Files
Agent-Workbench/docs/task-control-j-release-evidence/0008-model-accounting-initial.tap
T
2026-11-01 16:35:58 +08:00

87 lines
7.6 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
✔ model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart (1333.0803ms)
✔ config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts (1164.1443ms)
✔ real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity (3585.9704ms)
✔ pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests (5366.5035ms)
✔ 401 blocks the credential revision; updating the key restores availability without leaking error echoes (1747.0949ms)
✔ queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request (1136.4961ms)
✔ compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model (2389.606ms)
✔ model registry disk failures restore routing, pool profiles and credential references without partial updates (783.0563ms)
✔ model selection and saved configuration commit together and failures preserve the original mode and endpoint (814.7471ms)
✔ configuration imports roll back the entire batch and retain one usable preview after validation or commit failure (1151.8458ms)
✔ saved engine budgets verify all Chat/Responses route variants and reject a mismatched output allowance (1168.6738ms)
✔ owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched (1381.3996ms)
✔ Responses executes one original tool through Runtime, carries encrypted Items, reports raw usage and seals exact wire bytes (2996.4647ms)
✔ mixed-protocol pool keeps both actual variants and changes route on 429 without re-executing completed tools (3912.209ms)
▶ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool
✔ Reject {"body":{"id":"resp_owned","status":"incomplete","output":[{"type":"function_call","id":"fc_partial" (1906.461ms)
✔ Reject {"body":{"id":"resp_owned","status":"failed","output":[{"type":"function_call","id":"fc_failed","cal (1906.9122ms)
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"function_call","id":"fc_bad","cal (1928.8754ms)
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"computer_call","id":"not-supporte (1296.527ms)
✔ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool (7039.6819ms)
▶ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay
✔ chat-completions (2081.2153ms)
✔ responses (2080.5379ms)
✔ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay (4162.253ms)
✔ wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint (0.3055ms)
✔ connection JSON import accepts explicit Responses protocol and continues to reject unknown protocols without reading client sessions (544.1457ms)
✔ HTTP download preserves original malformed SSE bytes and artifact SHA instead of decoding invalid UTF8 (2336.2815ms)
✖ terminated SSE adapts empty optional tool arguments, retains the exact wire bytes and executes the validated batch once (2722.3065ms)
✔ reported SSE usage survives rejected required arguments "" without dispatching any tool (1396.4399ms)
✔ reported SSE usage survives rejected required arguments "{\"path\":" without dispatching any tool (1157.9208ms)
✔ reported SSE usage survives rejected required arguments "null" without dispatching any tool (1234.1828ms)
✔ a stream without DONE retains reported usage but cannot adapt or execute even an optional tool (1298.4688ms)
✔ a timeout after reasoning-only fragments creates one unknown receipt and never invents reported tokens (1641.0366ms)
✔ real Chat SSE carries UTF8 and split tool JSON; Runtime executes only after DONE, stores partial progress and original usage (2366.4535ms)
✔ Responses typed SSE validates original item identity, terminal data, raw usage and tool result pair (1953.0612ms)
✔ incomplete network stream retains unknown attempt and never automatically switches pool or dispatches fragment tools (1415.3169ms)
✔ stopping an active HTTP stream closes only original request and keeps partial text without executing tools (1335.9278ms)
✔ explicit streaming probe uses actual SSE despite unknown declaration and binds its own original attempt (661.5481ms)
✔ coalesced initial SSE events publish the latest partial state even when the upstream stays idle (1386.1776ms)
✔ stream timeout closes the original HTTP response, preserves redacted capture and never retries (868.242ms)
✔ SSE accepts CR-only final event boundaries and retains exact invalid UTF8 bytes without dispatch (0.7513ms)
▶ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data
✔ reject 0 (0.2119ms)
✔ reject 1 (0.178ms)
✔ reject 2 (0.1575ms)
✔ reject 3 (4.7821ms)
✔ reject 4 (0.3083ms)
✔ reject 5 (0.1834ms)
✔ stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data (6.3774ms)
ℹ tests 46
ℹ suites 0
ℹ pass 45
ℹ fail 1
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 41525.9633
✖ failing tests:
test at tests\model-stream.test.mjs:46:1
✖ terminated SSE adapts empty optional tool arguments, retains the exact wire bytes and executes the validated batch once (2722.3065ms)
AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:
+ actual - expected
+ 'data: {"choices":[{"index":0,"delta":{"content":"读取已完成。"},"finish_reason":null}]}\r\n' +
- 'data: {"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"id":"empty-inspection","type":"function","function":{"name":"inspect_project","arguments":""}},{"index":1,"id":"valid-file","type":"function","function":{"name":"read_file","arguments":"{\\"path\\":\\"README.md\\"}"}}]},"finish_reason":null}]}\r\n' +
'\r\n' +
+ 'data: {"choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}\r\n' +
- 'data: {"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}\r\n' +
'\r\n' +
'data: {"choices":[],"usage":{"prompt_tokens":20,"completion_tokens":10}}\r\n' +
'\r\n' +
'data: [DONE]\r\n' +
'\r\n'
at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/tests/model-stream.test.mjs:58:10)
at async Test.run (node:internal/test_runner/test:1409:7)
at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {
generatedMessage: true,
code: 'ERR_ASSERTION',
actual: 'data: {"choices":[{"index":0,"delta":{"content":"读取已完成。"},"finish_reason":null}]}\r\n\r\ndata: {"choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}\r\n\r\ndata: {"choices":[],"usage":{"prompt_tokens":20,"completion_tokens":10}}\r\n\r\ndata: [DONE]\r\n\r\n',
expected: 'data: {"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"id":"empty-inspection","type":"function","function":{"name":"inspect_project","arguments":""}},{"index":1,"id":"valid-file","type":"function","function":{"name":"read_file","arguments":"{\\"path\\":\\"README.md\\"}"}}]},"finish_reason":null}]}\r\n\r\ndata: {"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}]}\r\n\r\ndata: {"choices":[],"usage":{"prompt_tokens":20,"completion_tokens":10}}\r\n\r\ndata: [DONE]\r\n\r\n',
operator: 'strictEqual',
diff: 'simple'
}