Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
39 commits
Select commit Hold shift + click to select a range
fe7a7de
spec: openspec init
TomCC7 Jun 4, 2026
76158b2
chore: revert change to doc folder
TomCC7 Jun 8, 2026
35c8b14
Merge branch 'main' into cc/feat/openspec
TomCC7 Jun 8, 2026
12d4346
Merge branch 'main' into cc/feat/openspec
TomCC7 Jun 10, 2026
6cd2fd3
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jun 12, 2026
45f7f73
Merge branch 'main' into cc/feat/openspec
TomCC7 Jun 15, 2026
86a600d
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jun 18, 2026
43fd853
Merge branch 'main' into cc/feat/openspec
TomCC7 Jun 20, 2026
8394a61
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jun 20, 2026
bae46c4
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jun 23, 2026
4cf815e
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jun 30, 2026
2c80dab
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jul 7, 2026
bc381cb
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jul 11, 2026
3a976da
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jul 14, 2026
4e25297
add mattskill
TomCC7 Jul 20, 2026
11f0d7f
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jul 23, 2026
9ffcd58
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jul 23, 2026
f873ddf
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jul 24, 2026
e87e93e
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jul 27, 2026
e689348
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jul 28, 2026
794e585
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Jul 29, 2026
cfa3e3a
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Aug 1, 2026
d221a4f
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Aug 4, 2026
df82a32
Merge remote-tracking branch 'origin/main' into cc/feat/openspec
TomCC7 Aug 5, 2026
f9f660a
feat: add frozen recording agent evaluation
TomCC7 Aug 5, 2026
a7b0c0f
[autofix.ci] apply automated fixes
autofix-ci[bot] Aug 5, 2026
405d250
refactor: simplify frozen agent evaluation
TomCC7 Aug 5, 2026
ca270d4
refactor: consolidate evaluation models
TomCC7 Aug 5, 2026
7430fb7
[autofix.ci] apply automated fixes
autofix-ci[bot] Aug 5, 2026
a11488d
feat: stream evaluation progress live
TomCC7 Aug 5, 2026
d963021
fix: reduce evaluation log noise
TomCC7 Aug 5, 2026
537c9f4
spec: remove
TomCC7 Aug 5, 2026
3fe0b2e
ci: drop dedicated Pi extension job
TomCC7 Aug 5, 2026
2555126
Merge branch 'main' into cc/feat/frozen-qa-eval
TomCC7 Aug 5, 2026
2805308
fix: harden frozen eval CI and caching
TomCC7 Aug 5, 2026
0166eec
Merge branch 'cc/feat/frozen-qa-eval' into cc/feat/agent-eval-standar…
TomCC7 Aug 8, 2026
c7f7c89
feat: standardize agent evaluation framework
TomCC7 Aug 8, 2026
7a8f1d0
Merge branch 'cc/feat/frozen-qa-eval' into cc/feat/agent-eval-standar…
TomCC7 Aug 8, 2026
be3ada0
spec: remove
TomCC7 Aug 8, 2026
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 2 additions & 3 deletions dimos/agents/code_policy_server.py
Original file line number Diff line number Diff line change
Expand Up @@ -33,9 +33,8 @@

PYTHON_EXEC_DESCRIPTION = """Execute Python in a persistent trusted, unsandboxed session.

The frozen evaluation session exposes read-only `memory`. Imports, functions, and
variables persist between calls. Use this tool to inspect the recording and compute
the answer; do not guess from the prompt.
Imports, functions, and variables persist between calls. The runtime environment
determines which globals are available.
"""

_NOISY_MCP_TRANSPORT_LOGGERS = (
Expand Down
113 changes: 0 additions & 113 deletions dimos/benchmark/agent_eval/models.py

This file was deleted.

221 changes: 0 additions & 221 deletions dimos/benchmark/agent_eval/single_case.py

This file was deleted.

Loading
Loading