Skip to content
Merged
Changes from all commits
Commits
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
18 changes: 11 additions & 7 deletions MODELS.md
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ does not establish that a review ran.
| 2. Second build | Opus 5.5 (`claude-opus-5-5`, through Claude Code) | Checks the implementation and tests, corrects gaps within scope, and simplifies code without weakening parser protection or changing contracts accidentally. |
| 3. Independent review | Sol 6.1 (`gpt-6.1-sol`, through Codex) | Reviews Java correctness, streaming behavior, exact output, public API and packaged-consumer compatibility. |
| 3. Independent review | Daybreak Blue (the Codex model-picker entry; `gpt-daybreak-blue-latest`) | Examines parser-boundary attacks, context confusion and resource exhaustion. Explicitly select Blue access and run the preflight below. Record the requested alias, any returned model identity, and access program separately. |
| 3. Independent review | Mythos 5.1 (`claude-mythos-5-1`, through Claude Code) | Challenges security assumptions with primary specifications and adversarial parser tests, including trusted/untrusted fragment composition. |
| 3. Independent review | Mythos 5.2 (`claude-mythos-5-2`, through Claude Code; requires verified access) | Challenges security assumptions with primary specifications and adversarial parser tests, including trusted/untrusted fragment composition. |
| 3. Independent review | Sonnet 5.5 (`claude-sonnet-5-5`, through Claude Code) | Checks Javadocs, examples and migration notes for accurate context selection, complete surrounding syntax, concision and plain US English. |
| 4. Resolve and deliver | Astra (`gpt-6-astra`, through Codex) | Resolves findings with evidence, validates the final revision, and reports the verdict, remaining blockers and results to the operator. |

Expand Down Expand Up @@ -77,8 +77,8 @@ a release merely because a review was requested.

### CLI recipes

These routes were checked with **Codex CLI 0.163.0** and **Claude Code 2.1.304**
on **2026-10-20**. Recheck local `--help` when the installed version changes or
These routes were checked with **Codex CLI 0.169.0** and **Claude Code 2.1.325**
on **2026-11-14**. Recheck local `--help` when the installed version changes or
a flag fails; do not silently change models. The commands assume absolute
`review_dir`, `review_packet`, and `review_role_file` paths. The packet contains
shared evidence; the role file contains the slot's instructions. Use a fresh
Expand Down Expand Up @@ -114,8 +114,11 @@ review_status=$?
printf '%s\n' "$review_status" > "$review_dir/$review_model.exit"
```

For Claude, use exactly `claude-opus-5-5`, `claude-mythos-5-1`, or
`claude-sonnet-5-5`. This packet-only recipe disables tools and MCP servers;
For Claude, use exactly `claude-opus-5-5`, `claude-mythos-5-2`, or
`claude-sonnet-5-5`. Mythos 5.2 is available only to organizations verified
through Anthropic's programs; an account without that access fails with a
"may not have access" error. Report the slot as unfilled in that case rather
than substituting Fable 5.2 or another model. This packet-only recipe disables tools and MCP servers;
provide source/specification/test evidence in the packet. Select the Claude ID
and prepare its per-slot input as above before running:

Expand Down Expand Up @@ -161,7 +164,7 @@ Official references for troubleshooting:
[Astra](https://developers.openai.com/api/docs/models/gpt-6-astra),
[Sol 6.1](https://developers.openai.com/api/docs/models/gpt-6.1-sol),
[Claude models](https://platform.claude.com/docs/en/models/overview),
[Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview),
[Mythos 5.2](https://platform.claude.com/docs/en/models/mythos-5-2/overview),
and [Claude CLI](https://code.claude.com/docs/en/cli-reference).

### Daybreak Blue preflight
Expand Down Expand Up @@ -239,7 +242,8 @@ an unfilled slot as a coverage gap, not a passing review.

On 2026-10-18, Codex 0.163.0 advertised the exact picker entry with Blue access,
and its explicit probe completed successfully. The catalog and explicit probe
were verified again on 2026-10-20 with the same CLI version. The earlier #243 review had
were verified again on 2026-10-20 with the same CLI version, and on 2026-11-14
with Codex 0.169.0. The earlier #243 review had
not attempted that probe; its unavailable label did not establish an access
failure. This dated result does not guarantee future access. Any review added
after publication must be labeled supplemental, not retroactively counted as a
Expand Down
Loading