@databricks/appkit 0.70.0 → 0.72.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CLAUDE.md +46 -0
- package/NOTICE.md +2 -2
- package/dist/appkit/package.js +1 -1
- package/dist/beta.d.ts +13 -1
- package/dist/beta.js +13 -1
- package/dist/cli/commands/agent/eval.js +112 -0
- package/dist/cli/commands/agent/eval.js.map +1 -0
- package/dist/cli/commands/agent/index.js +18 -0
- package/dist/cli/commands/agent/index.js.map +1 -0
- package/dist/cli/index.js +2 -0
- package/dist/cli/index.js.map +1 -1
- package/dist/connectors/index.js +2 -0
- package/dist/connectors/mlflow/auth.d.ts +18 -0
- package/dist/connectors/mlflow/auth.d.ts.map +1 -0
- package/dist/connectors/mlflow/auth.js +50 -0
- package/dist/connectors/mlflow/auth.js.map +1 -0
- package/dist/connectors/mlflow/client.d.ts +51 -0
- package/dist/connectors/mlflow/client.d.ts.map +1 -0
- package/dist/connectors/mlflow/client.js +93 -0
- package/dist/connectors/mlflow/client.js.map +1 -0
- package/dist/core/appkit.d.ts.map +1 -1
- package/dist/core/appkit.js +1 -0
- package/dist/core/appkit.js.map +1 -1
- package/dist/evals/define-eval.d.ts +26 -0
- package/dist/evals/define-eval.d.ts.map +1 -0
- package/dist/evals/define-eval.js +28 -0
- package/dist/evals/define-eval.js.map +1 -0
- package/dist/evals/discover.d.ts +20 -0
- package/dist/evals/discover.d.ts.map +1 -0
- package/dist/evals/discover.js +49 -0
- package/dist/evals/discover.js.map +1 -0
- package/dist/evals/http-driver.d.ts +33 -0
- package/dist/evals/http-driver.d.ts.map +1 -0
- package/dist/evals/http-driver.js +118 -0
- package/dist/evals/http-driver.js.map +1 -0
- package/dist/evals/index.js +13 -0
- package/dist/evals/judge.d.ts +26 -0
- package/dist/evals/judge.d.ts.map +1 -0
- package/dist/evals/judge.js +77 -0
- package/dist/evals/judge.js.map +1 -0
- package/dist/evals/matchers.d.ts +12 -0
- package/dist/evals/matchers.d.ts.map +1 -0
- package/dist/evals/matchers.js +26 -0
- package/dist/evals/matchers.js.map +1 -0
- package/dist/evals/mlflow-report.d.ts +36 -0
- package/dist/evals/mlflow-report.d.ts.map +1 -0
- package/dist/evals/mlflow-report.js +161 -0
- package/dist/evals/mlflow-report.js.map +1 -0
- package/dist/evals/mlflow-run.d.ts +11 -0
- package/dist/evals/mlflow-run.d.ts.map +1 -0
- package/dist/evals/mlflow-run.js +101 -0
- package/dist/evals/mlflow-run.js.map +1 -0
- package/dist/evals/pool.js +24 -0
- package/dist/evals/pool.js.map +1 -0
- package/dist/evals/report.d.ts +25 -0
- package/dist/evals/report.d.ts.map +1 -0
- package/dist/evals/report.js +57 -0
- package/dist/evals/report.js.map +1 -0
- package/dist/evals/run-eval.d.ts +20 -0
- package/dist/evals/run-eval.d.ts.map +1 -0
- package/dist/evals/run-eval.js +144 -0
- package/dist/evals/run-eval.js.map +1 -0
- package/dist/evals/run-evals.d.ts +85 -0
- package/dist/evals/run-evals.d.ts.map +1 -0
- package/dist/evals/run-evals.js +178 -0
- package/dist/evals/run-evals.js.map +1 -0
- package/dist/evals/types.d.ts +127 -0
- package/dist/evals/types.d.ts.map +1 -0
- package/dist/plugins/agents/agents.d.ts.map +1 -1
- package/dist/plugins/agents/agents.js +5 -2
- package/dist/plugins/agents/agents.js.map +1 -1
- package/dist/plugins/agents/mlflow.js +267 -11
- package/dist/plugins/agents/mlflow.js.map +1 -1
- package/dist/plugins/server/index.js +2 -2
- package/dist/plugins/server/index.js.map +1 -1
- package/dist/plugins/server/remote-tunnel/remote-tunnel-manager.js +3 -3
- package/dist/plugins/server/remote-tunnel/remote-tunnel-manager.js.map +1 -1
- package/dist/plugins/server/static-server.js +3 -3
- package/dist/plugins/server/static-server.js.map +1 -1
- package/dist/plugins/server/utils.js +3 -3
- package/dist/plugins/server/utils.js.map +1 -1
- package/dist/plugins/server/vite-dev-server.js +4 -4
- package/dist/plugins/server/vite-dev-server.js.map +1 -1
- package/dist/shared/src/schemas/manifest.d.ts +33 -33
- package/dist/telemetry/index.js +2 -2
- package/dist/telemetry/telemetry-manager.d.ts +2 -1
- package/dist/telemetry/telemetry-manager.js +114 -26
- package/dist/telemetry/telemetry-manager.js.map +1 -1
- package/dist/type-generator/database/generate.js +3 -3
- package/dist/type-generator/database/generate.js.map +1 -1
- package/dist/type-generator/errors.js +45 -11
- package/dist/type-generator/errors.js.map +1 -1
- package/dist/type-generator/migration.js +2 -2
- package/dist/type-generator/migration.js.map +1 -1
- package/dist/type-generator/mv-registry/sync.js +3 -3
- package/dist/type-generator/mv-registry/sync.js.map +1 -1
- package/dist/type-generator/mv-registry/types.d.ts +5 -2
- package/dist/type-generator/mv-registry/types.d.ts.map +1 -1
- package/dist/type-generator/query-registry.js +3 -3
- package/dist/type-generator/query-registry.js.map +1 -1
- package/dist/type-generator/serving/server-file-extractor.js +3 -3
- package/dist/type-generator/serving/server-file-extractor.js.map +1 -1
- package/docs/api/appkit/Class.MlflowClient.md +103 -0
- package/docs/api/appkit/Function.buildAssessments.md +16 -0
- package/docs/api/appkit/Function.configureJudge.md +18 -0
- package/docs/api/appkit/Function.createHttpDriver.md +18 -0
- package/docs/api/appkit/Function.defineEval.md +35 -0
- package/docs/api/appkit/Function.discoverEvalFiles.md +18 -0
- package/docs/api/appkit/Function.equals.md +18 -0
- package/docs/api/appkit/Function.evalGlyph.md +18 -0
- package/docs/api/appkit/Function.formatEvalDetail.md +18 -0
- package/docs/api/appkit/Function.formatEvalHeadline.md +18 -0
- package/docs/api/appkit/Function.formatEvalResults.md +18 -0
- package/docs/api/appkit/Function.formatSummaryLine.md +18 -0
- package/docs/api/appkit/Function.includes.md +18 -0
- package/docs/api/appkit/Function.isJudgeConfigured.md +10 -0
- package/docs/api/appkit/Function.matches.md +18 -0
- package/docs/api/appkit/Function.normalizeHost.md +18 -0
- package/docs/api/appkit/Function.reportToMlflow.md +23 -0
- package/docs/api/appkit/Function.resolveDatabricksAuth.md +16 -0
- package/docs/api/appkit/Function.runEval.md +19 -0
- package/docs/api/appkit/Function.runEvalsInDir.md +18 -0
- package/docs/api/appkit/Function.summarize.md +16 -0
- package/docs/api/appkit/Interface.AssertionHandle.md +54 -0
- package/docs/api/appkit/Interface.AssertionResult.md +48 -0
- package/docs/api/appkit/Interface.Assessment.md +83 -0
- package/docs/api/appkit/Interface.CustomJudgeSpec.md +30 -0
- package/docs/api/appkit/Interface.DatabricksAuth.md +21 -0
- package/docs/api/appkit/Interface.DiscoveredEval.md +36 -0
- package/docs/api/appkit/Interface.DriveResult.md +58 -0
- package/docs/api/appkit/Interface.EvalDefinition.md +46 -0
- package/docs/api/appkit/Interface.EvalDriver.md +22 -0
- package/docs/api/appkit/Interface.EvalResult.md +83 -0
- package/docs/api/appkit/Interface.EvalRunSummary.md +46 -0
- package/docs/api/appkit/Interface.EvalSummary.md +48 -0
- package/docs/api/appkit/Interface.HttpDriverOptions.md +67 -0
- package/docs/api/appkit/Interface.JudgeConfig.md +34 -0
- package/docs/api/appkit/Interface.JudgeScore.md +21 -0
- package/docs/api/appkit/Interface.MatchResult.md +34 -0
- package/docs/api/appkit/Interface.PostResult.md +30 -0
- package/docs/api/appkit/Interface.ReportOutcome.md +53 -0
- package/docs/api/appkit/Interface.ResolveDatabricksAuthOptions.md +34 -0
- package/docs/api/appkit/Interface.RunEvalOptions.md +34 -0
- package/docs/api/appkit/Interface.RunEvalsOptions.md +192 -0
- package/docs/api/appkit/Interface.TestContext.md +208 -0
- package/docs/api/appkit/TypeAlias.EvalProgress.md +26 -0
- package/docs/api/appkit/TypeAlias.Matcher.md +18 -0
- package/docs/api/appkit/TypeAlias.Severity.md +8 -0
- package/docs/api/appkit.md +63 -17
- package/llms.txt +46 -0
- package/package.json +5 -4
- package/sbom.cdx.json +1 -1
|
@@ -0,0 +1,208 @@
|
|
|
1
|
+
# Interface: TestContext
|
|
2
|
+
|
|
3
|
+
The `t` context passed to an eval's `test` function.
|
|
4
|
+
|
|
5
|
+
## Properties[](#properties "Direct link to Properties")
|
|
6
|
+
|
|
7
|
+
### judge[](#judge "Direct link to judge")
|
|
8
|
+
|
|
9
|
+
```ts
|
|
10
|
+
judge: {
|
|
11
|
+
closedQA: Promise<AssertionHandle>;
|
|
12
|
+
custom: Promise<AssertionHandle>;
|
|
13
|
+
factuality: Promise<AssertionHandle>;
|
|
14
|
+
};
|
|
15
|
+
|
|
16
|
+
```
|
|
17
|
+
|
|
18
|
+
LLM-as-judge scoring of the last reply (via autoevals → a Databricks judge model). Each returns a scored, soft-by-default assertion; chain `.atLeast(n)` to set the pass threshold or `.gate()` to make it a hard gate. Requires the judge to be configured (`--judge-model`).
|
|
19
|
+
|
|
20
|
+
#### closedQA()[](#closedqa "Direct link to closedQA()")
|
|
21
|
+
|
|
22
|
+
```ts
|
|
23
|
+
closedQA(criteria: string): Promise<AssertionHandle>;
|
|
24
|
+
|
|
25
|
+
```
|
|
26
|
+
|
|
27
|
+
Score whether the reply answers the question, per optional `criteria`.
|
|
28
|
+
|
|
29
|
+
##### Parameters[](#parameters "Direct link to Parameters")
|
|
30
|
+
|
|
31
|
+
| Parameter | Type |
|
|
32
|
+
| ---------- | -------- |
|
|
33
|
+
| `criteria` | `string` |
|
|
34
|
+
|
|
35
|
+
##### Returns[](#returns "Direct link to Returns")
|
|
36
|
+
|
|
37
|
+
`Promise`<[`AssertionHandle`](./docs/api/appkit/Interface.AssertionHandle.md)>
|
|
38
|
+
|
|
39
|
+
#### custom()[](#custom "Direct link to custom()")
|
|
40
|
+
|
|
41
|
+
```ts
|
|
42
|
+
custom(spec: CustomJudgeSpec): Promise<AssertionHandle>;
|
|
43
|
+
|
|
44
|
+
```
|
|
45
|
+
|
|
46
|
+
A custom prompt-template judge (the TS analog of MLflow's `@scorer`).
|
|
47
|
+
|
|
48
|
+
##### Parameters[](#parameters-1 "Direct link to Parameters")
|
|
49
|
+
|
|
50
|
+
| Parameter | Type |
|
|
51
|
+
| --------- | ------------------------------------------------------------------------- |
|
|
52
|
+
| `spec` | [`CustomJudgeSpec`](./docs/api/appkit/Interface.CustomJudgeSpec.md) |
|
|
53
|
+
|
|
54
|
+
##### Returns[](#returns-1 "Direct link to Returns")
|
|
55
|
+
|
|
56
|
+
`Promise`<[`AssertionHandle`](./docs/api/appkit/Interface.AssertionHandle.md)>
|
|
57
|
+
|
|
58
|
+
#### factuality()[](#factuality "Direct link to factuality()")
|
|
59
|
+
|
|
60
|
+
```ts
|
|
61
|
+
factuality(expected: string): Promise<AssertionHandle>;
|
|
62
|
+
|
|
63
|
+
```
|
|
64
|
+
|
|
65
|
+
Score factuality of the reply against an expected reference.
|
|
66
|
+
|
|
67
|
+
##### Parameters[](#parameters-2 "Direct link to Parameters")
|
|
68
|
+
|
|
69
|
+
| Parameter | Type |
|
|
70
|
+
| ---------- | -------- |
|
|
71
|
+
| `expected` | `string` |
|
|
72
|
+
|
|
73
|
+
##### Returns[](#returns-2 "Direct link to Returns")
|
|
74
|
+
|
|
75
|
+
`Promise`<[`AssertionHandle`](./docs/api/appkit/Interface.AssertionHandle.md)>
|
|
76
|
+
|
|
77
|
+
***
|
|
78
|
+
|
|
79
|
+
### reply[](#reply "Direct link to reply")
|
|
80
|
+
|
|
81
|
+
```ts
|
|
82
|
+
readonly reply: string;
|
|
83
|
+
|
|
84
|
+
```
|
|
85
|
+
|
|
86
|
+
The last assistant reply.
|
|
87
|
+
|
|
88
|
+
***
|
|
89
|
+
|
|
90
|
+
### sessionId[](#sessionid "Direct link to sessionId")
|
|
91
|
+
|
|
92
|
+
```ts
|
|
93
|
+
readonly sessionId: string | undefined;
|
|
94
|
+
|
|
95
|
+
```
|
|
96
|
+
|
|
97
|
+
The current session/thread id, if any.
|
|
98
|
+
|
|
99
|
+
***
|
|
100
|
+
|
|
101
|
+
### toolCalls[](#toolcalls "Direct link to toolCalls")
|
|
102
|
+
|
|
103
|
+
```ts
|
|
104
|
+
readonly toolCalls: string[];
|
|
105
|
+
|
|
106
|
+
```
|
|
107
|
+
|
|
108
|
+
Tools called during the last turn.
|
|
109
|
+
|
|
110
|
+
## Methods[](#methods "Direct link to Methods")
|
|
111
|
+
|
|
112
|
+
### calledTool()[](#calledtool "Direct link to calledTool()")
|
|
113
|
+
|
|
114
|
+
```ts
|
|
115
|
+
calledTool(name: string): AssertionHandle;
|
|
116
|
+
|
|
117
|
+
```
|
|
118
|
+
|
|
119
|
+
Assert a tool was called during the run (gate by default).
|
|
120
|
+
|
|
121
|
+
#### Parameters[](#parameters-3 "Direct link to Parameters")
|
|
122
|
+
|
|
123
|
+
| Parameter | Type |
|
|
124
|
+
| --------- | -------- |
|
|
125
|
+
| `name` | `string` |
|
|
126
|
+
|
|
127
|
+
#### Returns[](#returns-3 "Direct link to Returns")
|
|
128
|
+
|
|
129
|
+
[`AssertionHandle`](./docs/api/appkit/Interface.AssertionHandle.md)
|
|
130
|
+
|
|
131
|
+
***
|
|
132
|
+
|
|
133
|
+
### check()[](#check "Direct link to check()")
|
|
134
|
+
|
|
135
|
+
```ts
|
|
136
|
+
check(value: string, matcher: Matcher): AssertionHandle;
|
|
137
|
+
|
|
138
|
+
```
|
|
139
|
+
|
|
140
|
+
Assert a value against a matcher, e.g. `t.check(t.reply, includes("Sunny"))`.
|
|
141
|
+
|
|
142
|
+
#### Parameters[](#parameters-4 "Direct link to Parameters")
|
|
143
|
+
|
|
144
|
+
| Parameter | Type |
|
|
145
|
+
| --------- | --------------------------------------------------------- |
|
|
146
|
+
| `value` | `string` |
|
|
147
|
+
| `matcher` | [`Matcher`](./docs/api/appkit/TypeAlias.Matcher.md) |
|
|
148
|
+
|
|
149
|
+
#### Returns[](#returns-4 "Direct link to Returns")
|
|
150
|
+
|
|
151
|
+
[`AssertionHandle`](./docs/api/appkit/Interface.AssertionHandle.md)
|
|
152
|
+
|
|
153
|
+
***
|
|
154
|
+
|
|
155
|
+
### send()[](#send "Direct link to send()")
|
|
156
|
+
|
|
157
|
+
```ts
|
|
158
|
+
send(message: string): Promise<void>;
|
|
159
|
+
|
|
160
|
+
```
|
|
161
|
+
|
|
162
|
+
Send a user message to the agent and capture its response.
|
|
163
|
+
|
|
164
|
+
#### Parameters[](#parameters-5 "Direct link to Parameters")
|
|
165
|
+
|
|
166
|
+
| Parameter | Type |
|
|
167
|
+
| --------- | -------- |
|
|
168
|
+
| `message` | `string` |
|
|
169
|
+
|
|
170
|
+
#### Returns[](#returns-5 "Direct link to Returns")
|
|
171
|
+
|
|
172
|
+
`Promise`<`void`>
|
|
173
|
+
|
|
174
|
+
***
|
|
175
|
+
|
|
176
|
+
### skip()[](#skip "Direct link to skip()")
|
|
177
|
+
|
|
178
|
+
```ts
|
|
179
|
+
skip(reason?: string): never;
|
|
180
|
+
|
|
181
|
+
```
|
|
182
|
+
|
|
183
|
+
Skip this eval with an optional reason.
|
|
184
|
+
|
|
185
|
+
#### Parameters[](#parameters-6 "Direct link to Parameters")
|
|
186
|
+
|
|
187
|
+
| Parameter | Type |
|
|
188
|
+
| --------- | -------- |
|
|
189
|
+
| `reason?` | `string` |
|
|
190
|
+
|
|
191
|
+
#### Returns[](#returns-6 "Direct link to Returns")
|
|
192
|
+
|
|
193
|
+
`never`
|
|
194
|
+
|
|
195
|
+
***
|
|
196
|
+
|
|
197
|
+
### succeeded()[](#succeeded "Direct link to succeeded()")
|
|
198
|
+
|
|
199
|
+
```ts
|
|
200
|
+
succeeded(): AssertionHandle;
|
|
201
|
+
|
|
202
|
+
```
|
|
203
|
+
|
|
204
|
+
Assert the last turn completed successfully (gate by default).
|
|
205
|
+
|
|
206
|
+
#### Returns[](#returns-7 "Direct link to Returns")
|
|
207
|
+
|
|
208
|
+
[`AssertionHandle`](./docs/api/appkit/Interface.AssertionHandle.md)
|
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
# Type Alias: EvalProgress
|
|
2
|
+
|
|
3
|
+
```ts
|
|
4
|
+
type EvalProgress =
|
|
5
|
+
| {
|
|
6
|
+
total: number;
|
|
7
|
+
type: "discovered";
|
|
8
|
+
}
|
|
9
|
+
| {
|
|
10
|
+
runId: string;
|
|
11
|
+
type: "run-created";
|
|
12
|
+
}
|
|
13
|
+
| {
|
|
14
|
+
id: string;
|
|
15
|
+
index: number;
|
|
16
|
+
total: number;
|
|
17
|
+
type: "start";
|
|
18
|
+
}
|
|
19
|
+
| {
|
|
20
|
+
index: number;
|
|
21
|
+
result: EvalResult;
|
|
22
|
+
total: number;
|
|
23
|
+
type: "result";
|
|
24
|
+
};
|
|
25
|
+
|
|
26
|
+
```
|
|
@@ -0,0 +1,18 @@
|
|
|
1
|
+
# Type Alias: Matcher()
|
|
2
|
+
|
|
3
|
+
```ts
|
|
4
|
+
type Matcher = (value: string) => MatchResult;
|
|
5
|
+
|
|
6
|
+
```
|
|
7
|
+
|
|
8
|
+
A deterministic matcher: inspects a string value and returns a result.
|
|
9
|
+
|
|
10
|
+
## Parameters[](#parameters "Direct link to Parameters")
|
|
11
|
+
|
|
12
|
+
| Parameter | Type |
|
|
13
|
+
| --------- | -------- |
|
|
14
|
+
| `value` | `string` |
|
|
15
|
+
|
|
16
|
+
## Returns[](#returns "Direct link to Returns")
|
|
17
|
+
|
|
18
|
+
[`MatchResult`](./docs/api/appkit/Interface.MatchResult.md)
|
package/docs/api/appkit.md
CHANGED
|
@@ -11,23 +11,24 @@ Documentation merge entry for Typedoc — combines the stable `@databricks/appki
|
|
|
11
11
|
|
|
12
12
|
## Classes[](#classes "Direct link to Classes")
|
|
13
13
|
|
|
14
|
-
| Class | Description
|
|
15
|
-
| ----------------------------------------------------------------------------- |
|
|
16
|
-
| [AppKitError](./docs/api/appkit/Class.AppKitError.md) | Base error class for all AppKit errors. Provides a consistent structure for error handling across the framework.
|
|
17
|
-
| [AppKitMcpClient](./docs/api/appkit/Class.AppKitMcpClient.md) | Lightweight MCP client for Databricks-hosted MCP servers.
|
|
18
|
-
| [AuthenticationError](./docs/api/appkit/Class.AuthenticationError.md) | Error thrown when authentication fails. Use for missing tokens, invalid credentials, or authorization failures.
|
|
19
|
-
| [ConfigurationError](./docs/api/appkit/Class.ConfigurationError.md) | Error thrown when configuration is missing or invalid. Use for missing environment variables, invalid settings, or setup issues.
|
|
20
|
-
| [ConnectionError](./docs/api/appkit/Class.ConnectionError.md) | Error thrown when a connection or network operation fails. Use for database pool errors, API failures, timeouts, etc.
|
|
21
|
-
| [DatabricksAdapter](./docs/api/appkit/Class.DatabricksAdapter.md) | Adapter that talks directly to Databricks Model Serving `/invocations` endpoint.
|
|
22
|
-
| [ExecutionError](./docs/api/appkit/Class.ExecutionError.md) | Error thrown when an operation execution fails. Use for statement failures, canceled operations, or unexpected states.
|
|
23
|
-
| [InitializationError](./docs/api/appkit/Class.InitializationError.md) | Error thrown when a service or component is not properly initialized. Use when accessing services before they are ready.
|
|
24
|
-
| [
|
|
25
|
-
| [
|
|
26
|
-
| [
|
|
27
|
-
| [
|
|
28
|
-
| [
|
|
29
|
-
| [
|
|
30
|
-
| [
|
|
14
|
+
| Class | Description |
|
|
15
|
+
| ----------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
16
|
+
| [AppKitError](./docs/api/appkit/Class.AppKitError.md) | Base error class for all AppKit errors. Provides a consistent structure for error handling across the framework. |
|
|
17
|
+
| [AppKitMcpClient](./docs/api/appkit/Class.AppKitMcpClient.md) | Lightweight MCP client for Databricks-hosted MCP servers. |
|
|
18
|
+
| [AuthenticationError](./docs/api/appkit/Class.AuthenticationError.md) | Error thrown when authentication fails. Use for missing tokens, invalid credentials, or authorization failures. |
|
|
19
|
+
| [ConfigurationError](./docs/api/appkit/Class.ConfigurationError.md) | Error thrown when configuration is missing or invalid. Use for missing environment variables, invalid settings, or setup issues. |
|
|
20
|
+
| [ConnectionError](./docs/api/appkit/Class.ConnectionError.md) | Error thrown when a connection or network operation fails. Use for database pool errors, API failures, timeouts, etc. |
|
|
21
|
+
| [DatabricksAdapter](./docs/api/appkit/Class.DatabricksAdapter.md) | Adapter that talks directly to Databricks Model Serving `/invocations` endpoint. |
|
|
22
|
+
| [ExecutionError](./docs/api/appkit/Class.ExecutionError.md) | Error thrown when an operation execution fails. Use for statement failures, canceled operations, or unexpected states. |
|
|
23
|
+
| [InitializationError](./docs/api/appkit/Class.InitializationError.md) | Error thrown when a service or component is not properly initialized. Use when accessing services before they are ready. |
|
|
24
|
+
| [MlflowClient](./docs/api/appkit/Class.MlflowClient.md) | A thin client over the Databricks workspace REST API, owning the host + bearer token so callers (eval-run creation, assessment writes, the judge's serving endpoint) don't each re-derive URLs or re-attach auth. The host is normalized once at construction. |
|
|
25
|
+
| [Plugin](./docs/api/appkit/Class.Plugin.md) | Base abstract class for creating AppKit plugins. |
|
|
26
|
+
| [PolicyDeniedError](./docs/api/appkit/Class.PolicyDeniedError.md) | Thrown when a policy denies an action. |
|
|
27
|
+
| [ResourceRegistry](./docs/api/appkit/Class.ResourceRegistry.md) | Central registry for tracking plugin resource requirements. Deduplication uses type + resourceKey (machine-stable); alias is for display only. |
|
|
28
|
+
| [ServerError](./docs/api/appkit/Class.ServerError.md) | Error thrown when server lifecycle operations fail. Use for server start/stop issues, configuration conflicts, etc. |
|
|
29
|
+
| [SupervisorApiAdapter](./docs/api/appkit/Class.SupervisorApiAdapter.md) | Adapter that calls the Databricks AI Gateway Responses API (`/ai-gateway/mlflow/v1/responses`). |
|
|
30
|
+
| [TunnelError](./docs/api/appkit/Class.TunnelError.md) | Error thrown when remote tunnel operations fail. Use for tunnel connection issues, message parsing failures, etc. |
|
|
31
|
+
| [ValidationError](./docs/api/appkit/Class.ValidationError.md) | Error thrown when input validation fails. Use for invalid parameters, missing required fields, or type mismatches. |
|
|
31
32
|
|
|
32
33
|
## Interfaces[](#interfaces "Direct link to Interfaces")
|
|
33
34
|
|
|
@@ -39,18 +40,31 @@ Documentation merge entry for Typedoc — combines the stable `@databricks/appki
|
|
|
39
40
|
| [AgentRunContext](./docs/api/appkit/Interface.AgentRunContext.md) | - |
|
|
40
41
|
| [AgentsPluginConfig](./docs/api/appkit/Interface.AgentsPluginConfig.md) | Base configuration interface for AppKit plugins |
|
|
41
42
|
| [AgentToolDefinition](./docs/api/appkit/Interface.AgentToolDefinition.md) | - |
|
|
43
|
+
| [AssertionHandle](./docs/api/appkit/Interface.AssertionHandle.md) | Chainable handle returned by every assertion to control its severity. Mirrors eve: assertions are gates by default; `.soft()` demotes to a tracked metric; `.atLeast(n)` is a soft, score-thresholded assertion. |
|
|
44
|
+
| [AssertionResult](./docs/api/appkit/Interface.AssertionResult.md) | A single recorded assertion outcome. |
|
|
45
|
+
| [Assessment](./docs/api/appkit/Interface.Assessment.md) | A Feedback assessment in the MLflow REST proto-JSON shape. |
|
|
42
46
|
| [AutoInheritToolsConfig](./docs/api/appkit/Interface.AutoInheritToolsConfig.md) | Auto-inherit configuration. When enabled for a given agent origin, agents with no explicit `tools:` declaration receive every registered ToolProvider plugin tool whose author marked `autoInheritable: true`. Tools without that flag — destructive, state-mutating, or privilege-sensitive — never spread automatically and must be wired via `tools:` (object or function form in code, `plugin:NAME` entries in markdown frontmatter). |
|
|
43
47
|
| [BasePluginConfig](./docs/api/appkit/Interface.BasePluginConfig.md) | Base configuration interface for AppKit plugins |
|
|
44
48
|
| [CacheConfig](./docs/api/appkit/Interface.CacheConfig.md) | Configuration for the CacheInterceptor. Controls TTL, size limits, storage backend, and probabilistic cleanup. |
|
|
49
|
+
| [CustomJudgeSpec](./docs/api/appkit/Interface.CustomJudgeSpec.md) | A custom LLM-judge definition: a prompt template and choice→score mapping. |
|
|
45
50
|
| [DatabaseCredential](./docs/api/appkit/Interface.DatabaseCredential.md) | Database credentials with OAuth token for Postgres connection |
|
|
46
51
|
| [DatabaseRegistry](./docs/api/appkit/Interface.DatabaseRegistry.md) | CANONICAL augmentation target. Empty by default; the generated `database.d.ts` augments it via `declare module "@databricks/appkit" { interface DatabaseRegistry { ... } }`. |
|
|
52
|
+
| [DatabricksAuth](./docs/api/appkit/Interface.DatabricksAuth.md) | Resolved Databricks host + bearer token for the eval runner's REST calls. |
|
|
53
|
+
| [DiscoveredEval](./docs/api/appkit/Interface.DiscoveredEval.md) | An eval file found under `server/agents/<agent>/evals/`. |
|
|
54
|
+
| [DriveResult](./docs/api/appkit/Interface.DriveResult.md) | What a driver returns for a single `t.send`. |
|
|
47
55
|
| [EndpointConfig](./docs/api/appkit/Interface.EndpointConfig.md) | - |
|
|
56
|
+
| [EvalDefinition](./docs/api/appkit/Interface.EvalDefinition.md) | A single eval, default-exported from a `*.eval.ts` file. |
|
|
57
|
+
| [EvalDriver](./docs/api/appkit/Interface.EvalDriver.md) | Abstraction over how the agent is driven. The HTTP driver posts to a running app's agents endpoint; future drivers (in-process) implement the same shape. |
|
|
58
|
+
| [EvalResult](./docs/api/appkit/Interface.EvalResult.md) | The outcome of running one eval. |
|
|
59
|
+
| [EvalRunSummary](./docs/api/appkit/Interface.EvalRunSummary.md) | - |
|
|
60
|
+
| [EvalSummary](./docs/api/appkit/Interface.EvalSummary.md) | - |
|
|
48
61
|
| [FilePolicyUser](./docs/api/appkit/Interface.FilePolicyUser.md) | Minimal user identity passed to the policy function. |
|
|
49
62
|
| [FileResource](./docs/api/appkit/Interface.FileResource.md) | Describes the file or directory being acted upon. |
|
|
50
63
|
| [FunctionTool](./docs/api/appkit/Interface.FunctionTool.md) | - |
|
|
51
64
|
| [GenerateDatabaseCredentialRequest](./docs/api/appkit/Interface.GenerateDatabaseCredentialRequest.md) | Request parameters for generating database OAuth credentials |
|
|
52
65
|
| [GenerationParams](./docs/api/appkit/Interface.GenerationParams.md) | Optional generation parameters forwarded to the OpenAI-compatible serving request body. Names match the serving API wire keys. Only keys that are set are sent — undefined values are omitted so the endpoint applies its own defaults. Ranges are not validated here; the serving endpoint validates. |
|
|
53
66
|
| [HostedSupervisorTool](./docs/api/appkit/Interface.HostedSupervisorTool.md) | Tagged record returned by every [supervisorTools](./docs/api/appkit/Variable.supervisorTools.md) factory. The `__kind` discriminator lets the agents plugin (and standalone `runAgent`) classify these tools without a structural match against the wire format — keeps the SA wire shape free to evolve and avoids namespace collisions with MCP hosted tools (which use `type: "genie-space"` hyphenated, vs SA's `type: "genie_space"` underscored). |
|
|
67
|
+
| [HttpDriverOptions](./docs/api/appkit/Interface.HttpDriverOptions.md) | - |
|
|
54
68
|
| [IAiSearchConfig](./docs/api/appkit/Interface.IAiSearchConfig.md) | Base configuration interface for AppKit plugins |
|
|
55
69
|
| [IJobsConfig](./docs/api/appkit/Interface.IJobsConfig.md) | Configuration for the Jobs plugin. |
|
|
56
70
|
| [IndexConfig](./docs/api/appkit/Interface.IndexConfig.md) | - |
|
|
@@ -58,22 +72,30 @@ Documentation merge entry for Typedoc — combines the stable `@databricks/appki
|
|
|
58
72
|
| [JobAPI](./docs/api/appkit/Interface.JobAPI.md) | User-facing API for a single configured job. |
|
|
59
73
|
| [JobConfig](./docs/api/appkit/Interface.JobConfig.md) | Per-job configuration options. |
|
|
60
74
|
| [JobsConnectorConfig](./docs/api/appkit/Interface.JobsConnectorConfig.md) | - |
|
|
75
|
+
| [JudgeConfig](./docs/api/appkit/Interface.JudgeConfig.md) | - |
|
|
76
|
+
| [JudgeScore](./docs/api/appkit/Interface.JudgeScore.md) | A normalized judge result. `score` is 0..1. |
|
|
61
77
|
| [LakebasePool](./docs/api/appkit/Interface.LakebasePool.md) | Subset of `pg.Pool` exposed by the Lakebase plugin. |
|
|
62
78
|
| [LakebasePoolConfig](./docs/api/appkit/Interface.LakebasePoolConfig.md) | Configuration for creating a Lakebase connection pool |
|
|
63
79
|
| [LakebasePoolManager](./docs/api/appkit/Interface.LakebasePoolManager.md) | Manages multiple Lakebase connection pools keyed by an identifier (e.g. userId). |
|
|
80
|
+
| [MatchResult](./docs/api/appkit/Interface.MatchResult.md) | Result of a deterministic matcher run against a value. |
|
|
64
81
|
| [McpConnectAllResult](./docs/api/appkit/Interface.McpConnectAllResult.md) | Per-endpoint outcome of [AppKitMcpClient.connectAll](./docs/api/appkit/Class.AppKitMcpClient.md#connectall). Callers (the agents plugin in particular) use the split to warn at startup when some MCP servers are unreachable without aborting boot for the rest. |
|
|
65
82
|
| [Message](./docs/api/appkit/Interface.Message.md) | - |
|
|
66
83
|
| [PluginManifest](./docs/api/appkit/Interface.PluginManifest.md) | Plugin manifest that declares metadata and resource requirements. Attached to plugin classes as a static property. Extends the shared PluginManifest with strict resource types. |
|
|
67
84
|
| [PluginToolkitProvider](./docs/api/appkit/Interface.PluginToolkitProvider.md) | Minimum shape every entry in the [Plugins](./docs/api/appkit/TypeAlias.Plugins.md) map must expose. Core plugins (analytics, files, genie, lakebase) implement this directly via their `.toolkit()` method. The agents plugin and standalone `runAgent` synthesize this shape for any registered plugin that doesn't implement `.toolkit()` directly (falling back to `getAgentTools()` walking). |
|
|
85
|
+
| [PostResult](./docs/api/appkit/Interface.PostResult.md) | Structured result for a best-effort POST that must not throw. |
|
|
68
86
|
| [PromptContext](./docs/api/appkit/Interface.PromptContext.md) | Context passed to `baseSystemPrompt` callbacks. |
|
|
69
87
|
| [RegisteredAgent](./docs/api/appkit/Interface.RegisteredAgent.md) | - |
|
|
88
|
+
| [ReportOutcome](./docs/api/appkit/Interface.ReportOutcome.md) | - |
|
|
70
89
|
| [RequestedClaims](./docs/api/appkit/Interface.RequestedClaims.md) | Optional claims for fine-grained Unity Catalog table permissions When specified, the returned token will be scoped to only the requested tables |
|
|
71
90
|
| [RequestedResource](./docs/api/appkit/Interface.RequestedResource.md) | Resource to request permissions for in Unity Catalog |
|
|
72
91
|
| [RerankerConfig](./docs/api/appkit/Interface.RerankerConfig.md) | - |
|
|
92
|
+
| [ResolveDatabricksAuthOptions](./docs/api/appkit/Interface.ResolveDatabricksAuthOptions.md) | - |
|
|
73
93
|
| [ResourceEntry](./docs/api/appkit/Interface.ResourceEntry.md) | Internal representation of a resource in the registry. Extends ResourceRequirement with resolution state and plugin ownership. |
|
|
74
94
|
| [ResourceRequirement](./docs/api/appkit/Interface.ResourceRequirement.md) | Declares a resource requirement for a plugin. Can be defined statically in a manifest or dynamically via getResourceRequirements(). |
|
|
75
95
|
| [RunAgentInput](./docs/api/appkit/Interface.RunAgentInput.md) | - |
|
|
76
96
|
| [RunAgentResult](./docs/api/appkit/Interface.RunAgentResult.md) | - |
|
|
97
|
+
| [RunEvalOptions](./docs/api/appkit/Interface.RunEvalOptions.md) | - |
|
|
98
|
+
| [RunEvalsOptions](./docs/api/appkit/Interface.RunEvalsOptions.md) | - |
|
|
77
99
|
| [Schema](./docs/api/appkit/Interface.Schema.md) | One finalized schema. `TTableName` keeps the declared names in the type, so configuration that addresses a table by name is checked against the schema it was written for. Code that accepts any schema uses the default. |
|
|
78
100
|
| [SearchRequest](./docs/api/appkit/Interface.SearchRequest.md) | - |
|
|
79
101
|
| [SearchResponse](./docs/api/appkit/Interface.SearchResponse.md) | - |
|
|
@@ -84,6 +106,7 @@ Documentation merge entry for Typedoc — combines the stable `@databricks/appki
|
|
|
84
106
|
| [SupervisorApiAdapterOptions](./docs/api/appkit/Interface.SupervisorApiAdapterOptions.md) | - |
|
|
85
107
|
| [SupervisorExtension](./docs/api/appkit/Interface.SupervisorExtension.md) | Shape of the value at `AgentInput.extensions[SUPERVISOR_EXTENSION_KEY]`. The agents plugin / `runAgent` build this from the tool index; advanced callers invoking `adapter.run(...)` directly populate it themselves. |
|
|
86
108
|
| [TelemetryConfig](./docs/api/appkit/Interface.TelemetryConfig.md) | OpenTelemetry configuration for AppKit applications |
|
|
109
|
+
| [TestContext](./docs/api/appkit/Interface.TestContext.md) | The `t` context passed to an eval's `test` function. |
|
|
87
110
|
| [Thread](./docs/api/appkit/Interface.Thread.md) | - |
|
|
88
111
|
| [ThreadStore](./docs/api/appkit/Interface.ThreadStore.md) | - |
|
|
89
112
|
| [ToolAnnotations](./docs/api/appkit/Interface.ToolAnnotations.md) | - |
|
|
@@ -108,6 +131,7 @@ Documentation merge entry for Typedoc — combines the stable `@databricks/appki
|
|
|
108
131
|
| [BaseSystemPromptOption](./docs/api/appkit/TypeAlias.BaseSystemPromptOption.md) | - |
|
|
109
132
|
| [ConfigSchema](./docs/api/appkit/TypeAlias.ConfigSchema.md) | Configuration schema definition for plugin config. Re-exported from the standard JSON Schema Draft 7 types. |
|
|
110
133
|
| [DatabaseExports](./docs/api/appkit/TypeAlias.DatabaseExports.md) | Typed database API published by the plugin. |
|
|
134
|
+
| [EvalProgress](./docs/api/appkit/TypeAlias.EvalProgress.md) | - |
|
|
111
135
|
| [ExecutionResult](./docs/api/appkit/TypeAlias.ExecutionResult.md) | Discriminated union for plugin execution results. |
|
|
112
136
|
| [FileAction](./docs/api/appkit/TypeAlias.FileAction.md) | Every action the files plugin can perform. |
|
|
113
137
|
| [FilePolicy](./docs/api/appkit/TypeAlias.FilePolicy.md) | A policy function that decides whether `user` may perform `action` on `resource`. Return `true` to allow, `false` to deny. |
|
|
@@ -115,6 +139,7 @@ Documentation merge entry for Typedoc — combines the stable `@databricks/appki
|
|
|
115
139
|
| [IAppRouter](./docs/api/appkit/TypeAlias.IAppRouter.md) | Express router type for plugin route registration |
|
|
116
140
|
| [IDatabaseConfig](./docs/api/appkit/TypeAlias.IDatabaseConfig.md) | Configuration for one schema-bound DatabasePlugin instance. |
|
|
117
141
|
| [JobsExport](./docs/api/appkit/TypeAlias.JobsExport.md) | Public API shape of the jobs plugin. Callable to select a job by key. |
|
|
142
|
+
| [Matcher](./docs/api/appkit/TypeAlias.Matcher.md) | A deterministic matcher: inspects a string value and returns a result. |
|
|
118
143
|
| [PluginData](./docs/api/appkit/TypeAlias.PluginData.md) | Tuple of plugin class, config, and name. Created by `toPlugin()` and passed to `createApp()`. |
|
|
119
144
|
| [Plugins](./docs/api/appkit/TypeAlias.Plugins.md) | Plugin map passed to the function form of [AgentDefinition.tools](./docs/api/appkit/Interface.AgentDefinition.md#tools). Each entry exposes a `.toolkit(opts?)` method that returns a record of [ToolkitEntry](./docs/api/appkit/Interface.ToolkitEntry.md) markers ready to be spread into a tool record. |
|
|
120
145
|
| [ResolvedToolEntry](./docs/api/appkit/TypeAlias.ResolvedToolEntry.md) | Internal tool-index entry after a tool record has been resolved to a dispatchable form. |
|
|
@@ -122,6 +147,7 @@ Documentation merge entry for Typedoc — combines the stable `@databricks/appki
|
|
|
122
147
|
| [ResourcePermission](./docs/api/appkit/TypeAlias.ResourcePermission.md) | Union of all possible permission levels across all resource types. |
|
|
123
148
|
| [SearchFilters](./docs/api/appkit/TypeAlias.SearchFilters.md) | - |
|
|
124
149
|
| [ServingFactory](./docs/api/appkit/TypeAlias.ServingFactory.md) | Factory function returned by `AppKit.serving`. |
|
|
150
|
+
| [Severity](./docs/api/appkit/TypeAlias.Severity.md) | Whether an assertion fails the eval (`gate`) or is tracked only (`soft`). |
|
|
125
151
|
| [SupervisorTool](./docs/api/appkit/TypeAlias.SupervisorTool.md) | Tools supported by the Databricks AI Gateway Responses API. The shapes match the wire format the endpoint expects, so the adapter passes the array straight into the request body. |
|
|
126
152
|
| [ToolRegistry](./docs/api/appkit/TypeAlias.ToolRegistry.md) | - |
|
|
127
153
|
| [ToPlugin](./docs/api/appkit/TypeAlias.ToPlugin.md) | Factory function type returned by `toPlugin()`. Accepts optional config and returns a PluginData tuple. |
|
|
@@ -148,20 +174,31 @@ Documentation merge entry for Typedoc — combines the stable `@databricks/appki
|
|
|
148
174
|
| [bigid](./docs/api/appkit/Function.bigid.md) | - |
|
|
149
175
|
| [bigint](./docs/api/appkit/Function.bigint.md) | - |
|
|
150
176
|
| [boolean](./docs/api/appkit/Function.boolean.md) | - |
|
|
177
|
+
| [buildAssessments](./docs/api/appkit/Function.buildAssessments.md) | - |
|
|
178
|
+
| [configureJudge](./docs/api/appkit/Function.configureJudge.md) | Configure the judge once. Sets the OpenAI-compatible client env autoevals reads and the default judge model. No-op-safe: on failure, judging stays disabled and [isJudgeConfigured](./docs/api/appkit/Function.isJudgeConfigured.md) returns false. |
|
|
151
179
|
| [createAgent](./docs/api/appkit/Function.createAgent.md) | Pure factory for agent definitions: cycle-detects the sub-agent graph and returns the same object, stamped with a non-enumerable AGENT\_BRAND so discovery recognizes it. Safe at module top-level; no adapter is built. Don't `Object.freeze` the definition before passing it in — the brand is written onto the argument. |
|
|
152
180
|
| [createApp](./docs/api/appkit/Function.createApp.md) | Bootstraps AppKit with the provided configuration. |
|
|
181
|
+
| [createHttpDriver](./docs/api/appkit/Function.createHttpDriver.md) | Drives an agent by POSTing to a running app's chat endpoint and parsing the SSE response. Keeps the thread id across `send`s so multi-turn evals share a conversation. Agent/stream errors surface as `succeeded: false` rather than throwing, so `t.succeeded()` can assert on them. |
|
|
153
182
|
| [createLakebasePool](./docs/api/appkit/Function.createLakebasePool.md) | Create a Lakebase pool with appkit's logger integration. Telemetry automatically uses appkit's OpenTelemetry configuration via global registry. |
|
|
154
183
|
| [createLakebasePoolManager](./docs/api/appkit/Function.createLakebasePoolManager.md) | Create a pool manager that maintains per-key Lakebase connection pools. |
|
|
155
184
|
| [createWorkspaceClient](./docs/api/appkit/Function.createWorkspaceClient.md) | Construct an AppKit workspace client. |
|
|
156
185
|
| [database](./docs/api/appkit/Function.database.md) | Create a typed database plugin registration for a finalized schema. |
|
|
186
|
+
| [defineEval](./docs/api/appkit/Function.defineEval.md) | Define an agent eval. Default-export the result from a `server/agents/<id>/evals/*.eval.ts` file. |
|
|
157
187
|
| [defineManifest](./docs/api/appkit/Function.defineManifest.md) | Validates a raw manifest (typically a `manifest.json` import) against the canonical Zod schema and returns it as a strict [PluginManifest](./docs/api/appkit/Interface.PluginManifest.md). |
|
|
158
188
|
| [defineSchema](./docs/api/appkit/Function.defineSchema.md) | Compile one declared schema. The returned type keeps the table names the builder returned, so `crudRoutes` and `hooks` can name only real tables. |
|
|
159
189
|
| [defineTool](./docs/api/appkit/Function.defineTool.md) | Defines a single tool entry for a plugin's internal registry. |
|
|
190
|
+
| [discoverEvalFiles](./docs/api/appkit/Function.discoverEvalFiles.md) | Discover evals under `<rootDir>/server/agents/<agent>/evals/` — co-located with each agent's `agent.{md,ts}` (same folder-per-agent layout the agents plugin discovers). The agent id is the folder name; the eval id is the file path relative to that evals dir with `.eval.ts` stripped. Sorted + stable. |
|
|
160
191
|
| [enumColumn](./docs/api/appkit/Function.enumColumn.md) | - |
|
|
192
|
+
| [equals](./docs/api/appkit/Function.equals.md) | Passes when the value equals `expected` exactly. |
|
|
193
|
+
| [evalGlyph](./docs/api/appkit/Function.evalGlyph.md) | Status glyph for a single eval result. |
|
|
161
194
|
| [executeFromRegistry](./docs/api/appkit/Function.executeFromRegistry.md) | Validates tool-call arguments against the entry's schema and invokes its handler. On validation failure, returns an LLM-friendly error string (matching the behavior of `tool()`) rather than throwing, so the model can self-correct on its next turn. |
|
|
162
195
|
| [extractServingEndpoints](./docs/api/appkit/Function.extractServingEndpoints.md) | Extract serving endpoint config from a server file by AST-parsing it. Looks for `serving({ endpoints: { alias: { env: "..." }, ... } })` calls and extracts the endpoint alias names and their environment variable mappings. |
|
|
163
196
|
| [findServerFile](./docs/api/appkit/Function.findServerFile.md) | Find the server entry file by checking candidate paths in order. |
|
|
164
197
|
| [fk](./docs/api/appkit/Function.fk.md) | Declare foreign-key to another column. |
|
|
198
|
+
| [formatEvalDetail](./docs/api/appkit/Function.formatEvalDetail.md) | Indented detail lines for a failing eval (error + failing assertions). |
|
|
199
|
+
| [formatEvalHeadline](./docs/api/appkit/Function.formatEvalHeadline.md) | The one-line header for a single eval result (no failure detail). |
|
|
200
|
+
| [formatEvalResults](./docs/api/appkit/Function.formatEvalResults.md) | Render all results as a human-readable console report (non-streaming). |
|
|
201
|
+
| [formatSummaryLine](./docs/api/appkit/Function.formatSummaryLine.md) | The final PASS/FAIL summary line. |
|
|
165
202
|
| [fromSupervisorApi](./docs/api/appkit/Function.fromSupervisorApi.md) | Creates an [AgentAdapter](./docs/api/appkit/Interface.AgentAdapter.md) backed by the Databricks AI Gateway Responses API (`/ai-gateway/mlflow/v1/responses`). |
|
|
166
203
|
| [functionToolToDefinition](./docs/api/appkit/Function.functionToolToDefinition.md) | - |
|
|
167
204
|
| [generateDatabaseCredential](./docs/api/appkit/Function.generateDatabaseCredential.md) | Generate OAuth credentials for Postgres database connection using the proper Postgres API. |
|
|
@@ -173,19 +210,28 @@ Documentation merge entry for Typedoc — combines the stable `@databricks/appki
|
|
|
173
210
|
| [getUsernameWithApiLookup](./docs/api/appkit/Function.getUsernameWithApiLookup.md) | Resolves the PostgreSQL username for a Lakebase connection. |
|
|
174
211
|
| [getWorkspaceClient](./docs/api/appkit/Function.getWorkspaceClient.md) | Get workspace client from config or SDK default auth chain |
|
|
175
212
|
| [id](./docs/api/appkit/Function.id.md) | - |
|
|
213
|
+
| [includes](./docs/api/appkit/Function.includes.md) | Passes when the value contains `substring`. |
|
|
176
214
|
| [integer](./docs/api/appkit/Function.integer.md) | - |
|
|
177
215
|
| [isFunctionTool](./docs/api/appkit/Function.isFunctionTool.md) | - |
|
|
178
216
|
| [isHostedTool](./docs/api/appkit/Function.isHostedTool.md) | - |
|
|
217
|
+
| [isJudgeConfigured](./docs/api/appkit/Function.isJudgeConfigured.md) | - |
|
|
179
218
|
| [isSQLTypeMarker](./docs/api/appkit/Function.isSQLTypeMarker.md) | Type guard to check if a value is a SQL type marker |
|
|
180
219
|
| [isSupervisorTool](./docs/api/appkit/Function.isSupervisorTool.md) | Type guard for [HostedSupervisorTool](./docs/api/appkit/Interface.HostedSupervisorTool.md). Used by the agents plugin (`buildToolIndex`) and standalone `runAgent` (`classifyTool`) to route supervisor-hosted tools to the extensions payload rather than the adapter's `tools` array. |
|
|
181
220
|
| [isToolkitEntry](./docs/api/appkit/Function.isToolkitEntry.md) | Type guard for `ToolkitEntry` — used by the agents plugin to differentiate toolkit references from inline tools in a mixed `tools` record. |
|
|
182
221
|
| [jsonb](./docs/api/appkit/Function.jsonb.md) | - |
|
|
183
222
|
| [loadAgentFromFile](./docs/api/appkit/Function.loadAgentFromFile.md) | Loads a single markdown agent file and resolves its frontmatter against registered plugin toolkits + ambient tool library. |
|
|
184
223
|
| [loadAgentsFromDir](./docs/api/appkit/Function.loadAgentsFromDir.md) | Scans a directory for one subdirectory per agent, each containing `agent.md` (frontmatter + body). Produces an `AgentDefinition` record keyed by agent id (folder name). Throws on frontmatter errors or unresolved references. Returns an empty map if the directory does not exist. |
|
|
224
|
+
| [matches](./docs/api/appkit/Function.matches.md) | Passes when the value matches `pattern`. |
|
|
185
225
|
| [mcpServer](./docs/api/appkit/Function.mcpServer.md) | Factory for declaring a custom MCP server tool. |
|
|
226
|
+
| [normalizeHost](./docs/api/appkit/Function.normalizeHost.md) | Ensure the host has a scheme (Databricks env often lacks `https://`). |
|
|
186
227
|
| [parseTextToolCalls](./docs/api/appkit/Function.parseTextToolCalls.md) | Parses text-based tool calls from model output. |
|
|
228
|
+
| [reportToMlflow](./docs/api/appkit/Function.reportToMlflow.md) | Write one pass/fail assessment per eval result to the Databricks MLflow REST API. Never throws — failures are collected so the run still reports. |
|
|
229
|
+
| [resolveDatabricksAuth](./docs/api/appkit/Function.resolveDatabricksAuth.md) | - |
|
|
187
230
|
| [resolveHostedTools](./docs/api/appkit/Function.resolveHostedTools.md) | - |
|
|
188
231
|
| [runAgent](./docs/api/appkit/Function.runAgent.md) | Standalone agent execution without `createApp`. Resolves the adapter, binds inline tools, and drives the adapter's `run()` loop to completion. |
|
|
232
|
+
| [runEval](./docs/api/appkit/Function.runEval.md) | Run a single eval against a driver. Never throws for assertion or agent failures — those become a non-passing [EvalResult](./docs/api/appkit/Interface.EvalResult.md). Only a malformed eval definition surfaces as `result.error`. |
|
|
233
|
+
| [runEvalsInDir](./docs/api/appkit/Function.runEvalsInDir.md) | Discover, load, and run every eval under each agent's `evals/` dir, driving the agents on a running app. Never throws for an individual eval — load/run failures become non-passing [EvalResult](./docs/api/appkit/Interface.EvalResult.md)s. |
|
|
234
|
+
| [summarize](./docs/api/appkit/Function.summarize.md) | - |
|
|
189
235
|
| [text](./docs/api/appkit/Function.text.md) | - |
|
|
190
236
|
| [timestamp](./docs/api/appkit/Function.timestamp.md) | - |
|
|
191
237
|
| [tool](./docs/api/appkit/Function.tool.md) | Factory for defining function tools with Zod schemas. |
|