From c7017a476de20cb15c1f7a3fd39efb4904e29e0c Mon Sep 17 00:00:00 2001
From: shenzhennan <1641225799szn@gmail.com>
Date: Fri, 18 Jul 2025 07:14:35 +0000
Subject: [PATCH 1/3] fix impress instruction 0a211154

---
 .../0a211154-fda0-48d0-9274-eaac4ce5486d.json                   | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/evaluation_examples/examples/libreoffice_impress/0a211154-fda0-48d0-9274-eaac4ce5486d.json b/evaluation_examples/examples/libreoffice_impress/0a211154-fda0-48d0-9274-eaac4ce5486d.json
index c98378a..5f400f5 100644
--- a/evaluation_examples/examples/libreoffice_impress/0a211154-fda0-48d0-9274-eaac4ce5486d.json
+++ b/evaluation_examples/examples/libreoffice_impress/0a211154-fda0-48d0-9274-eaac4ce5486d.json
@@ -1,7 +1,7 @@
 {
   "id": "0a211154-fda0-48d0-9274-eaac4ce5486d",
   "snapshot": "libreoffice_impress",
-  "instruction": "Set the background color of slides with a real person picture as yellow and set the title of slide 2 as \"Let's start\".",
+  "instruction": "Set the background color to yellow for any slide that contains one or more images of real people, and set the title of slide 2 as \"Let's start\".",
   "source": "https://arxiv.org/pdf/2311.01767.pdf",
   "config": [
     {

From 7fb1cee5757cc57940a34f44a4e6b4892a695e27 Mon Sep 17 00:00:00 2001
From: Zilong Zhou <zzl0712@connect.hku.hk>
Date: Fri, 18 Jul 2025 19:52:03 +0800
Subject: [PATCH 2/3] fix: img path error (#271)

* feat&style: add task status configuration and clear cache functionality; enhance UI styles

* feat&refactor: enhance current configuration API and improve cache clearing logic

* refactor&style: simplify task status update logic and improve page refresh mechanism

* refactor&feat: streamline default configuration retrieval and enhance cache initialization logic

* feat&refactor: add caching to default configuration retrieval and streamline task status logic

* feat&style: add collapsible section for additional model parameters and enhance styling for config items

* refactor&style: remove floating action button and clean up related styles

* fix: update video and screenshot sources to include action space, observation type, and model name parameters
---
 monitor/templates/task_detail.html | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/monitor/templates/task_detail.html b/monitor/templates/task_detail.html
index 4bf6f95..ced6f52 100644
--- a/monitor/templates/task_detail.html
+++ b/monitor/templates/task_detail.html
@@ -73,7 +73,7 @@
                     <div class="video-player">
                         <video id="task-recording" controls playsinline webkit-playsinline
                                preload="metadata" width="100%" controlslist="nodownload">
-                            <source src="/task/{{ task_type }}/{{ task_id }}/recording" type="video/mp4">
+                            <source src="/task/{{ task_type }}/{{ task_id }}/recording?action_space={{ action_space }}&observation_type={{ observation_type }}&model_name={{ model_name }}" type="video/mp4">
                             Your browser does not support the video tag.
                         </video>
                         <div id="video-status" class="video-status">Loading video...</div>
@@ -103,7 +103,7 @@
                             {% endif %}</pre>
                             {% if step.screenshot_file %}
                                 <div>
-                                    <img src="/task/{{ task_type }}/{{ task_id }}/screenshot/{{ step.screenshot_file }}" 
+                                    <img src="/task/{{ task_type }}/{{ task_id }}/screenshot/{{ step.screenshot_file }}?action_space={{ action_space }}&observation_type={{ observation_type }}&model_name={{ model_name }}" 
                                             alt="Step {{ step.step_num }} Screenshot" class="step-image">
                                 </div>
                             {% endif %}
@@ -155,7 +155,7 @@
                 }, 2000);
                 
                 // Directly check video source availability with fetch API
-                fetch('/task/{{ task_type }}/{{ task_id }}/recording', {method: 'HEAD'})
+                fetch('/task/{{ task_type }}/{{ task_id }}/recording?action_space={{ action_space }}&observation_type={{ observation_type }}&model_name={{ model_name }}', {method: 'HEAD'})
                     .then(function(response) {
                         if (response.ok && videoStatus.textContent === 'Loading video...') {
                             // If HEAD request succeeds but video events haven't fired

From 53ffc05042a52a7eaa0b5be30a3d2132d6837cc2 Mon Sep 17 00:00:00 2001
From: Danyang Zhang <zdy004007@126.com>
Date: Fri, 18 Jul 2025 21:28:48 +0800
Subject: [PATCH 3/3] Calc eval fix (#272)

* ver Jun17th

updating annotations

* ver Jun17th

corrected annotation of 1d17
added check for cell merge

* ver Jun17th

updated several annotations

* ver Jun20th

fixed set-up config of 2bd59342-0664-4ccb-ba87-79379096cc08

* fix: Enhance instructions in LibreOffice Calc examples for clarity and specificity, including details on using Pivot Tables, column placements, and revenue calculations.

* ver Jun21st

updating calc evals

* ver Jun22nd

fixed an impress task

* ver Jun22ndv2

adjusted several calc tasks

* Clean scalfolds

* ver Jul18th

added two try-excepts to handle possible formula parsing and calculation
failures

---------

Co-authored-by: BowenBryanWang <bryanwang.nlp@connect.hku.hk>
Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
---
 desktop_env/evaluators/metrics/utils.py        | 18 ++++++++++++++----
 .../01b269ae-2111-4a07-81fd-3fcd711993b0.json  |  2 +-
 .../0326d92d-d218-48a8-9ca1-981cd6d064c7.json  |  2 +-
 .../035f41ba-6653-43ab-aa63-c86d449d62e5.json  |  2 +-
 .../04d9aeaf-7bed-4024-bedb-e10e6f00eb7f.json  |  2 +-
 .../0bf05a7d-b28b-44d2-955a-50b41e24012a.json  |  2 +-
 .../0cecd4f3-74de-457b-ba94-29ad6b5dafb6.json  |  2 +-
 .../1d17d234-e39d-4ed7-b46f-4417922a4e7c.json  |  2 +-
 .../26a8440e-c166-4c50-aef4-bfb77314b46b.json  |  2 +-
 .../2bd59342-0664-4ccb-ba87-79379096cc08.json  |  2 +-
 .../347ef137-7eeb-4c80-a3bb-0951f26a8aff.json  |  2 +-
 .../535364ea-05bd-46ea-9937-9f55c68507e8.json  |  2 +-
 .../aa3a8974-2e85-438b-b29e-a64df44deb4b.json  |  2 +-
 .../eb03d19a-b88d-4de4-8a64-ca0ac66f426b.json  |  2 +-
 .../ecb0df7a-4e8d-4a03-b162-053391d3afaf.json  |  2 +-
 .../f9584479-3d0d-4c79-affa-9ad7afdd8850.json  |  2 +-
 .../af2d657a-e6b3-4c6a-9f67-9e3ed015974c.json  |  2 +-
 .../82e3c869-49f6-4305-a7ce-f3e64a0618e7.json  |  2 +-
 .../869de13e-bef9-4b91-ba51-f6708c40b096.json  |  2 +-
 19 files changed, 32 insertions(+), 22 deletions(-)

diff --git a/desktop_env/evaluators/metrics/utils.py b/desktop_env/evaluators/metrics/utils.py
index 1136655..c3280eb 100644
--- a/desktop_env/evaluators/metrics/utils.py
+++ b/desktop_env/evaluators/metrics/utils.py
@@ -459,7 +459,11 @@ def load_xlsx_styles(xlsx_file: Workbook, sheet_name: str, book_name: str, **opt
         for r in fmt.rules:
             active_cells: List[Cell] = []
             if r.type == "expression":
-                condition: Callable[[str], bool] = formula_parser.ast("=" + r.formula[0])[1].compile()
+                try:
+                    condition: Callable[[str], bool] = formula_parser.ast("=" + r.formula[0])[1].compile()
+                except:
+                    logger.exception("Formula parsing error: %s. Skipping.", repr(r.formula[0]))
+                    continue
                 logger.debug("Expression condition: %s", r.formula[0])
 
                 arguments: List[Any] = []
@@ -493,9 +497,15 @@ def load_xlsx_styles(xlsx_file: Workbook, sheet_name: str, book_name: str, **opt
                             if nb_contiguous_nothings>50:
                                 break
                             continue
-                        elif condition(cell_value, *arguments):
-                            logger.debug("Active Cell %s(%s) for %s", repr(cell), str(cell_value), r.formula[0])
-                            active_cells.append(cell)
+                        else:
+                            try:
+                                satisfies_condition: bool = condition(cell_value, *arguments)
+                            except:
+                                logger.exception("Error in formula calculation with cell value %d", repr(cell_value))
+                                satisfies_condition = False
+                            if satisfies_condition:
+                                logger.debug("Active Cell %s(%s) for %s", repr(cell), repr(cell_value), r.formula[0])
+                                active_cells.append(cell)
             else:
                 raise NotImplementedError("Not Implemented Condition Type: {:}".format(r.type))
 
diff --git a/evaluation_examples/examples/libreoffice_calc/01b269ae-2111-4a07-81fd-3fcd711993b0.json b/evaluation_examples/examples/libreoffice_calc/01b269ae-2111-4a07-81fd-3fcd711993b0.json
index 0d169d5..b68f9a6 100644
--- a/evaluation_examples/examples/libreoffice_calc/01b269ae-2111-4a07-81fd-3fcd711993b0.json
+++ b/evaluation_examples/examples/libreoffice_calc/01b269ae-2111-4a07-81fd-3fcd711993b0.json
@@ -82,4 +82,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/0326d92d-d218-48a8-9ca1-981cd6d064c7.json b/evaluation_examples/examples/libreoffice_calc/0326d92d-d218-48a8-9ca1-981cd6d064c7.json
index 144be86..804a060 100644
--- a/evaluation_examples/examples/libreoffice_calc/0326d92d-d218-48a8-9ca1-981cd6d064c7.json
+++ b/evaluation_examples/examples/libreoffice_calc/0326d92d-d218-48a8-9ca1-981cd6d064c7.json
@@ -91,4 +91,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/035f41ba-6653-43ab-aa63-c86d449d62e5.json b/evaluation_examples/examples/libreoffice_calc/035f41ba-6653-43ab-aa63-c86d449d62e5.json
index db50cf5..f2fe2a6 100644
--- a/evaluation_examples/examples/libreoffice_calc/035f41ba-6653-43ab-aa63-c86d449d62e5.json
+++ b/evaluation_examples/examples/libreoffice_calc/035f41ba-6653-43ab-aa63-c86d449d62e5.json
@@ -87,4 +87,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f.json b/evaluation_examples/examples/libreoffice_calc/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f.json
index 7cd054c..c38131c 100644
--- a/evaluation_examples/examples/libreoffice_calc/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f.json
+++ b/evaluation_examples/examples/libreoffice_calc/04d9aeaf-7bed-4024-bedb-e10e6f00eb7f.json
@@ -82,4 +82,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/0bf05a7d-b28b-44d2-955a-50b41e24012a.json b/evaluation_examples/examples/libreoffice_calc/0bf05a7d-b28b-44d2-955a-50b41e24012a.json
index 72a968f..73e3b8f 100644
--- a/evaluation_examples/examples/libreoffice_calc/0bf05a7d-b28b-44d2-955a-50b41e24012a.json
+++ b/evaluation_examples/examples/libreoffice_calc/0bf05a7d-b28b-44d2-955a-50b41e24012a.json
@@ -109,4 +109,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/0cecd4f3-74de-457b-ba94-29ad6b5dafb6.json b/evaluation_examples/examples/libreoffice_calc/0cecd4f3-74de-457b-ba94-29ad6b5dafb6.json
index f0b43f1..106315c 100644
--- a/evaluation_examples/examples/libreoffice_calc/0cecd4f3-74de-457b-ba94-29ad6b5dafb6.json
+++ b/evaluation_examples/examples/libreoffice_calc/0cecd4f3-74de-457b-ba94-29ad6b5dafb6.json
@@ -95,4 +95,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/1d17d234-e39d-4ed7-b46f-4417922a4e7c.json b/evaluation_examples/examples/libreoffice_calc/1d17d234-e39d-4ed7-b46f-4417922a4e7c.json
index 3c964fa..4149a06 100644
--- a/evaluation_examples/examples/libreoffice_calc/1d17d234-e39d-4ed7-b46f-4417922a4e7c.json
+++ b/evaluation_examples/examples/libreoffice_calc/1d17d234-e39d-4ed7-b46f-4417922a4e7c.json
@@ -176,4 +176,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/26a8440e-c166-4c50-aef4-bfb77314b46b.json b/evaluation_examples/examples/libreoffice_calc/26a8440e-c166-4c50-aef4-bfb77314b46b.json
index a150c9c..e3122f9 100644
--- a/evaluation_examples/examples/libreoffice_calc/26a8440e-c166-4c50-aef4-bfb77314b46b.json
+++ b/evaluation_examples/examples/libreoffice_calc/26a8440e-c166-4c50-aef4-bfb77314b46b.json
@@ -82,4 +82,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/2bd59342-0664-4ccb-ba87-79379096cc08.json b/evaluation_examples/examples/libreoffice_calc/2bd59342-0664-4ccb-ba87-79379096cc08.json
index aa074c4..c915953 100644
--- a/evaluation_examples/examples/libreoffice_calc/2bd59342-0664-4ccb-ba87-79379096cc08.json
+++ b/evaluation_examples/examples/libreoffice_calc/2bd59342-0664-4ccb-ba87-79379096cc08.json
@@ -32,4 +32,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/347ef137-7eeb-4c80-a3bb-0951f26a8aff.json b/evaluation_examples/examples/libreoffice_calc/347ef137-7eeb-4c80-a3bb-0951f26a8aff.json
index d87d82b..df7eeab 100644
--- a/evaluation_examples/examples/libreoffice_calc/347ef137-7eeb-4c80-a3bb-0951f26a8aff.json
+++ b/evaluation_examples/examples/libreoffice_calc/347ef137-7eeb-4c80-a3bb-0951f26a8aff.json
@@ -91,4 +91,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/535364ea-05bd-46ea-9937-9f55c68507e8.json b/evaluation_examples/examples/libreoffice_calc/535364ea-05bd-46ea-9937-9f55c68507e8.json
index 5a03d94..4592c67 100644
--- a/evaluation_examples/examples/libreoffice_calc/535364ea-05bd-46ea-9937-9f55c68507e8.json
+++ b/evaluation_examples/examples/libreoffice_calc/535364ea-05bd-46ea-9937-9f55c68507e8.json
@@ -88,4 +88,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/aa3a8974-2e85-438b-b29e-a64df44deb4b.json b/evaluation_examples/examples/libreoffice_calc/aa3a8974-2e85-438b-b29e-a64df44deb4b.json
index 8ba693a..c27a27d 100644
--- a/evaluation_examples/examples/libreoffice_calc/aa3a8974-2e85-438b-b29e-a64df44deb4b.json
+++ b/evaluation_examples/examples/libreoffice_calc/aa3a8974-2e85-438b-b29e-a64df44deb4b.json
@@ -61,4 +61,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/eb03d19a-b88d-4de4-8a64-ca0ac66f426b.json b/evaluation_examples/examples/libreoffice_calc/eb03d19a-b88d-4de4-8a64-ca0ac66f426b.json
index 2e616fb..e9ea661 100644
--- a/evaluation_examples/examples/libreoffice_calc/eb03d19a-b88d-4de4-8a64-ca0ac66f426b.json
+++ b/evaluation_examples/examples/libreoffice_calc/eb03d19a-b88d-4de4-8a64-ca0ac66f426b.json
@@ -82,4 +82,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/ecb0df7a-4e8d-4a03-b162-053391d3afaf.json b/evaluation_examples/examples/libreoffice_calc/ecb0df7a-4e8d-4a03-b162-053391d3afaf.json
index bd95ca4..b254536 100644
--- a/evaluation_examples/examples/libreoffice_calc/ecb0df7a-4e8d-4a03-b162-053391d3afaf.json
+++ b/evaluation_examples/examples/libreoffice_calc/ecb0df7a-4e8d-4a03-b162-053391d3afaf.json
@@ -109,4 +109,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_calc/f9584479-3d0d-4c79-affa-9ad7afdd8850.json b/evaluation_examples/examples/libreoffice_calc/f9584479-3d0d-4c79-affa-9ad7afdd8850.json
index 63a9c16..7cfcb77 100644
--- a/evaluation_examples/examples/libreoffice_calc/f9584479-3d0d-4c79-affa-9ad7afdd8850.json
+++ b/evaluation_examples/examples/libreoffice_calc/f9584479-3d0d-4c79-affa-9ad7afdd8850.json
@@ -82,4 +82,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/libreoffice_impress/af2d657a-e6b3-4c6a-9f67-9e3ed015974c.json b/evaluation_examples/examples/libreoffice_impress/af2d657a-e6b3-4c6a-9f67-9e3ed015974c.json
index 04e388b..2e8f445 100644
--- a/evaluation_examples/examples/libreoffice_impress/af2d657a-e6b3-4c6a-9f67-9e3ed015974c.json
+++ b/evaluation_examples/examples/libreoffice_impress/af2d657a-e6b3-4c6a-9f67-9e3ed015974c.json
@@ -83,4 +83,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7.json b/evaluation_examples/examples/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7.json
index c58e773..0171168 100644
--- a/evaluation_examples/examples/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7.json
+++ b/evaluation_examples/examples/multi_apps/82e3c869-49f6-4305-a7ce-f3e64a0618e7.json
@@ -112,4 +112,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}
diff --git a/evaluation_examples/examples/multi_apps/869de13e-bef9-4b91-ba51-f6708c40b096.json b/evaluation_examples/examples/multi_apps/869de13e-bef9-4b91-ba51-f6708c40b096.json
index 81411cf..0a12b5f 100644
--- a/evaluation_examples/examples/multi_apps/869de13e-bef9-4b91-ba51-f6708c40b096.json
+++ b/evaluation_examples/examples/multi_apps/869de13e-bef9-4b91-ba51-f6708c40b096.json
@@ -168,4 +168,4 @@
   "proxy": false,
   "fixed_ip": false,
   "possibility_of_env_change": "low"
-}
\ No newline at end of file
+}