Update model catalog descriptions and GPT-5.6-Sol priority (#47085)

## What changed

- Describe GPT-5.6-Sol as a reliable agentic workhorse for everyday tasks and change its catalog `priority` from `6` to `4`.
- Describe GPT-5.5 as a proven previous-generation model for coding and general work.
- Refresh model picker, migration prompt, and agent tool snapshots to reflect the catalog updates.

GitOrigin-RevId: b39f51c22862b8cef585ed76f3973c9f4b670c27
This commit is contained in:
andrewgu-oai
2026-09-21 18:36:13 +00:00
committed by copyberry
parent 3627bb91b2
commit deb0a08f24
14 changed files with 35 additions and 35 deletions
@@ -7,7 +7,7 @@ Scenario: Astra asks who a launch update is for, keeps working, and receives the
## Window 1
-- request 1 (request) --
00:additional_tools/developer (3; hash=9e8e744a3a55a2dd):
00:additional_tools/developer (3; hash=825e6e666716b523):
- namespace/functions; hash=e7db0a45c4ec3157
- custom/exec
- function/wait
@@ -15,7 +15,7 @@ Scenario: Astra asks who a launch update is for, keeps working, and receives the
- function/request_user_input_async
- namespace/clock: Tools for reading and waiting on time.; hash=f402e8c5e9b5e317
- function/sleep
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=91f6de0e2773854f
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b25b153d1e4097db
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -6,7 +6,7 @@ Scenario: Astra receives host and handler timings on completed and failed code-m
## Window 1
-- request 1 (turn) --
00:additional_tools/developer (3; hash=9e8e744a3a55a2dd):
00:additional_tools/developer (3; hash=825e6e666716b523):
- namespace/functions; hash=e7db0a45c4ec3157
- custom/exec
- function/wait
@@ -14,7 +14,7 @@ Scenario: Astra receives host and handler timings on completed and failed code-m
- function/request_user_input_async
- namespace/clock: Tools for reading and waiting on time.; hash=f402e8c5e9b5e317
- function/sleep
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=91f6de0e2773854f
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b25b153d1e4097db
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -16,7 +16,7 @@ Settings:
text: {"verbosity":"low"}
tool_choice: "auto"
-- request 1 (request) --
00:additional_tools/developer (3; hash=1a25ddd32492d564):
00:additional_tools/developer (3; hash=e95d648e9a532330):
- namespace/functions; hash=99a630cff25563aa
- custom/exec
- function/wait
@@ -24,7 +24,7 @@ Settings:
- function/request_user_input_async
- namespace/clock: Tools for reading and waiting on time.; hash=f402e8c5e9b5e317
- function/sleep
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=91f6de0e2773854f
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b25b153d1e4097db
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -16,7 +16,7 @@ Settings:
text: {"verbosity":"low"}
tool_choice: "auto"
-- request 1 (turn) --
00:additional_tools/developer (3; hash=9e8e744a3a55a2dd):
00:additional_tools/developer (3; hash=825e6e666716b523):
- namespace/functions; hash=e7db0a45c4ec3157
- custom/exec
- function/wait
@@ -24,7 +24,7 @@ Settings:
- function/request_user_input_async
- namespace/clock: Tools for reading and waiting on time.; hash=f402e8c5e9b5e317
- function/sleep
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=91f6de0e2773854f
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b25b153d1e4097db
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -190,7 +190,7 @@ Settings:
## Window 2 (after request 3: input diverged at item 02)
Settings: same as window 1
-- request 4 (turn) --
00:additional_tools/developer (3; hash=9e8e744a3a55a2dd):
00:additional_tools/developer (3; hash=825e6e666716b523):
- namespace/functions; hash=e7db0a45c4ec3157
- custom/exec
- function/wait
@@ -198,7 +198,7 @@ Settings: same as window 1
- function/request_user_input_async
- namespace/clock: Tools for reading and waiting on time.; hash=f402e8c5e9b5e317
- function/sleep
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=91f6de0e2773854f
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b25b153d1e4097db
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -16,7 +16,7 @@ Settings:
text: {"verbosity":"low"}
tool_choice: "auto"
-- request 1 (turn) --
00:additional_tools/developer (3; hash=9e8e744a3a55a2dd):
00:additional_tools/developer (3; hash=825e6e666716b523):
- namespace/functions; hash=e7db0a45c4ec3157
- custom/exec
- function/wait
@@ -24,7 +24,7 @@ Settings:
- function/request_user_input_async
- namespace/clock: Tools for reading and waiting on time.; hash=f402e8c5e9b5e317
- function/sleep
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=91f6de0e2773854f
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b25b153d1e4097db
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -113,7 +113,7 @@ Settings:
## Window 2 (after request 2: input diverged at item 00)
Settings: same as window 1
-- request 3 (turn) --
00:additional_tools/developer (3; hash=d9bfc9d2033f8c93):
00:additional_tools/developer (3; hash=25b91d5f1c37c5f9):
- namespace/functions; hash=8c17932a39355f2d
- custom/exec
- function/wait
@@ -121,7 +121,7 @@ Settings: same as window 1
- function/request_user_input_async
- namespace/clock: Tools for reading and waiting on time.; hash=f402e8c5e9b5e317
- function/sleep
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=91f6de0e2773854f
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b25b153d1e4097db
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -16,7 +16,7 @@ Settings:
text: {"verbosity":"low"}
tool_choice: "auto"
-- request 1 (turn) --
00:additional_tools/developer (3; hash=d9bfc9d2033f8c93):
00:additional_tools/developer (3; hash=25b91d5f1c37c5f9):
- namespace/functions; hash=8c17932a39355f2d
- custom/exec
- function/wait
@@ -24,7 +24,7 @@ Settings:
- function/request_user_input_async
- namespace/clock: Tools for reading and waiting on time.; hash=f402e8c5e9b5e317
- function/sleep
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=91f6de0e2773854f
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b25b153d1e4097db
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -16,7 +16,7 @@ Settings:
text: {"verbosity":"low"}
tool_choice: "auto"
-- request 1 (turn) --
00:additional_tools/developer (3; hash=9d21738c014fb8eb):
00:additional_tools/developer (3; hash=72183a6fa8c2af41):
- namespace/functions; hash=e7db0a45c4ec3157
- custom/exec
- function/wait
@@ -24,7 +24,7 @@ Settings:
- function/request_user_input_async
- namespace/clock: Tools for reading and waiting on time.; hash=f402e8c5e9b5e317
- function/sleep
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=2943c667577fdb8b
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=fae5bb2424ee5d1f
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -16,7 +16,7 @@ Settings:
stream: true
text: {"verbosity":"low"}
tool_choice: "auto"
tools (11; hash=b74b49b673a090be):
tools (11; hash=84acbd4e08522132):
- function/exec_command: Runs a command in a PTY, returning output or a session ID for ongoing interaction.; args=[cmd, justification, login, max_output_tokens, prefix_rule, sandbox_permissions, shell, tty, workdir, yield_time_ms]; hash=c04108e51a8548c5
- function/write_stdin: Writes characters to an existing unified exec session and returns recent output.; args=[chars, max_output_tokens, session_id, yield_time_ms]; hash=7fb62d8a3e2df4e2
- function/list_mcp_resources: Lists resources provided by MCP servers. Resources allow servers to share data that provides cont...; args=[cursor, server]; hash=6792edaff13561bd
@@ -25,7 +25,7 @@ Settings:
- function/request_user_input: Request user input for one to three short questions and wait for the response. This tool is only ...; args=[questions]; hash=64a729b25c424fc6
- custom/apply_patch: The `apply_patch` tool can be used to edit files. This is a FREEFORM tool, so do not wrap the pat...; hash=dea9f12b0111a4ba
- function/view_image: View a local image file from the filesystem when visual inspection is needed. Use this for images...; args=[detail, path]; hash=3b766d5bdec5d50e
- namespace/multi_agent_v1: Tools for spawning and managing sub-agents.; hash=f2a2334f757ddd80
- namespace/multi_agent_v1: Tools for spawning and managing sub-agents.; hash=ff41b44574c58be4
- function/close_agent
- function/resume_agent
- function/send_input
File diff suppressed because one or more lines are too long
@@ -6,6 +6,6 @@ Codex just got an upgrade. Introducing GPT-5.5.
We recommend switching from gpt-5.2 to gpt-5.5.
Frontier model for complex coding, research, and real-world work.
Proven previous-generation model for coding and general work.
You can continue using gpt-5.2 if you prefer.
@@ -6,11 +6,11 @@ expression: "render_bottom_popup(&chat, 100)"
Select Model and Effort
› 1. GPT-5.6 Sol (current) Latest frontier agentic coding model.
› 1. GPT-5.6 Sol (current) Reliable agentic workhorse for everyday tasks.
2. GPT-6-Astra Our most capable model for complex, demanding work.
3. GPT-5.6 Terra Balanced agentic coding model for everyday work.
4. GPT-5.6 Luna Fast and affordable agentic coding model.
5. GPT-5.5 Frontier model for complex coding, research, and real-world work.
5. GPT-5.5 Proven previous-generation model for coding and general work.
6. GPT-5.4 Strong model for everyday coding.
enter select · esc back
@@ -6,11 +6,11 @@ expression: "render_bottom_popup(&chat, 100)"
Select Model and Effort
› 1. GPT-5.6 Sol (Global) (current) Latest frontier agentic coding model.
› 1. GPT-5.6 Sol (Global) (current) Reliable agentic workhorse for everyday tasks.
2. GPT-6-Astra (Global) Our most capable model for complex, demanding work.
3. GPT-5.6 Terra (Global) Balanced agentic coding model for everyday work.
4. GPT-5.6 Luna (Global) Fast and affordable agentic coding model.
5. GPT-5.6 Sol (US cross-region) Latest frontier agentic coding model.
5. GPT-5.6 Sol (US cross-region) Reliable agentic workhorse for everyday tasks.
6. GPT-6-Astra (US cross-region) Our most capable model for complex, demanding work.
7. GPT-5.6 Terra (US cross-region) Balanced agentic coding model for everyday work.
8. GPT-5.6 Luna (US cross-region) Fast and affordable agentic coding model.
@@ -1,6 +1,6 @@
---
source: tui/src/chatwidget/tests/popups_and_settings.rs
assertion_line: 3465
assertion_line: 3466
expression: "render_bottom_popup(&chat, 80)"
---
Select Model and Effort
@@ -8,7 +8,7 @@ expression: "render_bottom_popup(&chat, 80)"
› 1. Renamed model Balanced agentic coding model for everyday
work.
2. Shared display name (current) Frontier model for complex coding, research,
and real-world work.
2. Shared display name (current) Proven previous-generation model for coding
and general work.
enter select · esc back
@@ -1,16 +1,16 @@
---
source: tui/src/chatwidget/tests/popups_and_settings.rs
assertion_line: 3309
assertion_line: 3310
expression: popup
---
Select Model and Effort
1. GPT-6-Astra (default) Our most capable model for complex, demanding work.
2. GPT-5.6-Sol Latest frontier agentic coding model.
2. GPT-5.6-Sol Reliable agentic workhorse for everyday tasks.
3. GPT-5.6-Terra Balanced agentic coding model for everyday work.
4. GPT-5.6-Luna Fast and affordable agentic coding model.
› 5. GPT-5.5 (current) Frontier model for complex coding, research, and
real-world work.
› 5. GPT-5.5 (current) Proven previous-generation model for coding and
general work.
enter select · esc back