||||
const prepared = yield* LLMClient.prepare(LLM.request({ model, prompt: "Think." }))
|
||||
|
||||
expect(prepared.body).toMatchObject({
|
||||
reasoning: { effort: "low" },
|
||||
store: true,
|
||||
})
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("does not interpret OpenAI hosted-tool items", () =>
|
||||
Effect.gen(function* () {
|
||||
const model = configure({
|
||||
apiKey: "test-key",
|
||||
baseURL: "https://responses.example.test/v1",
|
||||
provider: "example",
|
||||
}).model("example-model")
|
||||
const response = yield* LLMClient.generate(LLM.request({ model, prompt: "Search." })).pipe(
|
||||
Effect.provide(
|
||||
fixedResponse(
|
||||
sseEvents(
|
||||
{
|
||||
type: "response.output_item.done",
|
||||
item: { type: "web_search_call", id: "ws_1", status: "completed", action: { query: "news" } },
|
||||
},
|
||||
{ type: "response.completed", response: { id: "resp_1" } },
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
expect(response.toolCalls).toEqual([])
|
||||
expect(response.events.find(LLMEvent.is.finish)).toMatchObject({
|
||||
providerMetadata: { openresponses: { responseId: "resp_1" } },
|
||||
})
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -1,62 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { Image, ImageInput } from "../../src"
|
||||
import { OpenAI } from "../../src/providers"
|
||||
import { dimensions } from "../lib/image"
|
||||
import { recordedTests } from "../recorded-test"
|
||||
|
||||
const model = OpenAI.configure({
|
||||
apiKey: process.env.OPENAI_API_KEY ?? "fixture",
|
||||
}).image("gpt-image-1-mini")
|
||||
|
||||
const recorded = recordedTests({
|
||||
prefix: "openai-images",
|
||||
provider: "openai",
|
||||
protocol: "openai-images",
|
||||
requires: ["OPENAI_API_KEY"],
|
||||
})
|
||||
|
||||
describe("OpenAI Images recorded", () => {
|
||||
recorded.effect("generates an image", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model,
|
||||
prompt: "A simple flat black circle centered on a plain white background.",
|
||||
options: { quality: "low", outputFormat: "jpeg", outputCompression: 10, size: "1024x1024" },
|
||||
})
|
||||
|
||||
expect(response.images).toHaveLength(1)
|
||||
expect(response.image?.mediaType).toBe("image/jpeg")
|
||||
expect(response.image?.data).toBeInstanceOf(Uint8Array)
|
||||
expect(response.image?.data.length).toBeGreaterThan(0)
|
||||
}),
|
||||
)
|
||||
|
||||
recorded.effect.with(
|
||||
"edits an image",
|
||||
{
|
||||
options: {
|
||||
match: (incoming, recorded) => incoming.method === recorded.method && incoming.url === recorded.url,
|
||||
},
|
||||
},
|
||||
() =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model,
|
||||
prompt: "Keep the simple shape and change it from black to bright green.",
|
||||
images: [
|
||||
ImageInput.bytes(
|
||||
yield* Effect.promise(() => Bun.file("test/fixtures/images/edit-source.jpg").bytes()),
|
||||
"image/jpeg",
|
||||
),
|
||||
],
|
||||
options: { quality: "low", outputFormat: "jpeg", outputCompression: 10, size: "1024x1024" },
|
||||
})
|
||||
|
||||
expect(response.image?.mediaType).toBe("image/jpeg")
|
||||
expect(response.image?.data).toBeInstanceOf(Uint8Array)
|
||||
if (!(response.image?.data instanceof Uint8Array)) throw new Error("Expected owned OpenAI image bytes")
|
||||
expect(dimensions(response.image.data)).toEqual({ width: 1024, height: 1024 })
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -1,66 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { LLM, LLMEvent, Message } from "../../src"
|
||||
import { OpenAI } from "../../src/providers"
|
||||
import { recordedTests } from "../recorded-test"
|
||||
|
||||
const openai = OpenAI.configure({
|
||||
apiKey: process.env.OPENAI_API_KEY ?? "fixture",
|
||||
})
|
||||
|
||||
const recorded = recordedTests({
|
||||
prefix: "openai-responses-images",
|
||||
provider: "openai",
|
||||
protocol: "openai-responses",
|
||||
requires: ["OPENAI_API_KEY"],
|
||||
})
|
||||
|
||||
describe("OpenAI Responses image generation recorded", () => {
|
||||
recorded.effect("generates and edits an image with the hosted tool", () =>
|
||||
Effect.gen(function* () {
|
||||
const initial = Message.user("Generate a simple flat black triangle centered on a plain white background.")
|
||||
const tools = [
|
||||
OpenAI.imageGeneration({
|
||||
action: "auto",
|
||||
quality: "low",
|
||||
size: "1024x1024",
|
||||
outputFormat: "jpeg",
|
||||
outputCompression: 10,
|
||||
partialImages: 0,
|
||||
}),
|
||||
]
|
||||
const response = yield* LLM.generate(
|
||||
LLM.request({
|
||||
model: openai.responses("gpt-5-mini"),
|
||||
messages: [initial],
|
||||
tools,
|
||||
toolChoice: "image_generation",
|
||||
}),
|
||||
)
|
||||
|
||||
const result = response.events.find(LLMEvent.is.toolResult)
|
||||
expect(result).toBeDefined()
|
||||
expect(result?.providerExecuted).toBe(true)
|
||||
expect(result?.result.type).toBe("content")
|
||||
if (result?.result.type !== "content") return
|
||||
expect(result.result.value).toHaveLength(1)
|
||||
expect(result.result.value[0]?.type).toBe("file")
|
||||
if (result.result.value[0]?.type !== "file") return
|
||||
expect(result.result.value[0].mime).toBe("image/jpeg")
|
||||
expect(result.result.value[0].uri.startsWith("data:image/jpeg;base64,")).toBe(true)
|
||||
|
||||
const edited = yield* LLM.generate(
|
||||
LLM.request({
|
||||
model: openai.responses("gpt-5-mini"),
|
||||
messages: [initial, response.message, Message.user("Now make the triangle blue.")],
|
||||
tools,
|
||||
toolChoice: "image_generation",
|
||||
}),
|
||||
)
|
||||
const editedResult = edited.events.find(LLMEvent.is.toolResult)
|
||||
expect(editedResult?.result.type).toBe("content")
|
||||
if (editedResult?.result.type !== "content") return
|
||||
expect(editedResult.result.value[0]?.type).toBe("file")
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -1,192 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { LLM, Message } from "../../src"
|
||||
import { LLMClient } from "../../src/route"
|
||||
import * as OpenRouter from "../../src/providers/openrouter"
|
||||
import { it } from "../lib/effect"
|
||||
import { fixedResponse } from "../lib/http"
|
||||
import { sseEvents } from "../lib/sse"
|
||||
|
||||
describe("OpenRouter", () => {
|
||||
it.effect("prepares OpenRouter models through the OpenAI-compatible Chat route", () =>
|
||||
Effect.gen(function* () {
|
||||
const model = OpenRouter.configure({ apiKey: "test-key" }).model("openai/gpt-4o-mini")
|
||||
|
||||
expect(model).toMatchObject({
|
||||
id: "openai/gpt-4o-mini",
|
||||
provider: "openrouter",
|
||||
route: { id: "openrouter" },
|
||||
})
|
||||
expect(model.route.endpoint.baseURL).toBe("https://openrouter.ai/api/v1")
|
||||
|
||||
const prepared = yield* LLMClient.prepare(LLM.request({ model, prompt: "Say hello." }))
|
||||
|
||||
expect(prepared.route).toBe("openrouter")
|
||||
expect(prepared.body).toMatchObject({
|
||||
model: "openai/gpt-4o-mini",
|
||||
messages: [{ role: "user", content: "Say hello." }],
|
||||
stream: true,
|
||||
})
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("applies OpenRouter payload options from the model helper", () =>
|
||||
Effect.gen(function* () {
|
||||
const prepared = yield* LLMClient.prepare(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({
|
||||
apiKey: "test-key",
|
||||
providerOptions: {
|
||||
openrouter: {
|
||||
usage: true,
|
||||
reasoning: { effort: "high" },
|
||||
promptCacheKey: "session_123",
|
||||
},
|
||||
},
|
||||
}).model("anthropic/claude-3.7-sonnet:thinking"),
|
||||
prompt: "Think briefly.",
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.body).toMatchObject({
|
||||
usage: { include: true },
|
||||
reasoning: { effort: "high" },
|
||||
prompt_cache_key: "session_123",
|
||||
})
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("preserves the upstream provider finish reason", () =>
|
||||
Effect.gen(function* () {
|
||||
const model = OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6")
|
||||
const response = yield* LLMClient.generate(LLM.request({ model, prompt: "Say hello." })).pipe(
|
||||
Effect.provide(
|
||||
fixedResponse(
|
||||
sseEvents({
|
||||
choices: [{ delta: { content: "Hello" }, finish_reason: "stop", native_finish_reason: "end_turn" }],
|
||||
}),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
expect(response.finishReason).toEqual({ normalized: "stop", raw: "end_turn" })
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("fails on a mid-stream provider error", () =>
|
||||
Effect.gen(function* () {
|
||||
const model = OpenRouter.configure({ apiKey: "test-key" }).model("openai/gpt-4o-mini")
|
||||
const error = yield* LLMClient.generate(LLM.request({ model, prompt: "Say hello." })).pipe(
|
||||
Effect.provide(
|
||||
fixedResponse(
|
||||
sseEvents({
|
||||
error: { code: 502, message: "Provider disconnected" },
|
||||
}),
|
||||
),
|
||||
),
|
||||
Effect.flip,
|
||||
)
|
||||
|
||||
expect(error.reason).toMatchObject({ _tag: "ProviderInternal" })
|
||||
expect(error.message).toContain("Provider disconnected")
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("preserves manually supplied reasoning details", () =>
|
||||
Effect.gen(function* () {
|
||||
const details = [
|
||||
{ type: "reasoning.text", text: "Think", format: "anthropic-claude-v1", index: 0 },
|
||||
{ type: "reasoning.text", text: "ing", format: "anthropic-claude-v1", index: 0 },
|
||||
{ type: "reasoning.text", signature: "signed", format: "anthropic-claude-v1", index: 0 },
|
||||
{ type: "reasoning.encrypted", data: "opaque", format: "openai-responses-v1", index: 1 },
|
||||
]
|
||||
const prepared = yield* LLMClient.prepare<OpenRouter.OpenRouterBody>(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
messages: [
|
||||
Message.assistant([
|
||||
{
|
||||
type: "reasoning",
|
||||
text: "Thinking",
|
||||
providerMetadata: { openai: { reasoningField: "reasoning", reasoningDetails: details } },
|
||||
},
|
||||
]),
|
||||
],
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.body.messages).toEqual([
|
||||
{
|
||||
role: "assistant",
|
||||
content: null,
|
||||
reasoning: "Thinking",
|
||||
reasoning_details: details,
|
||||
},
|
||||
])
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("preserves opaque and duplicate continuation details", () =>
|
||||
Effect.gen(function* () {
|
||||
const details = [
|
||||
{ type: "reasoning.future", format: "provider-v2", state: { opaque: true } },
|
||||
{ type: "reasoning.encrypted", id: "state", data: "opaque" },
|
||||
{ type: "reasoning.encrypted", id: "state", data: "opaque" },
|
||||
]
|
||||
const prepared = yield* LLMClient.prepare<OpenRouter.OpenRouterBody>(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
messages: [
|
||||
Message.assistant({
|
||||
type: "reasoning",
|
||||
text: "Thinking",
|
||||
providerMetadata: { openai: { reasoningField: "reasoning", reasoningDetails: details } },
|
||||
}),
|
||||
],
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.body.messages).toEqual([
|
||||
{ role: "assistant", content: null, reasoning: "Thinking", reasoning_details: details },
|
||||
])
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("does not merge distinct adjacent reasoning text blocks", () =>
|
||||
Effect.gen(function* () {
|
||||
const details = [
|
||||
{ type: "reasoning.text", id: "first", index: 0, text: "A", opaque: "first" },
|
||||
{ type: "reasoning.text", id: "second", index: 1, text: "B", opaque: "second" },
|
||||
]
|
||||
const prepared = yield* LLMClient.prepare<OpenRouter.OpenRouterBody>(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
messages: [
|
||||
Message.assistant({
|
||||
type: "reasoning",
|
||||
text: "AB",
|
||||
providerMetadata: { openai: { reasoningField: "reasoning", reasoningDetails: details } },
|
||||
}),
|
||||
],
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.body.messages).toEqual([
|
||||
{ role: "assistant", content: null, reasoning: "AB", reasoning_details: details },
|
||||
])
|
||||
}),
|
||||
)
|
||||
|
||||
it.effect("omits scalar reasoning without continuation details", () =>
|
||||
Effect.gen(function* () {
|
||||
const prepared = yield* LLMClient.prepare<OpenRouter.OpenRouterBody>(
|
||||
LLM.request({
|
||||
model: OpenRouter.configure({ apiKey: "test-key" }).model("anthropic/claude-sonnet-4.6"),
|
||||
messages: [Message.assistant({ type: "reasoning", text: "Thinking" })],
|
||||
}),
|
||||
)
|
||||
|
||||
expect(prepared.body.messages).toEqual([{ role: "assistant", content: null }])
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -1,207 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect, Schema, Stream } from "effect"
|
||||
import { LLM, LLMResponse, Message, ToolDefinition, type Model } from "../../src"
|
||||
import { AmazonBedrock, Anthropic, Google, OpenAI, XAI } from "../../src/providers"
|
||||
import { LLMClient } from "../../src/route"
|
||||
import { Tool } from "../../src/tool"
|
||||
import { runTools } from "../lib/tool-runtime"
|
||||
import { recordedTests } from "../recorded-test"
|
||||
|
||||
const CODE = "ORCHID-7391"
|
||||
const PDF =
|
||||
"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"
|
||||
|
||||
const openai = OpenAI.configure({ apiKey: process.env.OPENAI_API_KEY ?? "fixture" })
|
||||
const anthropic = Anthropic.configure({ apiKey: process.env.ANTHROPIC_API_KEY ?? "fixture" })
|
||||
const google = Google.configure({ apiKey: process.env.GOOGLE_API_KEY ?? "fixture" })
|
||||
const xai = XAI.configure({ apiKey: process.env.XAI_API_KEY ?? "fixture" })
|
||||
const bedrock = AmazonBedrock.configure({
|
||||
apiKey: process.env.AWS_BEDROCK_API_KEY ?? "fixture",
|
||||
region: process.env.AWS_REGION ?? "us-east-1",
|
||||
})
|
||||
|
||||
const targets: ReadonlyArray<{
|
||||
readonly id: string
|
||||
readonly name: string
|
||||
readonly provider: string
|
||||
readonly protocol: string
|
||||
readonly requires: string
|
||||
readonly filename: string
|
||||
readonly maxTokens: number
|
||||
readonly model: Model
|
||||
}> = [
|
||||
{
|
||||
id: "openai",
|
||||
name: "OpenAI Responses gpt-4o-mini",
|
||||
provider: "openai",
|
||||
protocol: "openai-responses",
|
||||
requires: "OPENAI_API_KEY",
|
||||
filename: "verification.pdf",
|
||||
maxTokens: 40,
|
||||
model: openai.responses("gpt-4o-mini"),
|
||||
},
|
||||
{
|
||||
id: "anthropic",
|
||||
name: "Anthropic Haiku 4.5",
|
||||
provider: "anthropic",
|
||||
protocol: "anthropic-messages",
|
||||
requires: "ANTHROPIC_API_KEY",
|
||||
filename: "verification.pdf",
|
||||
maxTokens: 40,
|
||||
model: anthropic.model("claude-haiku-4-5-20251001"),
|
||||
},
|
||||
{
|
||||
id: "gemini",
|
||||
name: "Gemini 3.5 Flash",
|
||||
provider: "google",
|
||||
protocol: "gemini",
|
||||
requires: "GOOGLE_API_KEY",
|
||||
filename: "verification.pdf",
|
||||
maxTokens: 256,
|
||||
model: google.model("gemini-3.5-flash"),
|
||||
},
|
||||
{
|
||||
id: "xai",
|
||||
name: "xAI Grok 4.5",
|
||||
provider: "xai",
|
||||
protocol: "openai-responses",
|
||||
requires: "XAI_API_KEY",
|
||||
filename: "verification.pdf",
|
||||
maxTokens: 40,
|
||||
model: xai.responses("grok-4.5"),
|
||||
},
|
||||
{
|
||||
id: "bedrock",
|
||||
name: "Bedrock Claude Haiku 4.5",
|
||||
provider: "amazon-bedrock",
|
||||
protocol: "bedrock-converse",
|
||||
requires: "AWS_BEDROCK_API_KEY",
|
||||
filename: "verification",
|
||||
maxTokens: 40,
|
||||
model: bedrock.model("us.anthropic.claude-haiku-4-5-20251001-v1:0"),
|
||||
},
|
||||
]
|
||||
|
||||
const recorded = recordedTests({ prefix: "pdf", tags: ["pdf"] })
|
||||
const prompt = "Return only the verification code from the PDF."
|
||||
const readPdf = ToolDefinition.make({
|
||||
name: "read_pdf",
|
||||
description: "Read the attached PDF.",
|
||||
inputSchema: { type: "object", properties: {}, additionalProperties: false },
|
||||
})
|
||||
const readPdfRuntime = Tool.make({
|
||||
description: readPdf.description,
|
||||
parameters: Schema.Struct({ path: Schema.String }),
|
||||
success: Schema.String,
|
||||
execute: () => Effect.succeed("PDF read successfully"),
|
||||
toModelOutput: () => [
|
||||
{ type: "text", text: "PDF read successfully" },
|
||||
{
|
||||
type: "file",
|
||||
uri: `data:application/pdf;base64,${PDF}`,
|
||||
mime: "application/pdf",
|
||||
name: "verification.pdf",
|
||||
},
|
||||
],
|
||||
})
|
||||
|
||||
const expectCode = (response: LLMResponse) => {
|
||||
expect(response.finishReason.normalized).toBe("stop")
|
||||
expect(response.text.toUpperCase()).toContain(CODE)
|
||||
}
|
||||
|
||||
describe("PDF recorded", () => {
|
||||
for (const target of targets) {
|
||||
recorded.effect.with(
|
||||
`reads a user PDF with ${target.name}`,
|
||||
{
|
||||
id: `${target.id}-user-input`,
|
||||
provider: target.provider,
|
||||
protocol: target.protocol,
|
||||
requires: [target.requires],
|
||||
tags: ["user-input"],
|
||||
},
|
||||
Effect.gen(function* () {
|
||||
expectCode(
|
||||
yield* LLMClient.generate(
|
||||
LLM.request({
|
||||
id: `recorded_pdf_${target.id}_user_input`,
|
||||
model: target.model,
|
||||
cache: "none",
|
||||
generation: { maxTokens: target.maxTokens, temperature: 0 },
|
||||
messages: [
|
||||
Message.user([
|
||||
{ type: "media", mediaType: "application/pdf", data: PDF, filename: target.filename },
|
||||
{ type: "text", text: prompt },
|
||||
]),
|
||||
],
|
||||
}),
|
||||
),
|
||||
)
|
||||
}),
|
||||
)
|
||||
|
||||
recorded.effect.with(
|
||||
`reads a PDF tool result with ${target.name}`,
|
||||
{
|
||||
id: `${target.id}-tool-result`,
|
||||
provider: target.provider,
|
||||
protocol: target.protocol,
|
||||
requires: [target.requires],
|
||||
tags: ["tool", "tool-result"],
|
||||
},
|
||||
Effect.gen(function* () {
|
||||
if (target.id === "gemini") {
|
||||
const events = Array.from(
|
||||
yield* runTools({
|
||||
request: LLM.request({
|
||||
id: "recorded_pdf_gemini_tool_result",
|
||||
model: target.model,
|
||||
system:
|
||||
"Call read_pdf exactly once with path verification.pdf, then reply only with the verification code from its PDF.",
|
||||
prompt: "Use read_pdf with path verification.pdf and return the verification code.",
|
||||
cache: "none",
|
||||
generation: { maxTokens: target.maxTokens, temperature: 0 },
|
||||
}),
|
||||
tools: { read_pdf: readPdfRuntime },
|
||||
}).pipe(Stream.runCollect),
|
||||
)
|
||||
expect(events.at(-1)).toMatchObject({ type: "finish", reason: { normalized: "stop" } })
|
||||
expect(LLMResponse.text({ events }).toUpperCase()).toContain(CODE)
|
||||
return
|
||||
}
|
||||
|
||||
expectCode(
|
||||
yield* LLMClient.generate(
|
||||
LLM.request({
|
||||
id: `recorded_pdf_${target.id}_tool_result`,
|
||||
model: target.model,
|
||||
system: "Read the PDF returned by the tool and follow the user's response format exactly.",
|
||||
cache: "none",
|
||||
generation: { maxTokens: target.maxTokens, temperature: 0 },
|
||||
messages: [
|
||||
Message.user(prompt),
|
||||
Message.assistant([{ type: "tool-call", id: "call_pdf_1", name: readPdf.name, input: {} }]),
|
||||
Message.tool({
|
||||
id: "call_pdf_1",
|
||||
name: readPdf.name,
|
||||
resultType: "content",
|
||||
result: [
|
||||
{ type: "text", text: "PDF read successfully" },
|
||||
{
|
||||
type: "file",
|
||||
uri: `data:application/pdf;base64,${PDF}`,
|
||||
mime: "application/pdf",
|
||||
name: target.filename,
|
||||
},
|
||||
],
|
||||
}),
|
||||
],
|
||||
tools: [readPdf],
|
||||
}),
|
||||
),
|
||||
)
|
||||
}),
|
||||
)
|
||||
}
|
||||
})
|
||||
@@ -1,55 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { Image, ImageInput } from "../../src"
|
||||
import { XAI } from "../../src/providers"
|
||||
import { dimensions } from "../lib/image"
|
||||
import { recordedTests } from "../recorded-test"
|
||||
|
||||
const model = XAI.configure({
|
||||
apiKey: process.env.XAI_API_KEY ?? "fixture",
|
||||
}).image("grok-imagine-image")
|
||||
|
||||
const recorded = recordedTests({
|
||||
prefix: "xai-images",
|
||||
provider: "xai",
|
||||
protocol: "xai-images",
|
||||
requires: ["XAI_API_KEY"],
|
||||
})
|
||||
|
||||
describe("xAI Images recorded", () => {
|
||||
recorded.effect("generates an image", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model,
|
||||
prompt: "A simple flat black diamond centered on a plain white background.",
|
||||
options: { aspectRatio: "1:1", resolution: "1k", responseFormat: "b64_json" },
|
||||
})
|
||||
|
||||
expect(response.images).toHaveLength(1)
|
||||
expect(response.image?.mediaType.startsWith("image/")).toBe(true)
|
||||
expect(response.image?.data).toBeInstanceOf(Uint8Array)
|
||||
expect(response.image?.data.length).toBeGreaterThan(0)
|
||||
}),
|
||||
)
|
||||
|
||||
recorded.effect("edits an image", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model,
|
||||
prompt: "Keep the simple shape and change it from black to bright purple.",
|
||||
images: [
|
||||
ImageInput.bytes(
|
||||
yield* Effect.promise(() => Bun.file("test/fixtures/images/edit-source.jpg").bytes()),
|
||||
"image/jpeg",
|
||||
),
|
||||
],
|
||||
options: { aspectRatio: "1:1", resolution: "1k", responseFormat: "b64_json" },
|
||||
})
|
||||
|
||||
expect(response.image?.mediaType).toMatch(/^image\/(jpeg|png)$/)
|
||||
expect(response.image?.data).toBeInstanceOf(Uint8Array)
|
||||
if (!(response.image?.data instanceof Uint8Array)) throw new Error("Expected owned xAI image bytes")
|
||||
expect(dimensions(response.image.data)).toEqual({ width: 1024, height: 1024 })
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -1,109 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect, Layer } from "effect"
|
||||
import { Headers, HttpClientRequest } from "effect/unstable/http"
|
||||
import { Image, ImageClient } from "../../src"
|
||||
import { XAI } from "../../src/providers"
|
||||
import { Auth } from "../../src/route"
|
||||
import { it } from "../lib/effect"
|
||||
import { dynamicResponse } from "../lib/http"
|
||||
|
||||
describe("xAI Images", () => {
|
||||
it.effect("generates through the OpenAI-compatible Images API", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model: XAI.configure({
|
||||
apiKey: "test",
|
||||
baseURL: "https://api.xai.test/v1",
|
||||
http: { body: { configured: true }, headers: { "x-default": "yes" } },
|
||||
}).image("grok-imagine-image"),
|
||||
prompt: "A robot tending a rooftop garden",
|
||||
options: {
|
||||
n: 2,
|
||||
aspectRatio: "16:9",
|
||||
aspect_ratio: "4:3",
|
||||
resolution: "1k",
|
||||
responseFormat: "url",
|
||||
response_format: "b64_json",
|
||||
future_option: true,
|
||||
},
|
||||
http: {
|
||||
body: { resolution: "2k", future_option: "http" },
|
||||
headers: { "x-request": "yes" },
|
||||
query: { trace: "1" },
|
||||
},
|
||||
})
|
||||
|
||||
expect(response.images).toHaveLength(2)
|
||||
expect(response.image?.mediaType).toBe("image/jpeg")
|
||||
expect(response.image?.data).toEqual(Uint8Array.from([1, 2, 3]))
|
||||
expect(response.images[1]?.mediaType).toBe("application/octet-stream")
|
||||
expect(response.images[1]?.data).toBe("https://api.xai.test/image.jpg")
|
||||
expect(response.usage?.providerMetadata).toEqual({ xai: { num_images: 2 } })
|
||||
expect(response.providerMetadata).toEqual({ xai: { usage: { num_images: 2 } } })
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
const request = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
|
||||
expect(request.url).toBe("https://api.xai.test/v1/images/generations?trace=1")
|
||||
expect(request.headers.get("authorization")).toBe("Bearer test")
|
||||
expect(request.headers.get("x-default")).toBe("yes")
|
||||
expect(request.headers.get("x-request")).toBe("yes")
|
||||
expect(JSON.parse(input.text)).toEqual({
|
||||
model: "grok-imagine-image",
|
||||
prompt: "A robot tending a rooftop garden",
|
||||
n: 2,
|
||||
aspect_ratio: "4:3",
|
||||
resolution: "2k",
|
||||
response_format: "b64_json",
|
||||
future_option: "http",
|
||||
configured: true,
|
||||
})
|
||||
return input.respond(
|
||||
JSON.stringify({
|
||||
data: [
|
||||
{ b64_json: "AQID", url: null, mime_type: "image/jpeg" },
|
||||
{ b64_json: null, url: "https://api.xai.test/image.jpg", mime_type: null },
|
||||
],
|
||||
usage: { num_images: 2 },
|
||||
}),
|
||||
{ headers: { "content-type": "application/json" } },
|
||||
)
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("supports request-level custom auth", () =>
|
||||
Image.generate({
|
||||
model: XAI.configure({
|
||||
baseURL: "https://api.xai.test/v1",
|
||||
auth: Auth.custom((input) =>
|
||||
Effect.succeed(Headers.set(input.headers, "x-custom-auth", new URL(input.url).hostname)),
|
||||
),
|
||||
}).image("grok-imagine-image"),
|
||||
prompt: "A robot tending a rooftop garden",
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
const request = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
|
||||
expect(request.headers.get("x-custom-auth")).toBe("api.xai.test")
|
||||
return input.respond(JSON.stringify({ data: [{ b64_json: "AQID", mime_type: "image/png" }] }), {
|
||||
headers: { "content-type": "application/json" },
|
||||
})
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
})
|
||||
@@ -1,32 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect } from "effect"
|
||||
import { Image } from "../../src"
|
||||
import { ZAI } from "../../src/providers"
|
||||
import { recordedTests } from "../recorded-test"
|
||||
|
||||
const model = ZAI.configure({ apiKey: process.env.ZAI_API_KEY ?? "fixture" }).image("cogview-4-250304")
|
||||
|
||||
const recorded = recordedTests({
|
||||
prefix: "zai-images",
|
||||
provider: "zai",
|
||||
protocol: "zai-images",
|
||||
requires: ["ZAI_API_KEY"],
|
||||
})
|
||||
|
||||
describe("Z.ai Images recorded", () => {
|
||||
recorded.effect("generates an image", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model,
|
||||
prompt: "A simple flat red circle centered on a plain white background.",
|
||||
options: { size: "1024x1024", quality: "standard", userID: "opencode-image-test" },
|
||||
})
|
||||
|
||||
expect(response.images).toHaveLength(1)
|
||||
expect(response.image?.mediaType).toBe("application/octet-stream")
|
||||
expect(response.image?.data).toBeString()
|
||||
expect(response.image?.data).toStartWith("https://")
|
||||
expect(response.providerMetadata?.zai).toBeDefined()
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -1,130 +0,0 @@
|
||||
import { describe, expect } from "bun:test"
|
||||
import { Effect, Layer } from "effect"
|
||||
import { HttpClientRequest } from "effect/unstable/http"
|
||||
import { Image, ImageClient } from "../../src"
|
||||
import { ZAI } from "../../src/providers"
|
||||
import { it } from "../lib/effect"
|
||||
import { dynamicResponse, fixedResponse } from "../lib/http"
|
||||
|
||||
describe("Z.ai Images", () => {
|
||||
it.effect("generates through the Z.ai Images API", () =>
|
||||
Effect.gen(function* () {
|
||||
const response = yield* Image.generate({
|
||||
model: ZAI.configure({
|
||||
apiKey: "test",
|
||||
baseURL: "https://api.z.ai.test/api/paas/v4",
|
||||
headers: { "x-default": "yes" },
|
||||
http: { body: { configured: true, quality: "configured" }, query: { trace: "default" } },
|
||||
}).image("glm-image"),
|
||||
prompt: "A red circle on a white background",
|
||||
options: {
|
||||
quality: "hd",
|
||||
userID: "alias-user",
|
||||
user_id: "raw-user",
|
||||
future_option: true,
|
||||
},
|
||||
http: {
|
||||
headers: { "x-request": "yes" },
|
||||
query: { trace: "request" },
|
||||
body: { quality: "final", user_id: "final-user" },
|
||||
},
|
||||
})
|
||||
|
||||
expect(response.images).toHaveLength(1)
|
||||
expect(response.image?.mediaType).toBe("application/octet-stream")
|
||||
expect(response.image?.data).toBe("https://cdn.z.ai/generated.png")
|
||||
expect(response.providerMetadata).toEqual({
|
||||
zai: {
|
||||
created: 1_760_335_349,
|
||||
id: "generation-1",
|
||||
requestID: "request-1",
|
||||
contentFilter: [{ role: "future-role", level: 4.5 }],
|
||||
},
|
||||
})
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) =>
|
||||
Effect.gen(function* () {
|
||||
const request = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
|
||||
expect(request.url).toBe("https://api.z.ai.test/api/paas/v4/images/generations?trace=request")
|
||||
expect(request.headers.get("authorization")).toBe("Bearer test")
|
||||
expect(request.headers.get("x-default")).toBe("yes")
|
||||
expect(request.headers.get("x-request")).toBe("yes")
|
||||
expect(JSON.parse(input.text)).toEqual({
|
||||
model: "glm-image",
|
||||
prompt: "A red circle on a white background",
|
||||
quality: "final",
|
||||
user_id: "final-user",
|
||||
future_option: true,
|
||||
configured: true,
|
||||
})
|
||||
return input.respond(
|
||||
JSON.stringify({
|
||||
created: 1_760_335_349,
|
||||
id: "generation-1",
|
||||
request_id: "request-1",
|
||||
data: [{ url: "https://cdn.z.ai/generated.png" }],
|
||||
content_filter: [{ role: "future-role", level: 4.5 }],
|
||||
}),
|
||||
{ headers: { "content-type": "application/json" } },
|
||||
)
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("lets raw native options override aliases", () =>
|
||||
Image.generate({
|
||||
model: ZAI.configure({ apiKey: "test" }).image("model"),
|
||||
prompt: "test",
|
||||
options: { quality: "future-quality", userID: "x", user_id: "raw-user" },
|
||||
}).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
dynamicResponse((input) => {
|
||||
expect(JSON.parse(input.text)).toMatchObject({ quality: "future-quality", user_id: "raw-user" })
|
||||
return Effect.succeed(
|
||||
input.respond(JSON.stringify({ data: [{ url: "https://example.test/image.jpg" }] }), {
|
||||
headers: { "content-type": "application/json" },
|
||||
}),
|
||||
)
|
||||
}),
|
||||
),
|
||||
),
|
||||
),
|
||||
),
|
||||
)
|
||||
|
||||
it.effect("rejects invalid response structures", () =>
|
||||
Effect.gen(function* () {
|
||||
const model = ZAI.configure({ apiKey: "test" }).image("model")
|
||||
const payloads = [
|
||||
{},
|
||||
{ data: [] },
|
||||
{ data: [{ b64_json: "image" }] },
|
||||
{ data: [{ url: 1 }] },
|
||||
{ data: [{ url: "https://example.test/image.jpg" }], content_filter: [{ role: 1, level: "high" }] },
|
||||
]
|
||||
|
||||
yield* Effect.forEach(payloads, (payload) =>
|
||||
Image.generate({ model, prompt: "test" }).pipe(
|
||||
Effect.provide(
|
||||
ImageClient.layer.pipe(
|
||||
Layer.provide(
|
||||
fixedResponse(JSON.stringify(payload), { headers: { "content-type": "application/json" } }),
|
||||
),
|
||||
),
|
||||
),
|
||||
Effect.flip,
|
||||
Effect.tap((error) => Effect.sync(() => expect(error.reason._tag).toBe("InvalidProviderOutput"))),
|
||||
),
|
||||
)
|
||||
}),
|
||||
)
|
||||
})
|
||||
@@ -1,8 +0,0 @@
|
||||
{
|
||||
"$schema": "https://json.schemastore.org/tsconfig",
|
||||
"extends": "./tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"allowImportingTsExtensions": false,
|
||||
"noEmit": false
|
||||
}
|
||||
}
|
||||
@@ -1,12 +0,0 @@
|
||||
{
|
||||
"$schema": "https://json.schemastore.org/tsconfig.json",
|
||||
"extends": "@tsconfig/bun/tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"rootDir": "src",
|
||||
"outDir": "dist",
|
||||
"declaration": true,
|
||||
"lib": ["ESNext", "DOM", "DOM.Iterable"],
|
||||
"noUncheckedIndexedAccess": false
|
||||
},
|
||||
"include": ["src"]
|
||||
}
|
||||
@@ -1,9 +0,0 @@
|
||||
{
|
||||
"$schema": "https://json.schemastore.org/tsconfig",
|
||||
"extends": "./tsconfig.json",
|
||||
"compilerOptions": {
|
||||
"noEmit": true,
|
||||
"rootDir": "."
|
||||
},
|
||||
"include": ["test/**/*.types.ts"]
|
||||
}
|
||||
@@ -97,7 +97,6 @@ export async function setupTimeline(
|
||||
locale?: string
|
||||
deviceScaleFactor?: number
|
||||
seedHistory?: boolean
|
||||
protocol?: "v1" | "v2"
|
||||
} = {},
|
||||
) {
|
||||
const sessions = input.sessions ?? [session()]
|
||||
@@ -115,7 +114,6 @@ export async function setupTimeline(
|
||||
retry: input.eventRetry ?? 20,
|
||||
})
|
||||
await mockOpenCodeServer(page, {
|
||||
protocol: input.protocol,
|
||||
directory,
|
||||
project: project(),
|
||||
provider: provider(),
|
||||
|
||||
@@ -1,50 +0,0 @@
|
||||
import { expect, test } from "@playwright/test"
|
||||
import { base64Encode } from "@opencode-ai/core/util/encode"
|
||||
import { mockOpenCodeServer } from "../utils/mock-server"
|
||||
import { expectAppVisible } from "../utils/waits"
|
||||
|
||||
const directory = "C:/OpenCode/PromptInputV2Editing"
|
||||
const projectID = "proj_prompt_input_v2_editing"
|
||||
const sessionID = "ses_prompt_input_v2_editing"
|
||||
|
||||
test("preserves the draft when a populated command menu triggers a built-in", async ({ page }) => {
|
||||
await mockOpenCodeServer(page, {
|
||||
directory,
|
||||
project: {
|
||||
id: projectID,
|
||||
worktree: directory,
|
||||
vcs: "git",
|
||||
name: "prompt-input-v2-editing",
|
||||
time: { created: 1700000000000, updated: 1700000000000 },
|
||||
sandboxes: [],
|
||||
},
|
||||
provider: { all: [], connected: [], default: {} },
|
||||
sessions: [
|
||||
{
|
||||
id: sessionID,
|
||||
slug: "prompt-input-v2-editing",
|
||||
projectID,
|
||||
directory,
|
||||
title: "Prompt input V2 editing",
|
||||
version: "dev",
|
||||
time: { created: 1700000000000, updated: 1700000000000 },
|
||||
},
|
||||
],
|
||||
pageMessages: () => ({ items: [] }),
|
||||
})
|
||||
await page.addInitScript(() => {
|
||||
localStorage.setItem("settings.v3", JSON.stringify({ general: { newLayoutDesigns: true } }))
|
||||
})
|
||||
|
||||
await page.goto(`/${base64Encode(directory)}/session/${sessionID}`)
|
||||
const composer = page.locator('[data-component="prompt-input-v2"]')
|
||||
const input = composer.locator('[data-component="prompt-input"]')
|
||||
await expectAppVisible(composer)
|
||||
|
||||
await input.fill("keep me")
|
||||
await composer.getByRole("button", { name: "Add images and files" }).click()
|
||||
await page.getByRole("menuitem", { name: "Commands" }).click()
|
||||
await page.locator('[data-suggestion-id="model.choose"]').click()
|
||||
|
||||
await expect(input).toHaveText("keep me")
|
||||
})
|
||||
@@ -54,15 +54,18 @@ test("shows the V2 thinking level control while relevant", async ({ page }) => {
|
||||
})
|
||||
|
||||
await page.goto(`/${base64Encode(directory)}/session/${sessionID}`)
|
||||
const composer = page.locator('[data-component="prompt-input-v2"]')
|
||||
const composer = page.locator('[data-component="session-composer"]')
|
||||
const input = composer.locator('[data-component="prompt-input"]')
|
||||
const control = composer.getByRole("button", { name: "Choose model variant" })
|
||||
const control = composer.locator('[data-component="prompt-variant-control"]')
|
||||
await expectAppVisible(composer)
|
||||
|
||||
await idleComposer(page)
|
||||
await expect(control).toBeHidden()
|
||||
|
||||
await composer.hover()
|
||||
await expect(control).toBeVisible()
|
||||
|
||||
await control.click()
|
||||
await control.locator('[data-action="prompt-model-variant"]').click()
|
||||
const high = page.getByRole("menuitemradio", { name: "high" })
|
||||
await expect(high).toBeVisible()
|
||||
await page.mouse.move(0, 0)
|
||||
|
||||
@@ -32,23 +32,6 @@ for (const expanded of [false, true]) {
|
||||
})
|
||||
}
|
||||
|
||||
test("shows and expands a running shell command without shimmering it", async ({ page }) => {
|
||||
const id = "prt_shell_running_command"
|
||||
const command = "sleep 10 && echo done"
|
||||
await setupTimeline(page, {
|
||||
messages: [userMessage(), assistantMessage([shell(id, "running", "still running", command)], { completed: false })],
|
||||
settings: { shellToolPartsExpanded: false },
|
||||
})
|
||||
|
||||
const tool = page.locator(`[data-timeline-part-id="${id}"]`)
|
||||
await expect(tool.locator('[data-component="text-shimmer"]')).toHaveAttribute("data-active", "true")
|
||||
await expect(tool.locator('[data-component="shell-submessage"]')).toHaveText(command)
|
||||
await expect(tool.locator('[data-component="shell-submessage"] [data-component="text-shimmer"]')).toHaveCount(0)
|
||||
await tool.locator('[data-slot="collapsible-trigger"]').click()
|
||||
await expect(tool.locator('[data-slot="collapsible-trigger"]')).toHaveAttribute("aria-expanded", "true")
|
||||
await expect(tool.locator('[data-slot="bash-pre"]')).toContainText("still running")
|
||||
})
|
||||
|
||||
test("transitions thinking and hidden reasoning through busy to idle", async ({ page }) => {
|
||||
const reasoningID = "prt_reasoning_hidden"
|
||||
const assistant = assistantMessage([reasoningPart(reasoningID, "## Inspecting stability")], { completed: false })
|
||||
|
||||
@@ -89,8 +89,8 @@ test("reconnects after a stream error", async ({ page }) => {
|
||||
expect((await timeline.transport.connections())[0]?.endedBy).toBe("error")
|
||||
})
|
||||
|
||||
test("does not request replay when reconnecting the volatile V2 event stream", async ({ page }) => {
|
||||
const timeline = await setupTimeline(page, { eventRetry: 10, protocol: "v2" })
|
||||
test("records event IDs and reconnect Last-Event-ID headers", async ({ page }) => {
|
||||
const timeline = await setupTimeline(page, { eventRetry: 10 })
|
||||
const first = await timeline.transport.send(partUpdated(textPart("prt_transport_id", "event with id")), {
|
||||
id: "timeline-event-7",
|
||||
})
|
||||
@@ -100,7 +100,7 @@ test("does not request replay when reconnecting the volatile V2 event stream", a
|
||||
const connection = await timeline.transport.waitForConnection({ after: first.connectionID })
|
||||
|
||||
expect(first.eventID).toBe("timeline-event-7")
|
||||
expect(connection.headers["last-event-id"]).toBeUndefined()
|
||||
expect(connection.headers["last-event-id"]).toBe("timeline-event-7")
|
||||
})
|
||||
|
||||
test("passes through non-event fetches", async ({ page }) => {
|
||||
|
||||
@@ -736,5 +736,5 @@ async function switchTitlebarSession(page: Page, sessionID: string, title: strin
|
||||
}
|
||||
|
||||
async function expectSessionReady(page: Page) {
|
||||
await expectAppVisible(page.getByRole("textbox", { name: "Prompt" }))
|
||||
await expectAppVisible(page.getByRole("textbox", { name: /Ask anything/i }))
|
||||
}
|
||||
|
||||
@@ -4,7 +4,6 @@ const emptyList = new Set(["/skill", "/command", "/lsp", "/formatter", "/vcs/sta
|
||||
const emptyObject = new Set(["/global/config", "/config", "/provider/auth", "/mcp", "/experimental/resource"])
|
||||
|
||||
export interface MockServerConfig {
|
||||
protocol?: "v1" | "v2"
|
||||
provider: unknown
|
||||
directory: string
|
||||
project: unknown
|
||||
@@ -54,20 +53,8 @@ export async function mockOpenCodeServer(page: Page, config: MockServerConfig) {
|
||||
if (url.port !== targetPort && url.port !== appPort) return route.fallback()
|
||||
|
||||
const path = url.pathname
|
||||
if (path === "/global/event" || path === "/event" || path === "/api/event") {
|
||||
const events = config.events?.()
|
||||
return sse(
|
||||
route,
|
||||
path === "/api/event"
|
||||
? [{ id: "evt_mock_connected", type: "server.connected", data: {} }, ...(events?.map(currentEvent) ?? [])]
|
||||
: events,
|
||||
config.eventRetry,
|
||||
)
|
||||
}
|
||||
if (path === "/global/health")
|
||||
return config.protocol === "v2" ? json(route, {}, undefined, 404) : json(route, { healthy: true })
|
||||
if (path === "/api/health" && config.protocol === "v2")
|
||||
return json(route, { healthy: true, version: "2.0.0", pid: 1 })
|
||||
if (path === "/global/event" || path === "/event") return sse(route, config.events?.(), config.eventRetry)
|
||||
if (path === "/global/health") return json(route, { healthy: true })
|
||||
if (path === "/experimental/capabilities") return json(route, { backgroundSubagents: true })
|
||||
if (path === "/permission")
|
||||
return json(route, typeof config.permissions === "function" ? config.permissions() : (config.permissions ?? []))
|
||||
@@ -96,129 +83,10 @@ export async function mockOpenCodeServer(page: Page, config: MockServerConfig) {
|
||||
},
|
||||
data: [],
|
||||
})
|
||||
if (path === "/api/agent")
|
||||
return json(route, {
|
||||
location: location(config),
|
||||
data: [
|
||||
{
|
||||
id: "build",
|
||||
name: "Build",
|
||||
mode: "primary",
|
||||
hidden: false,
|
||||
request: { settings: {}, headers: {}, body: {} },
|
||||
permissions: [],
|
||||
},
|
||||
],
|
||||
})
|
||||
if (path === "/api/command") return json(route, { location: location(config), data: [] })
|
||||
if (path === "/api/mcp") return json(route, { location: location(config), data: [] })
|
||||
if (path === "/api/mcp/resource")
|
||||
return json(route, { location: location(config), data: { resources: [], templates: [] } })
|
||||
const integration = path.match(/^\/api\/integration\/([^/]+)$/)?.[1]
|
||||
if (integration && route.request().method() === "GET")
|
||||
return json(route, {
|
||||
location: location(config),
|
||||
data: { id: integration, name: integration, methods: [{ type: "key", label: "API key" }], connections: [] },
|
||||
})
|
||||
if (/^\/api\/integration\/[^/]+\/connect\/key$/.test(path) && route.request().method() === "POST")
|
||||
return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
|
||||
if (path === "/api/project") return json(route, [config.project])
|
||||
if (path === "/api/project/current")
|
||||
return json(route, { id: (config.project as { id?: string }).id, directory: config.directory })
|
||||
if (path.startsWith("/api/project/") && route.request().method() === "PATCH") return json(route, config.project)
|
||||
if (path === "/api/path")
|
||||
return json(route, {
|
||||
state: config.directory,
|
||||
config: config.directory,
|
||||
worktree: config.directory,
|
||||
directory: config.directory,
|
||||
home: "C:/OpenCode",
|
||||
})
|
||||
if (path === "/api/permission/request")
|
||||
return json(route, {
|
||||
location: location(config),
|
||||
data: (typeof config.permissions === "function" ? config.permissions() : (config.permissions ?? [])).map(
|
||||
currentPermission,
|
||||
),
|
||||
})
|
||||
if (path === "/api/question/request")
|
||||
return json(route, {
|
||||
location: location(config),
|
||||
data: typeof config.questions === "function" ? config.questions() : (config.questions ?? []),
|
||||
})
|
||||
if (path === "/api/vcs")
|
||||
return json(route, { location: location(config), data: { branch: "main", defaultBranch: "main" } })
|
||||
if (path === "/api/vcs/status") return json(route, { location: location(config), data: [] })
|
||||
if (path === "/api/vcs/diff") return json(route, { location: location(config), data: config.vcsDiff ?? [] })
|
||||
if (path === "/api/pty/shells") return json(route, { location: location(config), data: [] })
|
||||
if (/^\/api\/pty\/[^/]+\/connect-token$/.test(path))
|
||||
return json(route, { location: location(config), data: { ticket: "e2e-ticket", expires_in: 60 } })
|
||||
if (emptyObject.has(path)) return json(route, {})
|
||||
if (emptyList.has(path)) return json(route, [])
|
||||
if (path === "/api/session") {
|
||||
const directory = url.searchParams.get("directory")
|
||||
const parentID = url.searchParams.get("parentID")
|
||||
const limit = Number(url.searchParams.get("limit") ?? 50)
|
||||
const offset = Number(url.searchParams.get("cursor") ?? 0)
|
||||
const sessions = config.sessions
|
||||
.filter((session) => !directory || session.directory === directory)
|
||||
.filter((session) => parentID !== "null" || session.parentID === undefined)
|
||||
.filter((session) => {
|
||||
const search = url.searchParams.get("search")?.toLowerCase()
|
||||
return (
|
||||
!search ||
|
||||
String(session.title ?? "")
|
||||
.toLowerCase()
|
||||
.includes(search)
|
||||
)
|
||||
})
|
||||
const ordered = url.searchParams.get("order") === "asc" ? sessions.toReversed() : sessions
|
||||
const data = ordered.slice(offset, offset + limit)
|
||||
const next = offset + limit < ordered.length ? String(offset + limit) : undefined
|
||||
return json(route, {
|
||||
data: data.map((session) => currentSession(session, config.directory)),
|
||||
cursor: { next },
|
||||
})
|
||||
}
|
||||
if (path === "/api/session/active") {
|
||||
const statuses = (config.sessionStatus ?? {}) as Record<string, { type?: string }>
|
||||
return json(route, {
|
||||
data: Object.fromEntries(
|
||||
Object.entries(statuses).flatMap(([id, status]) =>
|
||||
status.type === "idle" ? [] : [[id, { type: "running" }]],
|
||||
),
|
||||
),
|
||||
})
|
||||
}
|
||||
if (/^\/api\/session\/[^/]+\/shell$/.test(path) && route.request().method() === "POST") {
|
||||
return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
|
||||
}
|
||||
if (/^\/api\/session\/[^/]+\/question\/[^/]+\/(reply|reject)$/.test(path) && route.request().method() === "POST") {
|
||||
return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
|
||||
}
|
||||
if (/^\/api\/session\/[^/]+\/permission\/[^/]+\/reply$/.test(path) && route.request().method() === "POST") {
|
||||
return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
|
||||
}
|
||||
if (
|
||||
/^\/api\/session\/[^/]+\/(archive|rename|interrupt|revert\/clear|revert\/commit)$/.test(path) &&
|
||||
route.request().method() === "POST"
|
||||
) {
|
||||
return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
|
||||
}
|
||||
if (/^\/api\/session\/[^/]+$/.test(path) && route.request().method() === "DELETE") {
|
||||
return route.fulfill({ status: 204, headers: { "access-control-allow-origin": "*" } })
|
||||
}
|
||||
if (path in staticRoutes) return json(route, staticRoutes[path])
|
||||
|
||||
const currentSessionMatch = path.match(/^\/api\/session\/([^/]+)$/)
|
||||
if (currentSessionMatch) {
|
||||
const session = config.sessions.find((item) => item.id === currentSessionMatch[1])
|
||||
if (!session) return json(route, { error: "Session not found" }, undefined, 404)
|
||||
return json(route, {
|
||||
data: currentSession(session, config.directory),
|
||||
})
|
||||
}
|
||||
|
||||
const sessionMatch = path.match(/^\/session\/([^/]+)$/)
|
||||
if (sessionMatch) {
|
||||
const session = config.sessions.find((s) => s.id === sessionMatch[1])
|
||||
@@ -239,24 +107,6 @@ export async function mockOpenCodeServer(page: Page, config: MockServerConfig) {
|
||||
|
||||
if (/^\/session\/[^/]+\/(children|diff)$/.test(path)) return json(route, [])
|
||||
|
||||
const currentMessagesMatch = path.match(/^\/api\/session\/([^/]+)\/message$/)
|
||||
if (currentMessagesMatch) {
|
||||
const token = url.searchParams.get("cursor") ?? undefined
|
||||
const before = token ? cursors.get(token) : undefined
|
||||
if (token && !before) return json(route, { error: "Invalid cursor" }, undefined, 400)
|
||||
config.onMessages?.({ sessionID: currentMessagesMatch[1], before, phase: "start" })
|
||||
await config.beforeMessagesResponse?.({ sessionID: currentMessagesMatch[1]!, before })
|
||||
if (config.messageDelay !== undefined) await new Promise((resolve) => setTimeout(resolve, config.messageDelay))
|
||||
const pageData = config.pageMessages(currentMessagesMatch[1], Number(url.searchParams.get("limit") ?? 50), before)
|
||||
config.onMessages?.({ sessionID: currentMessagesMatch[1], before, phase: "end" })
|
||||
const cursor = pageData.cursor ? `cursor_${++nextCursor}` : undefined
|
||||
if (cursor) cursors.set(cursor, pageData.cursor!)
|
||||
return json(route, {
|
||||
data: pageData.items.map(currentMessage).reverse(),
|
||||
cursor: { next: cursor },
|
||||
})
|
||||
}
|
||||
|
||||
const messagesMatch = path.match(/^\/session\/([^/]+)\/message$/)
|
||||
if (messagesMatch) {
|
||||
const token = url.searchParams.get("before") ?? undefined
|
||||
@@ -279,115 +129,6 @@ export async function mockOpenCodeServer(page: Page, config: MockServerConfig) {
|
||||
})
|
||||
}
|
||||
|
||||
function location(config: MockServerConfig) {
|
||||
return {
|
||||
directory: config.directory,
|
||||
project: { id: (config.project as { id?: string }).id, directory: config.directory },
|
||||
}
|
||||
}
|
||||
|
||||
function currentPermission(value: unknown) {
|
||||
const permission = value as Record<string, unknown>
|
||||
if (permission.action) return permission
|
||||
const tool = permission.tool as { messageID?: string; callID?: string } | undefined
|
||||
return {
|
||||
id: permission.id,
|
||||
sessionID: permission.sessionID,
|
||||
action: permission.permission,
|
||||
resources: permission.patterns ?? [],
|
||||
save: permission.always,
|
||||
metadata: permission.metadata,
|
||||
source:
|
||||
tool?.messageID && tool.callID ? { type: "tool", messageID: tool.messageID, callID: tool.callID } : undefined,
|
||||
}
|
||||
}
|
||||
|
||||
export function currentSession(session: { id: string } & Record<string, unknown>, fallbackDirectory?: string) {
|
||||
const time = session.time && typeof session.time === "object" ? session.time : {}
|
||||
return {
|
||||
id: session.id,
|
||||
parentID: session.parentID,
|
||||
projectID: session.projectID ?? "project",
|
||||
agent: session.agent ?? "build",
|
||||
model: session.model ?? { id: "mock-model", providerID: "mock-provider" },
|
||||
cost: session.cost ?? 0,
|
||||
tokens: session.tokens ?? { input: 0, output: 0, reasoning: 0, cache: { read: 0, write: 0 } },
|
||||
time: {
|
||||
created: "created" in time && typeof time.created === "number" ? time.created : 0,
|
||||
updated: "updated" in time && typeof time.updated === "number" ? time.updated : 0,
|
||||
...(session.time && typeof session.time === "object" && "archived" in session.time
|
||||
? { archived: session.time.archived }
|
||||
: {}),
|
||||
},
|
||||
title: session.title ?? session.id,
|
||||
location: {
|
||||
directory: typeof session.directory === "string" ? session.directory : fallbackDirectory,
|
||||
...(typeof session.workspaceID === "string" ? { workspaceID: session.workspaceID } : {}),
|
||||
},
|
||||
subpath: session.path,
|
||||
revert: session.revert,
|
||||
}
|
||||
}
|
||||
|
||||
function currentMessage(value: unknown) {
|
||||
const item = value as {
|
||||
info: Record<string, unknown> & { id: string; role: "user" | "assistant"; time: { created: number } }
|
||||
parts: Array<Record<string, unknown> & { type: string }>
|
||||
}
|
||||
if (item.info.role === "user") {
|
||||
return {
|
||||
id: item.info.id,
|
||||
type: "user",
|
||||
time: item.info.time,
|
||||
text: item.parts
|
||||
.flatMap((part) => (part.type === "text" && typeof part.text === "string" ? [part.text] : []))
|
||||
.join("\n"),
|
||||
}
|
||||
}
|
||||
return {
|
||||
id: item.info.id,
|
||||
type: "assistant",
|
||||
time: item.info.time,
|
||||
agent: item.info.agent ?? "build",
|
||||
model: { id: item.info.modelID ?? "model", providerID: item.info.providerID ?? "provider" },
|
||||
cost: item.info.cost,
|
||||
tokens: item.info.tokens,
|
||||
error: item.info.error,
|
||||
content: item.parts.flatMap<unknown>((part) => {
|
||||
if (part.type === "text" || part.type === "reasoning") return [{ type: part.type, text: part.text ?? "" }]
|
||||
if (part.type !== "tool") return []
|
||||
const state = part.state as Record<string, unknown>
|
||||
return [
|
||||
{
|
||||
type: "tool",
|
||||
id: part.id,
|
||||
name: part.tool,
|
||||
time: state.time ?? { created: item.info.time.created },
|
||||
state:
|
||||
state.status === "pending"
|
||||
? { status: "streaming", input: state.raw ?? JSON.stringify(state.input ?? {}) }
|
||||
: state.status === "completed"
|
||||
? {
|
||||
status: "completed",
|
||||
input: state.input ?? {},
|
||||
structured: state.metadata ?? {},
|
||||
content: [{ type: "text", text: state.output ?? "" }],
|
||||
}
|
||||
: state.status === "error"
|
||||
? {
|
||||
status: "error",
|
||||
input: state.input ?? {},
|
||||
structured: state.metadata ?? {},
|
||||
content: [],
|
||||
error: { type: "ToolError", message: state.error ?? "Tool failed" },
|
||||
}
|
||||
: { status: "running", input: state.input ?? {}, structured: state.metadata ?? {}, content: [] },
|
||||
},
|
||||
]
|
||||
}),
|
||||
}
|
||||
}
|
||||
|
||||
function json(route: Route, body: unknown, headers?: Record<string, string>, status = 200) {
|
||||
return route.fulfill({
|
||||
status,
|
||||
@@ -408,18 +149,3 @@ function sse(route: Route, events?: unknown[], retry?: number) {
|
||||
body: `${retry === undefined ? "" : `retry: ${retry}\n\n`}${events?.map((event) => `data: ${JSON.stringify(event)}\n\n`).join("") || ": ok\n\n"}`,
|
||||
})
|
||||
}
|
||||
|
||||
function currentEvent(input: unknown) {
|
||||
if (!input || typeof input !== "object" || !("payload" in input)) return input
|
||||
const envelope = input as { directory?: string; payload?: unknown }
|
||||
if (!envelope.payload || typeof envelope.payload !== "object") return input
|
||||
const payload = envelope.payload as { id?: string; type?: string; properties?: unknown }
|
||||
if (!payload.type) return input
|
||||
return {
|
||||
id: payload.id ?? `evt_mock_${Date.now()}`,
|
||||
created: Date.now(),
|
||||
type: payload.type,
|
||||
data: payload.properties ?? {},
|
||||
location: envelope.directory && envelope.directory !== "global" ? { directory: envelope.directory } : undefined,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -3,7 +3,7 @@ import type { Page } from "@playwright/test"
|
||||
export type SseConnectionRecord = {
|
||||
id: number
|
||||
url: string
|
||||
path: "/global/event" | "/event" | "/api/event"
|
||||
path: "/global/event" | "/event"
|
||||
headers: Record<string, string>
|
||||
openedAt: number
|
||||
endedAt?: number
|
||||
@@ -93,21 +93,6 @@ export async function installSseTransport<T>(
|
||||
eventOptions.retry === undefined ? "" : `retry: ${eventOptions.retry}\n`,
|
||||
`data: ${JSON.stringify(payload)}\n\n`,
|
||||
].join("")
|
||||
const currentEvent = (input: unknown) => {
|
||||
if (!input || typeof input !== "object" || !("payload" in input)) return input
|
||||
const envelope = input as { directory?: string; payload?: unknown }
|
||||
if (!envelope.payload || typeof envelope.payload !== "object") return input
|
||||
const payload = envelope.payload as { id?: string; type?: string; properties?: unknown }
|
||||
if (!payload.type) return input
|
||||
return {
|
||||
id: payload.id ?? `evt_mock_${Date.now()}`,
|
||||
created: Date.now(),
|
||||
type: payload.type,
|
||||
data: payload.properties ?? {},
|
||||
location:
|
||||
envelope.directory && envelope.directory !== "global" ? { directory: envelope.directory } : undefined,
|
||||
}
|
||||
}
|
||||
const acknowledge = (
|
||||
connection: Connection,
|
||||
bytes: number,
|
||||
@@ -155,13 +140,15 @@ export async function installSseTransport<T>(
|
||||
output.forEach((chunk) => connection.controller.enqueue(chunk))
|
||||
return acknowledge(connection, input.bytes.length, output.length)
|
||||
}
|
||||
const encoded = input.deliveries.map((delivery) => {
|
||||
const payload = connection.path === "/api/event" ? currentEvent(delivery.payload) : delivery.payload
|
||||
return { delivery, payload, bytes: encoder.encode(frame(payload, delivery.options)) }
|
||||
})
|
||||
const encoded = input.deliveries.map((delivery) => ({
|
||||
delivery,
|
||||
bytes: encoder.encode(frame(delivery.payload, delivery.options)),
|
||||
}))
|
||||
encoded.forEach((item) => marker(item.delivery.options?.marker))
|
||||
if (input.burst) {
|
||||
const bytes = encoder.encode(encoded.map((item) => frame(item.payload, item.delivery.options)).join(""))
|
||||
const bytes = encoder.encode(
|
||||
encoded.map((item) => frame(item.delivery.payload, item.delivery.options)).join(""),
|
||||
)
|
||||
connection.controller.enqueue(bytes)
|
||||
return encoded.map((item) => acknowledge(connection, item.bytes.byteLength, 1, item.delivery.options?.id))
|
||||
}
|
||||
@@ -174,10 +161,7 @@ export async function installSseTransport<T>(
|
||||
const fetch = (input: RequestInfo | URL, init?: RequestInit) => {
|
||||
const request = new Request(input, init)
|
||||
const url = new URL(request.url)
|
||||
if (
|
||||
url.origin !== server ||
|
||||
(url.pathname !== "/global/event" && url.pathname !== "/event" && url.pathname !== "/api/event")
|
||||
)
|
||||
if (url.origin !== server || (url.pathname !== "/global/event" && url.pathname !== "/event"))
|
||||
return originalFetch(request)
|
||||
|
||||
const id = ++nextConnectionID
|
||||
@@ -193,10 +177,6 @@ export async function installSseTransport<T>(
|
||||
record.controller = controller
|
||||
connections.push(record)
|
||||
if (retry !== undefined) controller.enqueue(encoder.encode(`retry: ${retry}\n\n`))
|
||||
if (url.pathname === "/api/event")
|
||||
controller.enqueue(
|
||||
encoder.encode(frame({ id: `evt_mock_connected_${id}`, type: "server.connected", data: {} })),
|
||||
)
|
||||
request.signal.addEventListener(
|
||||
"abort",
|
||||
() => {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "@opencode-ai/app",
|
||||
"version": "1.18.4",
|
||||
"version": "1.17.20",
|
||||
"description": "",
|
||||
"type": "module",
|
||||
"exports": {
|
||||
@@ -53,7 +53,6 @@
|
||||
"@dnd-kit/helpers": "0.5.0",
|
||||
"@dnd-kit/solid": "0.5.0",
|
||||
"@kobalte/core": "catalog:",
|
||||
"@opencode-ai/client": "file:vendor/opencode-ai-client-1.17.13.tgz",
|
||||
"@opencode-ai/core": "workspace:*",
|
||||
"@opencode-ai/schema": "workspace:*",
|
||||
"@opencode-ai/sdk": "workspace:*",
|
||||
@@ -82,7 +81,7 @@
|
||||
"diff": "catalog:",
|
||||
"effect": "catalog:",
|
||||
"fuzzysort": "catalog:",
|
||||
"ghostty-web": "github:anomalyco/ghostty-web#83c0a07b8628b748aed073b232cb4b52a6ca11c1",
|
||||
"ghostty-web": "github:anomalyco/ghostty-web#513463a6f1190253057e8a3f0dac8f6ee8393553",
|
||||
"luxon": "catalog:",
|
||||
"marked": "catalog:",
|
||||
"marked-shiki": "catalog:",
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user