* feat(ai): resolve the Claude backend from the environment Tier 1 of #1406: a self-hosted deployment can now run every AI feature on a plain ANTHROPIC_API_KEY, with no AWS account. Hosted behaviour is unchanged. lib/ai/provider.ts resolves the backend once, from the environment: AI_PROVIDER explicit override, bedrock|anthropic AWS static key pair Bedrock ANTHROPIC_API_KEY the direct Anthropic API nothing set Bedrock, so the AWS credential provider chain (instance profile, IRSA) still resolves Bedrock deliberately wins when both credential sets are present. EU residency in eu-north-1 is a BFL/GDPR posture rather than a default, so adding an Anthropic key for an experiment must not silently move production inference out of the region. AI_PROVIDER is the way to say you meant it. Model ids are written bare in code and prefixed to eu.anthropic.* only for Bedrock, which needs the cross-region inference profile for on-demand throughput. An operator override that already carries a prefix passes through untouched, so BEDROCK_MODEL_ID and friends keep working as written. Converted call sites: the agent composer, invoice-inbox extraction, the document-extraction model label, and both receipt-hunt clients. The last two are not named in the issue, which predates receipt-hunt landing in main. @anthropic-ai/sdk is declared at 0.95.0, the version @anthropic-ai/bedrock-sdk 0.29.1 already pulled in transitively, so the lockfile dedupes to one copy with no new download. scripts/smoke-bedrock.ts becomes scripts/smoke-ai.ts and grows two steps. Unit tests can only prove which provider and model id get resolved; they cannot prove the resulting request is one the backend accepts. The script now sends real traffic over all three shapes the app uses: a plain create, a streamed turn carrying adaptive thinking, an effort level, an hour-long cache breakpoint and a tool, and document extraction end to end when given a file. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com> * docs(self-hosting): document the AI smoke test The script added alongside the provider split is what closes the #1406 acceptance criterion ("document extraction and the assistant both work"), so a self-hoster needs to know it exists. Covers both invocations and states that it exits non-zero, which is what makes it usable as a post-deploy check. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com> * test(ai): split the smoke test's thinking probe from its tool probe The combined probe could not falsify what it claimed to. It asked a question that needs a tool call, so the tool was used and adaptive thinking correctly declined to reason about it: the zero thinking-block count that came back was uninformative rather than a signal. 2a keeps the tool and drops thinking. 2b asks a question with several dependent steps (reverse charge, then a partial deduction, then the affected boxes) so that a model honouring the parameter must reason, and reports the thinking text length as well as the block count, since display:"summarized" can yield blocks with empty text. The cached system prompt is also padded past the 1024-token minimum cacheable prefix. Below that the API caches nothing and reports no error, so the old probe's cache counters read zero whether or not caching worked. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com> * fix(document-extraction): stop requiring AWS_REGION in the manifest The extension now needs one of two credential sets, AWS static keys or ANTHROPIC_API_KEY, and the manifest schema cannot express "one of". Since requiredEnvVars only drives a build-time warning and never gates anything, listing AWS_REGION told every self-hoster running the direct API to set a variable that has no effect for them. The description was also still promising Sonnet 4.6 via Bedrock specifically, which is no longer what the extension does. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com> * fix(ai): read documentKind defensively in the smoke test The field arrived with the receipt-aware extraction work, so referencing it directly stops the script compiling against any checkout from before that landed. tsconfig includes **/*.ts and next.config does not disable type checking, so on such a checkout this failed the production build rather than just the script: caught while preparing a test branch for a self-hosted instance that had not synced yet. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com> * fix(deps): restore the nested @swc/helpers entry in the lockfile Declaring @anthropic-ai/sdk with `npm install --package-lock-only` also pruned node_modules/next-intl/node_modules/@swc/helpers@0.5.23, an optional peer entry the local npm 11 considers redundant and the image's npm 10.9.8 does not. The result passed every local check and failed `npm ci` inside the Docker build, which is the only place the lockfile is actually enforced. The lockfile is now the previous one plus the single root dependency line, verified with `npm ci --dry-run`. @anthropic-ai/sdk needed nothing else: it was already in the tree as a transitive dependency of @anthropic-ai/bedrock-sdk. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com> * Update DECISIONS.md Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> * Update Docker documentation for AI provider credentials Clarify the role of credentials in AI provider selection and document extraction requirements. * Update SELF-HOSTING.md with smoke-ai script details Clarify usage of smoke-ai script for credential checks and document extraction. * Improve error handling and logging in smoke-ai script * fix(ai): complete plain-key self-hosting path Signed-off-by: Emil <emilmattsson14@gmail.com> --------- Signed-off-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com> Signed-off-by: Emil <emilmattsson14@gmail.com> Co-authored-by: Bjorn Bergenheim <29535152+bjornbergenheim@users.noreply.github.com> Co-authored-by: Claude Opus 5 <noreply@anthropic.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
184 lines
6.2 KiB
TypeScript
184 lines
6.2 KiB
TypeScript
import { describe, it, expect, beforeEach, afterEach } from 'vitest'
|
|
import Anthropic from '@anthropic-ai/sdk'
|
|
import AnthropicBedrock from '@anthropic-ai/bedrock-sdk'
|
|
import {
|
|
aiCredentialPrefix,
|
|
createAiClient,
|
|
hasAiCredentials,
|
|
resolveAiProvider,
|
|
toProviderModelId,
|
|
} from '../provider'
|
|
|
|
const AI_ENV_KEYS = [
|
|
'AI_PROVIDER',
|
|
'ANTHROPIC_API_KEY',
|
|
'AWS_ACCESS_KEY_ID',
|
|
'AWS_SECRET_ACCESS_KEY',
|
|
'AWS_REGION',
|
|
] as const
|
|
|
|
let saved: Partial<Record<(typeof AI_ENV_KEYS)[number], string | undefined>> = {}
|
|
|
|
beforeEach(() => {
|
|
saved = {}
|
|
for (const key of AI_ENV_KEYS) {
|
|
saved[key] = process.env[key]
|
|
delete process.env[key]
|
|
}
|
|
})
|
|
|
|
afterEach(() => {
|
|
for (const key of AI_ENV_KEYS) {
|
|
if (saved[key] === undefined) delete process.env[key]
|
|
else process.env[key] = saved[key]
|
|
}
|
|
})
|
|
|
|
describe('resolveAiProvider', () => {
|
|
it('uses Bedrock when static AWS keys are set (hosted stays unchanged)', () => {
|
|
process.env.AWS_ACCESS_KEY_ID = 'AKIAEXAMPLE'
|
|
process.env.AWS_SECRET_ACCESS_KEY = 'secret'
|
|
expect(resolveAiProvider()).toBe('bedrock')
|
|
})
|
|
|
|
it('uses the direct API when only an Anthropic key is set (self-hosted)', () => {
|
|
process.env.ANTHROPIC_API_KEY = 'sk-ant-api03-example'
|
|
expect(resolveAiProvider()).toBe('anthropic')
|
|
})
|
|
|
|
// The load-bearing precedence case: an operator who adds an Anthropic key
|
|
// for a side experiment must not silently move production inference out of
|
|
// eu-north-1, which is a deliberate BFL/GDPR posture rather than a default.
|
|
it('prefers Bedrock when both credential sets are present', () => {
|
|
process.env.AWS_ACCESS_KEY_ID = 'AKIAEXAMPLE'
|
|
process.env.AWS_SECRET_ACCESS_KEY = 'secret'
|
|
process.env.ANTHROPIC_API_KEY = 'sk-ant-api03-example'
|
|
expect(resolveAiProvider()).toBe('bedrock')
|
|
})
|
|
|
|
it('lets AI_PROVIDER override the credential-based guess, both ways', () => {
|
|
process.env.AWS_ACCESS_KEY_ID = 'AKIAEXAMPLE'
|
|
process.env.AWS_SECRET_ACCESS_KEY = 'secret'
|
|
process.env.ANTHROPIC_API_KEY = 'sk-ant-api03-example'
|
|
|
|
process.env.AI_PROVIDER = 'anthropic'
|
|
expect(resolveAiProvider()).toBe('anthropic')
|
|
|
|
process.env.AI_PROVIDER = 'bedrock'
|
|
expect(resolveAiProvider()).toBe('bedrock')
|
|
})
|
|
|
|
it('accepts AI_PROVIDER case-insensitively and trimmed', () => {
|
|
process.env.ANTHROPIC_API_KEY = 'sk-ant-api03-example'
|
|
process.env.AI_PROVIDER = ' Bedrock '
|
|
expect(resolveAiProvider()).toBe('bedrock')
|
|
})
|
|
|
|
it('ignores an unrecognised AI_PROVIDER rather than failing closed', () => {
|
|
process.env.AI_PROVIDER = 'openai'
|
|
process.env.ANTHROPIC_API_KEY = 'sk-ant-api03-example'
|
|
expect(resolveAiProvider()).toBe('anthropic')
|
|
})
|
|
|
|
// Hosted infrastructure that injects credentials via instance profile / IRSA
|
|
// sets no env vars at all: that must still resolve to Bedrock so the AWS
|
|
// credential provider chain gets its chance.
|
|
it('falls back to Bedrock when nothing is configured', () => {
|
|
expect(resolveAiProvider()).toBe('bedrock')
|
|
})
|
|
})
|
|
|
|
describe('hasAiCredentials', () => {
|
|
it('is true for a complete AWS static key pair', () => {
|
|
process.env.AWS_ACCESS_KEY_ID = 'AKIAEXAMPLE'
|
|
process.env.AWS_SECRET_ACCESS_KEY = 'secret'
|
|
expect(hasAiCredentials()).toBe(true)
|
|
})
|
|
|
|
it('is false for a half-configured AWS key pair', () => {
|
|
process.env.AWS_ACCESS_KEY_ID = 'AKIAEXAMPLE'
|
|
expect(hasAiCredentials()).toBe(false)
|
|
})
|
|
|
|
it('is true for an Anthropic key', () => {
|
|
process.env.ANTHROPIC_API_KEY = 'sk-ant-api03-example'
|
|
expect(hasAiCredentials()).toBe(true)
|
|
})
|
|
|
|
it('is false when nothing is configured', () => {
|
|
expect(hasAiCredentials()).toBe(false)
|
|
})
|
|
|
|
// AI_PROVIDER names the backend but does not conjure a credential for it.
|
|
it('is false when AI_PROVIDER names a backend with no key', () => {
|
|
process.env.AI_PROVIDER = 'anthropic'
|
|
process.env.AWS_ACCESS_KEY_ID = 'AKIAEXAMPLE'
|
|
process.env.AWS_SECRET_ACCESS_KEY = 'secret'
|
|
expect(hasAiCredentials()).toBe(false)
|
|
})
|
|
})
|
|
|
|
describe('createAiClient', () => {
|
|
it('builds a Bedrock client when AWS keys are set', () => {
|
|
process.env.AWS_ACCESS_KEY_ID = 'AKIAEXAMPLE'
|
|
process.env.AWS_SECRET_ACCESS_KEY = 'secret'
|
|
expect(createAiClient()).toBeInstanceOf(AnthropicBedrock)
|
|
})
|
|
|
|
it('builds a direct Anthropic client when only an Anthropic key is set', () => {
|
|
process.env.ANTHROPIC_API_KEY = 'sk-ant-api03-example'
|
|
expect(createAiClient()).toBeInstanceOf(Anthropic)
|
|
})
|
|
|
|
it('builds a Bedrock client for the AWS provider chain when nothing is set', () => {
|
|
expect(createAiClient()).toBeInstanceOf(AnthropicBedrock)
|
|
})
|
|
})
|
|
|
|
describe('toProviderModelId', () => {
|
|
it('passes the bare id through for the direct API', () => {
|
|
expect(toProviderModelId('claude-sonnet-5', 'anthropic')).toBe('claude-sonnet-5')
|
|
})
|
|
|
|
it('adds the eu inference-profile prefix for Bedrock', () => {
|
|
expect(toProviderModelId('claude-sonnet-5', 'bedrock')).toBe('eu.anthropic.claude-sonnet-5')
|
|
})
|
|
|
|
// An operator override may already be written in provider form; prefixing it
|
|
// again would produce eu.anthropic.eu.anthropic.… and 404 at call time.
|
|
it('leaves an already-prefixed id alone', () => {
|
|
expect(toProviderModelId('eu.anthropic.claude-sonnet-5', 'bedrock')).toBe(
|
|
'eu.anthropic.claude-sonnet-5'
|
|
)
|
|
expect(toProviderModelId('anthropic.claude-sonnet-5', 'bedrock')).toBe(
|
|
'anthropic.claude-sonnet-5'
|
|
)
|
|
})
|
|
|
|
it('defaults to the environment-resolved provider', () => {
|
|
process.env.ANTHROPIC_API_KEY = 'sk-ant-api03-example'
|
|
expect(toProviderModelId('claude-sonnet-5')).toBe('claude-sonnet-5')
|
|
})
|
|
})
|
|
|
|
describe('aiCredentialPrefix', () => {
|
|
it('returns only the non-secret Anthropic key prefix', () => {
|
|
process.env.ANTHROPIC_API_KEY = 'sk-ant-api03-SECRETSECRETSECRET'
|
|
const prefix = aiCredentialPrefix()
|
|
expect(prefix).toBe('sk-ant-api03')
|
|
expect(prefix).not.toContain('SECRET')
|
|
})
|
|
|
|
it('returns only the AWS access-key-id class prefix', () => {
|
|
process.env.AWS_ACCESS_KEY_ID = 'AKIASECRETSECRET'
|
|
process.env.AWS_SECRET_ACCESS_KEY = 'secret'
|
|
const prefix = aiCredentialPrefix()
|
|
expect(prefix).toBe('AKIA')
|
|
expect(prefix).not.toContain('SECRET')
|
|
})
|
|
|
|
it('returns null when nothing is configured', () => {
|
|
expect(aiCredentialPrefix()).toBeNull()
|
|
})
|
|
})
|