From e065e5304f3111b5564d52cdbd4b00460fbc6283 Mon Sep 17 00:00:00 2001 From: Jim Manico Date: Sat, 14 Nov 2026 08:58:30 -0800 Subject: [PATCH] Update model lineup to Mythos 5.2 Replace Mythos 5.1 with Mythos 5.2 in the independent security review slot, note that it requires verified access, and refresh the checked CLI versions and Daybreak Blue verification date. --- MODELS.md | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/MODELS.md b/MODELS.md index 4a56803..a2716f9 100644 --- a/MODELS.md +++ b/MODELS.md @@ -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. | @@ -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 @@ -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: @@ -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 @@ -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