[0.159] Prepare 0.159.1 release backports (#49323)

Prepare the backports for 0.159.1 on `release/0.159`. The release set is
incomplete: one additional backport is pending. Keep this PR in draft
until the full release set is included.

Currently includes #49318: add GPT-6.1 Sol as the default bundled model
and update the older Sol descriptions and model-picker snapshots.

The backport omits the `skill_catalog_dedup` snapshot because its test
does not exist on the 0.159 release line. The model catalog and all
retained snapshot files match the original public commit.

Release-line CI currently reports a stale `code-mode` feature exception
in the manifest checker, unlinked files in `codex-core` and
`codex-login`, and Codespell findings in the exec-server and TUI math
code. The reported files are unchanged from the 0.159.0 content commit.
A Linux Bazel job also failed while downloading Buildozer with HTTP 500.
This commit is contained in:
andrewgu-oai
2026-09-29 11:51:44 -07:00
committed by GitHub
parent 06971ec9aa
commit 9fb2f5f4b2
21 changed files with 240 additions and 62 deletions
@@ -6,7 +6,7 @@ Scenario: Astra starts in one workspace, switches for the next step of the activ
## Window 1
-- request 1 (turn) --
00:additional_tools/developer (3; hash=b1e101cdca5088a0):
00:additional_tools/developer (3; hash=a54e67018899e049):
- namespace/functions; hash=dead25325ac79c67
- custom/exec
- function/wait
@@ -14,7 +14,7 @@ Scenario: Astra starts in one workspace, switches for the next step of the activ
- 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=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -7,7 +7,7 @@ Scenario: Astra uses the catalog question schema to ask who a launch update is f
## Window 1
-- request 1 (request) --
00:additional_tools/developer (3; hash=9922060cb05f2122):
00:additional_tools/developer (3; hash=ae153e78f6722d2b):
- namespace/functions; hash=f1de44f63c977f3d
- custom/exec
- function/wait
@@ -15,7 +15,7 @@ Scenario: Astra uses the catalog question schema to ask who a launch update is f
- 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=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- 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=32be5470c6e39932):
00:additional_tools/developer (3; hash=a1bfbfab4176467b):
- 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=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- 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=61ac4d92c828cbf9):
00:additional_tools/developer (3; hash=e33e09a2c1478914):
- 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=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -6,7 +6,7 @@ Scenario: Astra receives new user input after its unfinished response is interru
## Window 1
-- request 1 (request) --
00:additional_tools/developer (3; hash=32be5470c6e39932):
00:additional_tools/developer (3; hash=a1bfbfab4176467b):
- namespace/functions; hash=e7db0a45c4ec3157
- custom/exec
- function/wait
@@ -14,7 +14,7 @@ Scenario: Astra receives new user input after its unfinished response is interru
- 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=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -6,7 +6,7 @@ Scenario: Astra continues after new user input yields a running code cell, then
## Window 1
-- request 1 (turn) --
00:additional_tools/developer (3; hash=07af97f334a32933):
00:additional_tools/developer (3; hash=b035de0e31ab087e):
- namespace/functions; hash=a0b6a7ae1ecf9f28
- custom/exec
- function/wait
@@ -14,7 +14,7 @@ Scenario: Astra continues after new user input yields a running code cell, then
- 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=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- 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=32be5470c6e39932):
00:additional_tools/developer (3; hash=a1bfbfab4176467b):
- 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=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -187,7 +187,7 @@ 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=32be5470c6e39932):
00:additional_tools/developer (3; hash=a1bfbfab4176467b):
- namespace/functions; hash=e7db0a45c4ec3157
- custom/exec
- function/wait
@@ -195,7 +195,7 @@ 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=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- 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=32be5470c6e39932):
00:additional_tools/developer (3; hash=a1bfbfab4176467b):
- 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=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -110,7 +110,7 @@ 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=4327e247f74ba810):
00:additional_tools/developer (3; hash=7810769c6e12d379):
- namespace/functions; hash=8c17932a39355f2d
- custom/exec
- function/wait
@@ -118,7 +118,7 @@ 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=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- 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=4327e247f74ba810):
00:additional_tools/developer (3; hash=7810769c6e12d379):
- 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=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -32,14 +32,14 @@ Settings:
stream: true
text: {"verbosity":"low"}
tool_choice: "auto"
tools (7; hash=884bfb8fc9050f65):
tools (7; hash=7a45a45148e7ea6a):
- custom/exec: Catalog exec instructions. Default yield: 1234 ms. `image(imageUrlOrItem: string | { image_url: s...; hash=a49b91fd82908e18
- function/wait: Catalog wait instructions: resume the yielded cell.; args=[cell_id, max_tokens, terminate, yield_time_ms]; hash=67bc0f04da3505b3
- 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
- function/request_user_input_async: Ask the user one or more questions during ongoing work. Use this tool only to request missing inf...; args=[questions]; hash=d6d74f33db330162
- namespace/clock: Tools for reading and waiting on time.; hash=f402e8c5e9b5e317
- function/sleep
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- function/followup_task
- function/interrupt_agent
- function/list_agents
@@ -16,8 +16,8 @@ Settings:
stream: true
text: {"verbosity":"low"}
tool_choice: "auto"
tools (4; hash=78e3b4e156c8704f):
- custom/exec: Run JavaScript code to orchestrate/compose tool calls - Evaluates the provided JavaScript code in...; hash=6382c54728ef9e96
tools (4; hash=ee397215c4055252):
- custom/exec: Run JavaScript code to orchestrate/compose tool calls - Evaluates the provided JavaScript code in...; hash=485f26f17d4a2899
- function/wait: Waits on a yielded `exec` cell and returns new output or completion. - Use `wait` only after `exe...; args=[cell_id, max_tokens, terminate, yield_time_ms]; hash=6692d8f6c55be489
- 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
- web_search; hash=e214d4db1bc49e89
@@ -16,8 +16,8 @@ Settings:
stream: true
text: {"verbosity":"low"}
tool_choice: "auto"
tools (4; hash=da1f22cdbb122728):
- custom/exec: Run JavaScript code to orchestrate/compose tool calls - Evaluates the provided JavaScript code in...; hash=bd4bc63f8dac64cb
tools (4; hash=045ecf3b2d3b6af5):
- custom/exec: Run JavaScript code to orchestrate/compose tool calls - Evaluates the provided JavaScript code in...; hash=e9cdd499ac568220
- function/wait: Waits on a yielded `exec` cell and returns new output or completion. - Use `wait` only after `exe...; args=[cell_id, max_tokens, terminate, yield_time_ms]; hash=6692d8f6c55be489
- 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
- web_search; hash=e214d4db1bc49e89
@@ -48,8 +48,8 @@ Settings:
## Window 2 (after request 2)
Settings: relative to window 1
model: "prefixes-cleared"
tools (4; hash=e51735744389fb0e):
~ custom/exec: Run JavaScript code to orchestrate/compose tool calls - Evaluates the provided JavaScript code in...; hash=1ef6e3872d1dfe3f
tools (4; hash=dec6fdcb7bf3fec7):
~ custom/exec: Run JavaScript code to orchestrate/compose tool calls - Evaluates the provided JavaScript code in...; hash=39e1eedcbc703718
-- request 3 (turn) --
00:message/developer:
<PERMISSIONS_INSTRUCTIONS>
@@ -32,14 +32,14 @@ Settings:
stream: true
text: {"verbosity":"low"}
tool_choice: "auto"
tools (7; hash=de6aceb7b0185d08):
tools (7; hash=4a2648ce3a65d327):
- custom/exec: Run JavaScript code to orchestrate/compose tool calls - Evaluates the provided JavaScript code in...; hash=50ea9b7f60e145b5
- function/wait: Waits on a yielded `exec` cell and returns new output or completion. - Use `wait` only after `exe...; args=[cell_id, max_tokens, terminate, yield_time_ms]; hash=6692d8f6c55be489
- 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
- function/request_user_input_async: Ask the user one or more questions during ongoing work. Use this tool only to request missing inf...; args=[questions]; hash=d6d74f33db330162
- namespace/clock: Tools for reading and waiting on time.; hash=f402e8c5e9b5e317
- function/sleep
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=fd994b11525da73c
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=b263e3c84ad07c37
- 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=48937f38e1083468):
00:additional_tools/developer (3; hash=78c6350cb8fdad81):
- 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=e7005987945a10f0
- namespace/collaboration: Tools for spawning and managing sub-agents.; hash=170baa4086bfe3cb
- 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=1974ec5490da160d):
tools (11; hash=14a76ba72d609d9e):
- 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=b109e235997460a9
- namespace/multi_agent_v1: Tools for spawning and managing sub-agents.; hash=2327142bda177c50
- function/close_agent
- function/resume_agent
- function/send_input
File diff suppressed because one or more lines are too long
@@ -14,7 +14,7 @@ attached:
› draft during startup
GPT-6-Astra default · /tmp/project
GPT-6.1-Sol default · /tmp/project
owned=true
startup:
@@ -27,4 +27,4 @@ attached:
› draft during startup
GPT-6-Astra default · /tmp/project
GPT-6.1-Sol default · /tmp/project
@@ -372,7 +372,7 @@ async fn fresh_startup_reads_destination_and_cleared_model_uses_catalog() -> Res
insta::assert_snapshot!(rendered, @r"
› Ask Codex to do anything
GPT-6-Astra high · <PROJECT>
GPT-6.1-Sol high · <PROJECT>
");
}
let expected_cwd = if override_cwd {
@@ -5,10 +5,10 @@ expression: "render_bottom_popup(&chat, 100)"
Select Model and Effort
› 1. GPT-6 Sol (current) Workhorse model for coding and everyday work.
› 1. GPT-6 Sol (current) Previous generation workhorse model.
2. GPT-6-Astra Frontier intelligence for the most demanding work.
3. GPT-6 Luna Fast and affordable model for easier tasks.
4. GPT-5.6 Sol Older coding model for complex work.
4. GPT-5.6 Sol Older generation workhorse model.
5. GPT-5.6 Terra Older balanced model for straightforward work.
6. GPT-5.6 Luna Older fast and efficient model.
7. GPT-5.5 Legacy coding model.
@@ -5,13 +5,13 @@ expression: "render_bottom_popup(&chat, 100)"
Select Model and Effort
› 1. GPT-6 Sol (Global) (current) Workhorse model for coding and everyday work.
› 1. GPT-6 Sol (Global) (current) Previous generation workhorse model.
2. GPT-6-Astra (Global) Frontier intelligence for the most demanding work.
3. GPT-6 Luna (Global) Fast and affordable model for easier tasks.
4. GPT-5.6 Sol (Global) Older coding model for complex work.
4. GPT-5.6 Sol (Global) Older generation workhorse model.
5. GPT-5.6 Terra (Global) Older balanced model for straightforward work.
6. GPT-5.6 Luna (Global) Older fast and efficient model.
7. GPT-6 Sol (US cross-region) Workhorse model for coding and everyday work.
7. GPT-6 Sol (US cross-region) Previous generation workhorse model.
8. GPT-6-Astra (US cross-region) Frontier intelligence for the most demanding work.
↓
enter select · esc back
@@ -5,12 +5,13 @@ expression: popup
Select Model and Effort
1. GPT-6-Astra (default) Frontier intelligence for the most demanding work.
2. GPT-6-Sol Workhorse model for coding and everyday work.
3. GPT-6-Luna Fast and affordable model for easier tasks.
4. GPT-5.6-Sol Older coding model for complex work.
5. GPT-5.6-Terra Older balanced model for straightforward work.
6. GPT-5.6-Luna Older fast and efficient model.
› 7. GPT-5.5 (current) Legacy coding model.
1. GPT-6.1-Sol (default) Latest workhorse model for coding and everyday work.
2. GPT-6-Astra Frontier intelligence for the most demanding work.
3. GPT-6-Sol Previous generation workhorse model.
4. GPT-6-Luna Fast and affordable model for easier tasks.
5. GPT-5.6-Sol Older generation workhorse model.
6. GPT-5.6-Terra Older balanced model for straightforward work.
7. GPT-5.6-Luna Older fast and efficient model.
› 8. GPT-5.5 (current) Legacy coding model.
enter select · esc back