Files
hermes-agent/tests/run_agent/test_run_agent_multimodal_prologue.py
T
Teknium 6b81590c55 test: prune low-value tests suite-wide (wave 1) — 46,820 → 28,106 test functions
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).
2026-07-29 13:10:23 -07:00

48 lines
1.6 KiB
Python

"""Regression tests for run_conversation's prologue handling of multimodal content.
PR #5621 and earlier multimodal PRs hit an ``AttributeError`` in
``run_agent.run_conversation`` because the prologue unconditionally called
``user_message[:80] + "..."`` / ``.replace()`` / ``_safe_print(f"...{user_message[:60]}")``
on what was now a list. These tests cover the two fixes:
1. ``_summarize_user_message_for_log`` accepts strings, lists, and ``None``.
2. ``_chat_content_to_responses_parts`` converts chat-style content to the
Responses API ``input_text`` / ``input_image`` shape.
They do NOT boot the full AIAgent — the prologue-fix guarantees are pure
function contracts at module scope.
"""
from run_agent import _summarize_user_message_for_log
from agent.codex_responses_adapter import _chat_content_to_responses_parts
class TestSummarizeUserMessageForLog:
def test_plain_string_passthrough(self):
assert _summarize_user_message_for_log("hello world") == "hello world"
def test_text_only_list(self):
content = [{"type": "text", "text": "hi"}, {"type": "text", "text": "there"}]
assert _summarize_user_message_for_log(content) == "hi there"
class TestChatContentToResponsesParts:
def test_non_list_returns_empty(self):
assert _chat_content_to_responses_parts("hi") == []
assert _chat_content_to_responses_parts(None) == []
def test_text_parts_become_input_text(self):
content = [{"type": "text", "text": "hello"}]
assert _chat_content_to_responses_parts(content) == [{"type": "input_text", "text": "hello"}]