hermes-agent/tests/agent/test_title_generator.py
Teknium 597615ade4
fix(ci): make tests, workflows, and attribution reliable under load (#66373)
* feat(attribution): conflict-free contributor mappings via contributors/emails/ directory

The AUTHOR_MAP dict in scripts/release.py was a merge-conflict magnet:
every concurrent salvage PR appended entries to the same lines of the
same file, so parallel PRs re-conflicted on every merge to main.

New system: one file per email under contributors/emails/ — filename is
the commit-author email, first non-comment line is the GitHub login.
File additions never conflict, so any number of PRs can add mappings
concurrently.

- scripts/release.py: AUTHOR_MAP is now LEGACY_AUTHOR_MAP (frozen)
  merged with the directory at import time (directory wins). All
  existing consumers (resolve_author, contributor_audit.py) unchanged.
- scripts/add_contributor.py: idempotent CLI to add a mapping; refuses
  conflicting reassignments (incl. against the legacy map), validates
  email/login shapes.
- contributor-check.yml: attribution gate now accepts a mapping file OR
  a legacy entry; failure message prints the exact add_contributor
  command. Also auto-resolves bare <login>@users.noreply.github.com
  emails is intentionally NOT added (kept id+login form only, matching
  previous behavior).
- contributor_audit.py: guidance now points at add_contributor.py.
- tests/scripts/test_contributor_map.py: 12 tests covering loader,
  merge precedence, CLI idempotency/conflict/validation, subprocess E2E.

* feat(ci): one-shot per-file flake retry in the parallel test runner

A failing test FILE is re-run once in a fresh subprocess. Pass-on-retry
counts as green but is loudly reported in a '⚠ FLAKY' summary section
(with both attempts' output preserved) so the flake gets fixed instead
of eating a full-run rerun. Deterministic failures fail both attempts —
regressions cannot be laundered green.

- --file-retries N / HERMES_TEST_FILE_RETRIES (default 1, 0 disables)
- E2E verified: simulated first-run-fail flake goes green with banner;
  deterministic failure still exits 1; retries=0 restores old behavior.

This converts the dominant CI failure mode (one timing-sensitive test
flaking a 4600-test shard, requiring a manual 10-minute rerun and an
agent triage loop) into a self-healing retry that costs one file's
runtime.

* test(approval): loosen wall-clock perf bounds 0.15s -> 2.0s

These guard against catastrophic regex backtracking (seconds-to-minutes
class), but 0.15s is within scheduler-stall noise on loaded shared CI
runners — test_max_accepted_separator_free_input_is_fast failed a CI
shard this week on runner load alone. 2.0s still catches the regression
class with zero flake surface.

* fix(ci): job timeouts everywhere + retries on all network installs

Reliability pass over every workflow:
- timeout-minutes on all 21 jobs that lacked one (a hung job previously
  burned the 6-hour default runner budget)
- ./.github/actions/retry wrapped around every network-fetching install
  that lacked it: pip installs (deploy-site, skills-index), npm ci
  (deploy-site website, upload_to_pypi web + ui-tui), uv sync (docker
  test deps). Deterministic build steps (npm run build) deliberately
  NOT retried — split into separate steps so a real build failure fails
  fast instead of retrying 3x.

* docs(agents): document the file-retry flake policy

* fix(ci): curl retries on deploy hook + skills-index probe

* fix(ci): kill the remaining transient-failure classes in workflows + Dockerfile

From the workflow reliability audit:
- tests.yml: duration-cache restore had NO restore-keys while saves use
  run_id-suffixed keys — the cache never matched once, so LPT slicing
  always ran blind and unbalanced slices pushed heavy files toward the
  per-file timeout. One-line restore-keys fixes slice balancing.
- Label gates (lint ci-reviewed, supply-chain mcp-catalog-reviewed):
  'gh pr view || true' turned an API blip into 'label absent' → false
  BLOCKING failure. Now 3x retry, and API failure is reported as an API
  failure instead of a missing label.
- detect-changes action: compare API retried before failing open (was
  silently running all lanes on any blip).
- uv-lockfile-check: 'uv lock --check' resolves against PyPI — retried
  so registry blips don't read as 'lockfile stale'.
- docker.yml merge job: imagetools create retried (Docker Hub eventual
  consistency on just-pushed digests).
- Dockerfile: apt-get Acquire::Retries=3; s6-overlay ADDs converted to
  curl --retry 3 (ADD cannot retry; checksums still enforced); npm
  --fetch-retries=5; playwright chromium fetch retried 3x.
- Advisory artifact uploads (per-slice durations, ci-timings report)
  get continue-on-error so an artifact-service blip can't fail a green
  test slice.

* fix(tests): kill the two root-cause flakes — leaking pre-warm timer + env-dependent provider list

- test_tui_gateway_server.py: session.create / non-eager session.resume
  arm a 50ms threading.Timer (_schedule_agent_build) that outlives its
  test and fires into the NEXT test's _make_agent mock, racily
  corrupting captured state (the recurring session_resume shard
  failures). Replaced the per-test whack-a-mole stub with a module-wide
  autouse fixture; the 3 worker-lifecycle tests that genuinely need the
  deferred build opt back in via @pytest.mark.real_agent_prewarm (new
  marker in pyproject).
- test_api_key_providers.py: PROVIDER_ENV_VARS is now derived from the
  live PROVIDER_REGISTRY instead of a hand-list that had drifted
  (missing HF_TOKEN / DEEPINFRA_API_KEY) — resolve_provider('auto')
  tests failed on any machine with HF_TOKEN exported. E2E-verified with
  HF_TOKEN/DEEPINFRA_API_KEY set: 42/42 pass.

* test: de-flake 30 timing-sensitive test files for loaded CI runners

Root-cause fixes from the flake audit (session-DB mining + repo sweep):

Event-based sync instead of sleep-sync:
- title_generator: mock sets threading.Event, wait(10) replaces
  sleep(0.3) hoping the daemon thread got scheduled
- docker zombie_reaping / profile_gateway: poll-for-state helpers
  replace fixed 1-3s sleeps (s6 transitions + SIGCHLD reaping are async)
- process_registry tree test: select()-bounded readline replaces an
  unbounded blocking read (parent wedge now fails THIS test with a clear
  message instead of an opaque rc=124 file kill); SIGTERM grace 1s->2s
  (the 1s partition window mid-interpreter-startup is how a child PID
  escaped the live-system guard in CI)

Timeout raises (loaded 8-way-sliced runners see ~5s scheduling floors;
all of these complete in ms-to-1s when healthy so the raises cost
nothing on green runs):
- subprocess/thread waits <= 2s raised to 10-15s across mcp_tool,
  mcp_circuit_breaker, mcp_reconnect_retry_reset, mcp_parked_self_probe,
  mcp_cancelled_error_propagation, registry, clarify_gateway, interrupt,
  voice_cli_integration, docker_environment, session_store_lock_io,
  planned_stop_watcher, cli_interrupt_subagent, thread_scoped_output
  (joins now also assert not is_alive() so stragglers fail loudly)
- wall-clock discrimination ceilings loosened where the guarded hang is
  10x larger: local_background_child_hang 4s->10s, interrupt_cleanup
  setup 5s->20s + pgid-exit 30s->60s, mcp_stability grandchild spinup
  5s->15s, protocol/gil-starvation fast-handler 0.5s->2s,
  iso_certify_seam 1.5s->5s, wait_for_mcp_discovery 0.1s->1s
- narrow assertion windows widened: honcho first-turn wait 0.4..0.65 ->
  0.25..2.0 (property is bounded-not-hung, not an exact wall-clock);
  compression fork-lock TTL 1s->3s (12 refresh chances per lease);
  compression-lock expiry margins symmetric (ttl 0.05->0.5, sleep 1.0)
- telegram hung-DNS bound 1.0->1.4 (fake hang is 1.5s — must stay under)

* fix(tests): repair indentation from de-flake batch edit

* fix(tests): harden env isolation and replace remaining sleep-sync races

The full 42k-test run and complete npm check surfaced three more classes:

- Environment isolation: local ~/.honcho defaultHost and SSH_* variables
  leaked into Python/TUI tests. Pin the default Honcho host in the
  hermetic fixture, isolate the one fallback test from ~/.honcho, and
  blank SSH_* around terminalSetup tests. This flipped 20 false failures
  back to deterministic behavior on developer machines.
- Background-thread sleep-sync: Honcho async writer tests patched
  time.sleep globally, then busy-polled with that same mocked sleep. Under
  full-suite load the poller could starve the writer. Each test now waits
  on an Event emitted by the exact flush/retry transition; 30/30 passed
  under 15-way contention.
- Desktop streaming: the test slept 80ms and assumed a 500ms timer could
  not fire before its assertion. A loaded runner descheduled the test for
  >500ms and both chunks arrived. Producer controls now gate second-chunk
  and completion transitions explicitly.

Also make file-retry observability complete: a self-healed flaky file now
prints BOTH attempts' full output in the FLAKY summary. Two behavioral
runner tests prove pass-on-retry is green+loud+traceback-preserving, while
a deterministic failure remains red.

* refactor(ci): use gh bot pat, better retries

refactor(ci): use retry action for PR label fetch
the retry action now captures stdout as a step output, so it can serve
double duty: retry + output capture for commands like 'gh pr view' whose
result must be consumed by later steps.

Retry action gains:
- 'stdout' output (heredoc-delimited to preserve newlines)
- tee to temp file so stdout still streams to the job log
- step id 'retry' for output reference

Both lint.yml and supply-chain-audit.yml now use the retry action
directly with 'command: gh pr view ...' and read
steps.<id>.outputs.stdout.

ci: use AUTOFIX_BOT_PAT for all gh CLI / GitHub API auth

Replace secrets.GITHUB_TOKEN and github.token with
secrets.AUTOFIX_BOT_PAT across all workflows and composite actions
that use the gh CLI or GitHub API. The PAT has consistent permissions
across fork PRs (where GITHUB_TOKEN is read-only), avoids API rate
limit sharing with the default token, and is already used by
js-autofix.yml for the same reasons.

19 sites swapped across 9 files:
- lint.yml (3): label fetch, comment post/edit, comment update
- supply-chain-audit.yml (5): scan, critical comment, unbounded dep
  comment, label fetch, mcp-catalog comment
- lockfile-diff.yml (1): PR comment post/update
- skills-index-freshness.yml (1): issue creation on degraded probe
- skills-index.yml (2): index build, trigger deploy workflow
- upload_to_pypi.yml (2): release view poll, release upload
- ci.yml (1): timings report
- deploy-site.yml (2): skills index crawl
- detect-changes/action.yml (1): compare API call

---------

Co-authored-by: ethernet <arilotter@gmail.com>
2026-07-17 20:55:24 +00:00

585 lines
23 KiB
Python

"""Tests for agent.title_generator — auto-generated session titles."""
import pytest
from unittest.mock import MagicMock, patch
from agent.title_generator import (
generate_title,
auto_title_session,
maybe_auto_title,
_title_language,
)
from hermes_state import SessionDB
class TestGenerateTitle:
"""Unit tests for generate_title()."""
def test_returns_title_on_success(self):
mock_response = MagicMock()
mock_response.choices = [MagicMock()]
mock_response.choices[0].message.content = "Debugging Python Import Errors"
with patch("agent.title_generator.call_llm", return_value=mock_response):
title = generate_title("help me fix this import", "Sure, let me check...")
assert title == "Debugging Python Import Errors"
def test_default_prompt_matches_user_language(self):
mock_response = MagicMock()
mock_response.choices = [MagicMock()]
mock_response.choices[0].message.content = "Some Title"
with patch("agent.title_generator.call_llm", return_value=mock_response) as llm:
generate_title("質問です", "回答です")
system_prompt = llm.call_args.kwargs["messages"][0]["content"]
assert "same language the user is writing in" in system_prompt
def test_configured_language_pins_prompt(self):
mock_response = MagicMock()
mock_response.choices = [MagicMock()]
mock_response.choices[0].message.content = "Some Title"
with (
patch("agent.title_generator.call_llm", return_value=mock_response) as llm,
patch("agent.title_generator._title_language", return_value="Japanese"),
):
generate_title("hello", "hi")
system_prompt = llm.call_args.kwargs["messages"][0]["content"]
assert "Write the title in Japanese" in system_prompt
assert "same language the user" not in system_prompt
def test_title_language_reads_config(self):
cfg = {"auxiliary": {"title_generation": {"language": " French "}}}
with patch("hermes_cli.config.load_config", return_value=cfg):
assert _title_language() == "French"
with patch("hermes_cli.config.load_config", return_value={}):
assert _title_language() == ""
with patch("hermes_cli.config.load_config", side_effect=RuntimeError("bad config")):
assert _title_language() == ""
def test_default_timeout_delegates_to_auxiliary_config(self):
captured_kwargs = {}
def mock_call_llm(**kwargs):
captured_kwargs.update(kwargs)
resp = MagicMock()
resp.choices = [MagicMock()]
resp.choices[0].message.content = "Configured Timeout"
return resp
with patch("agent.title_generator.call_llm", side_effect=mock_call_llm):
assert generate_title("question", "answer") == "Configured Timeout"
assert captured_kwargs["task"] == "title_generation"
assert captured_kwargs["timeout"] is None
def test_explicit_timeout_still_overrides_config(self):
captured_kwargs = {}
def mock_call_llm(**kwargs):
captured_kwargs.update(kwargs)
resp = MagicMock()
resp.choices = [MagicMock()]
resp.choices[0].message.content = "Explicit Timeout"
return resp
with patch("agent.title_generator.call_llm", side_effect=mock_call_llm):
assert generate_title("question", "answer", timeout=123.0) == "Explicit Timeout"
assert captured_kwargs["timeout"] == 123.0
def test_strips_quotes(self):
mock_response = MagicMock()
mock_response.choices = [MagicMock()]
mock_response.choices[0].message.content = '"Setting Up Docker Environment"'
with patch("agent.title_generator.call_llm", return_value=mock_response):
title = generate_title("how do I set up docker", "First install...")
assert title == "Setting Up Docker Environment"
def test_strips_think_blocks(self):
"""Reasoning-model output wrapped in <think>...</think> must not
leak into the session title."""
mock_response = MagicMock()
mock_response.choices = [MagicMock()]
mock_response.choices[0].message.content = (
"<think>The user wants a title. I'll summarize the topic "
"concisely.</think>Debugging Python Import Errors"
)
with patch("agent.title_generator.call_llm", return_value=mock_response):
title = generate_title("help me fix this import", "Sure...")
assert title == "Debugging Python Import Errors"
assert "<think>" not in title
assert "summarize" not in title
def test_strips_unterminated_think_block(self):
"""An unterminated <think> block (no close tag) must still be
stripped so the leaked reasoning doesn't become the title."""
mock_response = MagicMock()
mock_response.choices = [MagicMock()]
mock_response.choices[0].message.content = (
"<think>Let me reason about a good title for this session"
)
with patch("agent.title_generator.call_llm", return_value=mock_response):
title = generate_title("hello", "hi there")
# Everything from the unterminated open tag onward is stripped,
# leaving nothing → None.
assert title is None
def test_strips_title_prefix(self):
mock_response = MagicMock()
mock_response.choices = [MagicMock()]
mock_response.choices[0].message.content = "Title: Kubernetes Pod Debugging"
with patch("agent.title_generator.call_llm", return_value=mock_response):
title = generate_title("my pod keeps crashing", "Let me look...")
assert title == "Kubernetes Pod Debugging"
def test_truncates_long_titles(self):
mock_response = MagicMock()
mock_response.choices = [MagicMock()]
mock_response.choices[0].message.content = "A" * 100
with patch("agent.title_generator.call_llm", return_value=mock_response):
title = generate_title("question", "answer")
assert len(title) == 80
assert title.endswith("...")
def test_returns_none_on_empty_response(self):
mock_response = MagicMock()
mock_response.choices = [MagicMock()]
mock_response.choices[0].message.content = ""
with patch("agent.title_generator.call_llm", return_value=mock_response):
assert generate_title("question", "answer") is None
def test_returns_none_on_exception(self):
with patch("agent.title_generator.call_llm", side_effect=RuntimeError("no provider")):
assert generate_title("question", "answer") is None
def test_invokes_failure_callback_on_exception(self):
"""failure_callback must fire so the user sees a warning (issue #15775)."""
captured = []
def _cb(task, exc):
captured.append((task, exc))
exc = RuntimeError("openrouter 402: credits exhausted")
with patch("agent.title_generator.call_llm", side_effect=exc):
result = generate_title("question", "answer", failure_callback=_cb)
assert result is None
assert len(captured) == 1
assert captured[0][0] == "title generation"
assert captured[0][1] is exc
def test_failure_callback_errors_are_swallowed(self):
"""A broken callback must not crash title generation."""
def _bad_cb(task, exc):
raise ValueError("callback bug")
with patch("agent.title_generator.call_llm", side_effect=RuntimeError("nope")):
# Should return None without re-raising the callback error
assert generate_title("q", "a", failure_callback=_bad_cb) is None
def test_no_callback_matches_legacy_behavior(self):
"""Omitting failure_callback preserves the silent-None return."""
with patch("agent.title_generator.call_llm", side_effect=RuntimeError("nope")):
assert generate_title("q", "a") is None
def test_truncates_long_messages(self):
"""Long user/assistant messages should be truncated in the LLM request."""
captured_kwargs = {}
def mock_call_llm(**kwargs):
captured_kwargs.update(kwargs)
resp = MagicMock()
resp.choices = [MagicMock()]
resp.choices[0].message.content = "Short Title"
return resp
with patch("agent.title_generator.call_llm", side_effect=mock_call_llm):
generate_title("x" * 1000, "y" * 1000)
# The user content in the messages should be truncated
user_content = captured_kwargs["messages"][1]["content"]
assert len(user_content) < 1100 # 500 + 500 + formatting
def test_skips_when_title_generation_disabled(self):
"""auxiliary.title_generation.enabled=false disables automatic titles."""
config = {"auxiliary": {"title_generation": {"enabled": False}}}
with (
patch("hermes_cli.config.load_config_readonly", return_value=config),
patch("agent.title_generator.call_llm") as mock_call_llm,
):
assert generate_title("question", "answer") is None
mock_call_llm.assert_not_called()
class TestAutoTitleSession:
"""Tests for auto_title_session() — the sync worker function."""
def test_skips_if_no_session_db(self):
auto_title_session(None, "sess-1", "hi", "hello") # should not crash
def test_skips_if_title_exists(self):
db = MagicMock()
db.get_session_title.return_value = "Existing Title"
with patch("agent.title_generator.generate_title") as gen:
auto_title_session(db, "sess-1", "hi", "hello")
gen.assert_not_called()
def test_generates_and_sets_title(self):
db = MagicMock()
db.get_session_title.return_value = None
db.set_auto_title_if_empty.return_value = True
with patch("agent.title_generator.generate_title", return_value="New Title"):
auto_title_session(db, "sess-1", "hi", "hello")
db.set_auto_title_if_empty.assert_called_once_with("sess-1", "New Title")
def test_does_not_overwrite_title_set_immediately_before_conditional_write(
self, tmp_path
):
db = SessionDB(tmp_path / "state.db")
db.create_session(session_id="sess-1", source="cli")
seen = []
def generate_after_manual_title(*_args, **_kwargs):
db.set_session_title("sess-1", "Manual Title")
return "Auto Title"
with patch(
"agent.title_generator.generate_title",
side_effect=generate_after_manual_title,
):
auto_title_session(
db,
"sess-1",
"hi",
"hello",
title_callback=seen.append,
)
assert db.get_session_title("sess-1") == "Manual Title"
assert seen == []
def test_invokes_title_callback_after_setting_title(self):
db = MagicMock()
db.get_session_title.return_value = None
db.set_auto_title_if_empty.return_value = True
seen = []
with patch("agent.title_generator.generate_title", return_value="Readable Session"):
auto_title_session(
db,
"sess-1",
"hello",
"hi there",
title_callback=seen.append,
)
db.set_auto_title_if_empty.assert_called_once_with("sess-1", "Readable Session")
assert seen == ["Readable Session"]
def test_skips_if_generation_fails(self):
db = MagicMock()
db.get_session_title.return_value = None
with patch("agent.title_generator.generate_title", return_value=None):
auto_title_session(db, "sess-1", "hi", "hello")
db.set_auto_title_if_empty.assert_not_called()
def test_never_raises_when_body_throws(self):
"""Daemon-thread target must swallow ALL exceptions (e.g. the
post-update stale-module ImportError) instead of spraying a raw
traceback into the terminal via the default threading excepthook."""
db = MagicMock()
db.get_session_title.return_value = None
with patch(
"agent.title_generator._auto_title_session",
side_effect=ImportError(
"cannot import name 'set_conversation_context' from 'agent.portal_tags'"
),
):
auto_title_session(db, "sess-1", "hi", "hello") # must not raise
def test_body_exception_routed_to_failure_callback(self):
db = MagicMock()
db.get_session_title.return_value = None
seen = []
boom = ImportError("stale module")
with patch("agent.title_generator._auto_title_session", side_effect=boom):
auto_title_session(
db,
"sess-1",
"hi",
"hello",
failure_callback=lambda task, exc: seen.append((task, exc)),
)
assert seen == [("title generation", boom)]
def test_failure_callback_errors_also_swallowed(self):
db = MagicMock()
db.get_session_title.return_value = None
def bad_cb(task, exc):
raise RuntimeError("callback itself broke")
with patch(
"agent.title_generator._auto_title_session",
side_effect=ImportError("stale module"),
):
auto_title_session(db, "sess-1", "hi", "hello", failure_callback=bad_cb)
class TestMaybeAutoTitle:
"""Tests for maybe_auto_title() — the fire-and-forget entry point."""
def test_skips_if_not_first_exchange(self):
"""Should not fire for conversations with more than 2 user messages."""
db = MagicMock()
history = [
{"role": "user", "content": "first"},
{"role": "assistant", "content": "response 1"},
{"role": "user", "content": "second"},
{"role": "assistant", "content": "response 2"},
{"role": "user", "content": "third"},
{"role": "assistant", "content": "response 3"},
]
with patch("agent.title_generator.auto_title_session") as mock_auto:
maybe_auto_title(db, "sess-1", "third", "response 3", history)
# Wait briefly for any thread to start
import time
time.sleep(0.1)
mock_auto.assert_not_called()
def test_fires_on_first_exchange(self):
"""Should fire a background thread for the first exchange."""
db = MagicMock()
db.get_session_title.return_value = None
history = [
{"role": "user", "content": "hello"},
{"role": "assistant", "content": "hi there"},
]
with patch("agent.title_generator.auto_title_session") as mock_auto:
import threading
called = threading.Event()
mock_auto.side_effect = lambda *a, **k: called.set()
maybe_auto_title(db, "sess-1", "hello", "hi there", history)
# Event-based wait: sleep-sync flaked when the daemon thread
# wasn't scheduled within the fixed nap on a loaded runner.
assert called.wait(timeout=10), "auto_title thread never ran"
mock_auto.assert_called_once_with(
db,
"sess-1",
"hello",
"hi there",
failure_callback=None,
main_runtime=None,
title_callback=None,
runtime_validator=None,
)
def test_skips_when_title_generation_disabled(self):
"""Disabled title generation should not even start the background worker."""
db = MagicMock()
history = [
{"role": "user", "content": "hello"},
{"role": "assistant", "content": "hi there"},
]
config = {"auxiliary": {"title_generation": {"enabled": False}}}
with (
patch("hermes_cli.config.load_config_readonly", return_value=config),
patch("agent.title_generator.auto_title_session") as mock_auto,
):
maybe_auto_title(db, "sess-1", "hello", "hi there", history)
mock_auto.assert_not_called()
def test_forwards_failure_callback_to_worker(self):
"""maybe_auto_title must forward failure_callback into the thread."""
db = MagicMock()
db.get_session_title.return_value = None
history = [
{"role": "user", "content": "hello"},
{"role": "assistant", "content": "hi there"},
]
def _cb(task, exc):
pass
with patch("agent.title_generator.auto_title_session") as mock_auto:
import threading
called = threading.Event()
mock_auto.side_effect = lambda *a, **k: called.set()
maybe_auto_title(db, "sess-1", "hello", "hi there", history, failure_callback=_cb)
assert called.wait(timeout=10), "auto_title thread never ran"
mock_auto.assert_called_once_with(
db,
"sess-1",
"hello",
"hi there",
failure_callback=_cb,
main_runtime=None,
title_callback=None,
runtime_validator=None,
)
def test_skips_if_no_response(self):
db = MagicMock()
maybe_auto_title(db, "sess-1", "hello", "", []) # empty response
def test_skips_if_no_session_db(self):
maybe_auto_title(None, "sess-1", "hello", "response", []) # no db
class TestAutoTitleDuplicateHandling:
"""Duplicate auto-title handling and not-found hardening (#50537)."""
def test_dedupes_duplicate_title_via_lineage(self):
db = MagicMock()
db.get_session_title.return_value = None
# Atomic write path: collision raises ValueError, retry persists.
db.set_auto_title_if_empty.side_effect = [ValueError("in use"), True]
db.get_next_title_in_lineage.return_value = "Debugging Import Error #2"
with patch(
"agent.title_generator.generate_title",
return_value="Debugging Import Error",
):
seen = []
auto_title_session(db, "sess-1", "hi", "hello", title_callback=seen.append)
db.get_next_title_in_lineage.assert_called_once_with("Debugging Import Error")
assert db.set_auto_title_if_empty.call_args_list[-1][0] == (
"sess-1",
"Debugging Import Error #2",
)
# callback fires with the actually-persisted (deduped) title
assert seen == ["Debugging Import Error #2"]
def test_dedupes_duplicate_title_via_lineage_legacy_store(self):
# Store without set_auto_title_if_empty: same dedup via the plain
# set_session_title fallback.
db = MagicMock(
spec=["get_session_title", "set_session_title", "get_next_title_in_lineage"]
)
db.get_session_title.return_value = None
db.set_session_title.side_effect = [ValueError("in use"), True]
db.get_next_title_in_lineage.return_value = "Debugging Import Error #2"
with patch(
"agent.title_generator.generate_title",
return_value="Debugging Import Error",
):
seen = []
auto_title_session(db, "sess-1", "hi", "hello", title_callback=seen.append)
assert db.set_session_title.call_args_list[-1][0] == (
"sess-1",
"Debugging Import Error #2",
)
assert seen == ["Debugging Import Error #2"]
def test_swallows_value_error_without_lineage_support(self):
# No get_next_title_in_lineage -> ValueError propagates out of the
# persist helper but auto_title_session still swallows it (no crash).
db = MagicMock(spec=["get_session_title", "set_session_title"])
db.get_session_title.return_value = None
db.set_session_title.side_effect = ValueError("in use")
with patch(
"agent.title_generator.generate_title", return_value="Dup Title"
):
auto_title_session(db, "sess-1", "hi", "hello") # must not raise
def test_manual_title_race_skips_without_callback(self):
# Atomic predicate fails (manual /title landed while generation was in
# flight) -> nothing persisted, no callback fired.
from agent.title_generator import _persist_session_title
db = MagicMock()
db.set_auto_title_if_empty.return_value = False
assert _persist_session_title(db, "sess-1", "Some Title") is None
db.set_session_title.assert_not_called()
def test_not_found_raises_runtime_error_internally(self):
# Legacy store (no atomic write): set_session_title returning False
# (session vanished) -> RuntimeError in the persist helper, swallowed
# by auto_title_session, no callback.
from agent.title_generator import _persist_session_title
db = MagicMock(spec=["get_session_title", "set_session_title"])
db.set_session_title.return_value = False
with pytest.raises(RuntimeError):
_persist_session_title(db, "missing", "Some Title")
class TestRuntimeValidator:
"""runtime_validator gating (#19027): a stale background title request
must not fire when the session's model/provider changed after spawn."""
def test_skips_when_validator_returns_false(self):
with patch("agent.title_generator.call_llm") as mock_llm:
title = generate_title(
"question", "answer",
runtime_validator=lambda: False,
)
assert title is None
mock_llm.assert_not_called()
def test_allows_when_validator_returns_true(self):
mock_response = MagicMock()
mock_response.choices = [MagicMock()]
mock_response.choices[0].message.content = "Validated Title"
with patch("agent.title_generator.call_llm", return_value=mock_response) as mock_llm:
title = generate_title(
"question", "answer",
runtime_validator=lambda: True,
)
assert title == "Validated Title"
mock_llm.assert_called_once()
def test_broken_validator_fails_open(self):
mock_response = MagicMock()
mock_response.choices = [MagicMock()]
mock_response.choices[0].message.content = "Resilient Title"
def _bad_validator():
raise RuntimeError("validator gone")
with patch("agent.title_generator.call_llm", return_value=mock_response) as mock_llm:
title = generate_title(
"question", "answer",
runtime_validator=_bad_validator,
)
assert title == "Resilient Title"
mock_llm.assert_called_once()
def test_forwards_runtime_validator_to_worker(self):
db = MagicMock()
db.get_session_title.return_value = None
history = [
{"role": "user", "content": "hello"},
{"role": "assistant", "content": "hi there"},
]
def _v():
return True
with patch("agent.title_generator.auto_title_session") as mock_auto:
import threading
called = threading.Event()
mock_auto.side_effect = lambda *a, **k: called.set()
maybe_auto_title(db, "sess-1", "hello", "hi there", history, runtime_validator=_v)
assert called.wait(timeout=10), "auto_title thread never ran"
kwargs = mock_auto.call_args.kwargs
assert kwargs["runtime_validator"] is _v