mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
Systematic prune per AGENTS.md test policy, one pass over every major test tree (gateway, hermes_cli, tools, agent, run_agent, plugins, cli, cron, tui_gateway, honcho/openviking, root-level): - DELETE: source-reading tests (read_text/getsource on prod files), change-detector tests (exact catalog counts, model-name snapshots, config version literals), mock-echo tests (assert a mock returns what it was told), assertion-free/trivial tests, near-duplicate parametrizations (boundaries + one representative kept), async/sync twin duplicates, cosmetic within-file variations. - KEEP (mandatory): security/redaction/approval guards, message-role alternation invariants, prompt-caching/deterministic-call-id invariants, issue-number regression tests (deduped), E2E tests. - 6 test files deleted outright (script-style/no-assert or fully redundant); conftest.py, fakes/, fixtures/ untouched. - tests/acp/conftest.py added: autouse fixture stubs the live models.dev/GitHub/Copilot/Anthropic inventory fetches that ACP server tests performed on every session create — test_server.py 147s → 3.4s, and the tests are now genuinely hermetic. - Sleep-based slowness shrunk where safe (codex_ttfb_watchdog, compression_concurrent_fork, etc.); no wall-clock assertion tightened. Verification: full hermetic suite via scripts/run_tests.sh — 2439 files, 31,130 tests passed, 0 failed, 0 flaky retries, 315s wall (baseline: 583s wall, 13,564s subprocess CPU).
63 lines
1.4 KiB
Python
63 lines
1.4 KiB
Python
"""Tests for _repair_tool_call_arguments — malformed JSON repair pipeline."""
|
|
|
|
import json
|
|
|
|
from run_agent import _repair_tool_call_arguments
|
|
|
|
|
|
class TestRepairToolCallArguments:
|
|
"""Verify each repair stage in the pipeline."""
|
|
|
|
# -- Stage 1: empty / whitespace-only --
|
|
|
|
def test_empty_string_returns_empty_object(self):
|
|
assert _repair_tool_call_arguments("", "t") == "{}"
|
|
|
|
|
|
|
|
# -- Stage 2: Python None literal --
|
|
|
|
|
|
|
|
# -- Stage 3: trailing comma repair --
|
|
|
|
|
|
def test_trailing_comma_in_array(self):
|
|
result = _repair_tool_call_arguments('{"a": [1, 2,]}', "t")
|
|
parsed = json.loads(result)
|
|
assert parsed == {"a": [1, 2]}
|
|
|
|
|
|
# -- Stage 4: unclosed brackets --
|
|
|
|
|
|
|
|
# -- Stage 5: excess closing delimiters --
|
|
|
|
|
|
|
|
# -- Stage 6: last resort --
|
|
|
|
|
|
def test_unrepairable_partial_returns_empty_object(self):
|
|
# Truncated in the middle of a string key — bracket closing won't help
|
|
assert _repair_tool_call_arguments('{"truncated": "val', "t") == "{}"
|
|
|
|
# -- Valid JSON passthrough (this path is via except, but still works) --
|
|
|
|
|
|
# -- Combined repairs --
|
|
|
|
|
|
|
|
# -- Stage 0: strict=False (literal control chars in strings) --
|
|
# llama.cpp backends sometimes emit literal tabs/newlines inside JSON
|
|
# string values. strict=False accepts these; we re-serialise to the
|
|
# canonical wire form (#12068).
|
|
|
|
|
|
|
|
|
|
# -- Stage 4: control-char escape fallback --
|
|
|
|
|