Hugging Face's logo

Spaces:
GGUFGuy
/
ml-intern-custom
Sleeping

App Files Community
ml-intern-custom
File size: 4,977 Bytes
3eec386
 
 
 
437a804
3eec386
 
 
437a804
 
3eec386
 
 
 
 
 
 
 
ebc9798
3eec386
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
437a804
3eec386
 
437a804
3eec386
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
754345f
 
 
3eec386
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
437a804
3eec386
437a804
3eec386
 
ebc9798
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
"""Tests for LLM error classification helpers in agent.core.agent_loop.

Covers two regressions on 2026-04-25:

1. Router context overflow (Kimi 365k > 262k) was not classified as
   ``_is_context_overflow_error``, so the recovery path didn't fire and
   session 62ccfdcb died with 68 wasted compaction events.

2. Provider token-bucket rate limits (`Too many tokens, please wait before
   trying again.`) need the longer rate-limit retry schedule. The old schedule
   ([5, 15, 30] = 50s) burned through 6 sessions costing >$2,400 combined
   on the same day.
"""

from agent.core.agent_loop import (
    _MAX_LLM_RETRIES,
    _LLM_RATE_LIMIT_RETRY_DELAYS,
    _LLM_RETRY_DELAYS,
    _friendly_error_message,
    _is_context_overflow_error,
    _is_rate_limit_error,
    _is_transient_error,
    _retry_delay_for,
)


# ── context overflow ────────────────────────────────────────────────────


def test_kimi_prompt_too_long_is_context_overflow():
    # Verbatim error text from session 62ccfdcb (2026-04-25, Kimi K2.6).
    err = Exception(
        "litellm.BadRequestError: OpenAIException - The prompt is too long: "
        "365407, model maximum context length: 262143"
    )
    assert _is_context_overflow_error(err)


def test_openai_context_length_exceeded_is_context_overflow():
    err = Exception("Error: This model's maximum context length is 8192 tokens.")
    assert _is_context_overflow_error(err)


def test_random_error_is_not_context_overflow():
    err = Exception("connection reset by peer")
    assert not _is_context_overflow_error(err)


# ── rate limit ──────────────────────────────────────────────────────────


def test_provider_too_many_tokens_is_rate_limit():
    # Verbatim from sessions b37a3823, c4d7a831, b63c4933 (2026-04-25).
    err = Exception(
        'litellm.RateLimitError: ProviderException - {"message":"Too many '
        'tokens, please wait before trying again."}'
    )
    assert _is_rate_limit_error(err)
    # Rate-limit errors are also classified as transient.
    assert _is_transient_error(err)


def test_429_is_rate_limit():
    err = Exception("HTTP 429 Too Many Requests")
    assert _is_rate_limit_error(err)


def test_timeout_is_transient_but_not_rate_limit():
    err = Exception("Request timed out after 600s")
    assert _is_transient_error(err)
    assert not _is_rate_limit_error(err)


# ── retry schedule selection ────────────────────────────────────────────


def test_rate_limit_uses_longer_schedule():
    err = Exception("Too many tokens, please wait before trying again.")
    delays = [
        _retry_delay_for(err, i) for i in range(len(_LLM_RATE_LIMIT_RETRY_DELAYS))
    ]
    assert delays == _LLM_RATE_LIMIT_RETRY_DELAYS
    # Just past the schedule → None (stop retrying).
    assert _retry_delay_for(err, len(_LLM_RATE_LIMIT_RETRY_DELAYS)) is None


def test_other_transient_uses_short_schedule():
    err = Exception("503 service unavailable")
    delays = [_retry_delay_for(err, i) for i in range(len(_LLM_RETRY_DELAYS))]
    assert delays == _LLM_RETRY_DELAYS
    assert _retry_delay_for(err, len(_LLM_RETRY_DELAYS)) is None


def test_non_transient_returns_none():
    err = Exception("invalid request: bad parameter")
    assert _retry_delay_for(err, 0) is None


def test_rate_limit_total_budget_covers_token_bucket_recovery():
    """The whole point of the rate-limit schedule: total wait time should
    exceed a typical ~60s provider token-bucket recovery window."""
    assert len(_LLM_RATE_LIMIT_RETRY_DELAYS) == _MAX_LLM_RETRIES - 1
    assert sum(_LLM_RATE_LIMIT_RETRY_DELAYS) > 60


def test_free_user_credit_error_mentions_pro_and_billing_links():
    msg = _friendly_error_message(
        Exception("402 Payment Required: monthly credits exhausted"),
        user_plan="free",
    )

    assert msg is not None
    assert "https://huggingface.co/subscribe/pro" in msg
    assert "https://huggingface.co/settings/billing" in msg


def test_pro_user_credit_error_mentions_billing_only():
    msg = _friendly_error_message(
        Exception("insufficient_quota"),
        user_plan="pro",
    )

    assert msg is not None
    assert "https://huggingface.co/settings/billing" in msg
    assert "https://huggingface.co/subscribe/pro" not in msg


def test_unknown_plan_credit_error_uses_fallback_wording():
    msg = _friendly_error_message(
        Exception("exhausted monthly credits"),
        user_plan="unknown",
    )

    assert msg is not None
    assert "appear to be exhausted" in msg
    assert "If this is a free account" in msg
    assert "https://huggingface.co/settings/billing" in msg
    assert "https://huggingface.co/subscribe/pro" in msg