Commit graph

6 commits

Author SHA1 Message Date
teknium1
5de42325db test: expect model slug in autoraise notice dict (follow-up to gpt-5.4 extension) 2026-07-06 12:46:20 -07:00
AIalliAI
60391d0eef fix(agent): don't apply Codex gpt-5.5 autoraise notice when an external context engine is active
When context.engine selects a plugin engine (e.g. LCM), the host
compression threshold — including the Codex gpt-5.5 50% -> 85%
autoraise — only configures the built-in ContextCompressor and never
reaches the plugin. The autoraise notice still fired, telling the user
auto-compaction was raised when nothing actually changed, and the
startup context-limit line printed the host percent next to the
engine's own threshold_tokens, contradicting itself.

- Clear _compression_threshold_autoraised when a plugin engine is
  selected, suppressing both the CLI startup notice and the gateway
  turn-1 replay via _compression_warning.
- Print the active engine's own threshold_percent in the startup
  context-limit line so percent and token count agree.
- Built-in behavior is preserved, including the fallback path where a
  configured engine fails to load and the built-in compressor takes
  over.

Fixes #44439
2026-07-06 12:46:20 -07:00
Stephen Schoettler
8595281f3c fix: expose context engine tools with saved toolsets 2026-05-28 00:28:42 -07:00
0z1-ghb
8b2adead78 fix(compressor): ABC compliance — total_tokens, api_mode, logger consistency 2026-05-23 17:38:19 -07:00
Teknium
d0e1388ca9
fix(tests): make AIAgent constructor calls self-contained (#11755)
* fix(tests): make AIAgent constructor calls self-contained (no env leakage)

Tests in tests/run_agent/ were constructing AIAgent() without passing
both api_key and base_url, then relying on leaked state from other
tests in the same xdist worker (or process-level env vars) to keep
provider resolution happy. Under hermetic conftest + pytest-split,
that state is gone and the tests fail with 'No LLM provider configured'.

Fix: pass both api_key and base_url explicitly on 47 AIAgent()
construction sites across 13 files. AIAgent.__init__ with both set
takes the direct-construction path (line 960 in run_agent.py) and
skips the resolver entirely.

One call site (test_none_base_url_passed_as_none) left alone — that
test asserts behavior for base_url=None specifically.

This is a prerequisite for any future matrix-split or stricter
isolation work, and lands cleanly on its own.

Validation:
- tests/run_agent/ full: 760 passed, 0 failed (local)
- Previously relied on cross-test pollution; now self-contained

* fix(tests): update opencode-go model order assertion to match kimi-k2.5-first

commit 78a74bb promoted kimi-k2.5 to first position in model suggestion
lists but didn't update this test, which has been failing on main since.
Reorder expected list to match the new canonical order.
2026-04-17 12:32:03 -07:00
Teknium
063244bb16 test: add coverage for plugin context engine init (#9071)
Verify that plugin context engines receive update_model() with correct
context_length during AIAgent init — regression test for the ctx -- bug.
2026-04-13 15:00:57 -07:00