Skip to content

fix(anthropic): correct Mythos 5.2 baseline (access blocked) - #145

Draft
amplifier-resolve[bot] wants to merge 3 commits into
mainfrom
automation/provider-model-scanner
Draft

amplifier-resolve[bot] wants to merge 3 commits into
mainfrom
automation/provider-model-scanner

Conversation

@amplifier-resolve

Copy link
Copy Markdown

Summary

DRAFT useful partial — BLOCKED access + blocked_review; not DELIVERED, not ready, not Goal achieved.

  • Correct the exact claude-mythos-5-2 baseline: cold 1M/128K budget metadata, conservative capability/forced-tool refusal through final-wire overrides, and exact observed-model accounting/discovery metadata. Preserve existing defaults and other model support; no SDK bump, CLI/core/foundation changes, Fast/computer-use expansion or account changes.
  • Published Standard/global USD per 1M token estimates: input 8, output 40, cache read 0.20, 5-minute cache write 10, 1-hour write 16. Keep unsupported IDs/tiers and malformed or incomplete usage unknown, not free; preserve sticky unknown session totals, including fragmented compressed SDK streams. These are documented estimates, not reconciled billing.
  • This is distinct from superseded Fable draft fix: add exact-model Fable 5.2 baseline #141, which stays CLOSED. Merged fix: publish truthful Anthropic fixed and tiered pricing #143 already preserved Fable support and pricing; fix: capture safe token-count unavailable diagnostics #144 diagnostics are preserved. The exact old scanner revision 07131d214484b632361ff5157fa3a51f6867a40f is incorporated by normal two-parent merge, not overwritten or replayed over newer accounting. No third-party branch is changed.

Sources and scope

Official sources re-read 2026-11-15 (living rates have no asserted effective date):

Current main incorporated: 6ea9d0cfb3df6c2cdf007de80d98c8f48016760e; original bootstrap 7793791a504aea5531806abcd904b7757c2d5a58 retained as ancestor. Candidate b3ecdf4703e1795adcbf33c5c5444ed71c60d829, approved identical tree a038bee858946d421b2c9249675ffef74a628891. Merge parents: reviewed d56d5d88ea8ca098cc0c36081b0e5b2e39640758 and old scanner 07131d214484b632361ff5157fa3a51f6867a40f.

Real tests and independent source review

  • Exact candidate Python 3.12 maintained offline run:
    python -I -S tests/run_offline.py -q
    3434 passed, 1 deselected, 99 warnings in 60.22s (0:01:00), exit 0; no audited attempts, shutdown accounted, import identities stable. Live vision is deliberately deselected and remains UNMET.
  • Focused cost/pricing/stream/Fable/Haiku regressions: 1189 passed, 52 warnings in 4.53s, exit 0.
  • Independent bounded source review APPROVED exact six-file hashes/full diff after compressed-stream R1 and explicit-None forced-tool R2 corrections. This is source acceptance, NOT the required GitHub correctness-review-bot verdict or delivery approval.
  • Retained extra Python 3.13 run failed: 23 failed, 3411 passed, 1 deselected, 99 warnings in 34.34s. Offline-isolation child-launch tests hit maintained audit refusal of os.posix_spawn; this is not a Python 3.11 pass or a waived failure. Required GitHub Ubuntu/macOS/Windows Python 3.11/3.12 matrix must be observed at this head; no remote CI pass is preclaimed.

Exact installed DTU evidence — access BLOCKED

Existing isolated run (now destroyed, absence verified) installed clean exact provider b3ecdf4703e1795adcbf33c5c5444ed71c60d829, actual CLI 9a053f52130014650a680ace6d26172c4ce207bd, SDK 1.17.0, Core 2.0.2 wheel, Foundation 1.0.0. Installed Python bytes and distribution RECORDs verified. The actual CLI initialization path mounted the exact one-provider source with model claude-mythos-5-2, both fallbacks off and zero retries. Loader/help/identity validation is not successful CLI inference.

One bounded public-library AnthropicProvider.complete request (128 output tokens, no fallback/retries) received HTTP 404 not_found_error, model: claude-mythos-5-2, request ID req_011Ch4euxqdNEU1hX7DMdarv, about 0.363 seconds, command exit 10. No replacement model or repeated target call. The 404 does not distinguish model availability from entitlement/verification/retention; account status remains unknown. Vendor/account-owner investigation is needed; no policy or credentials changed. No inference usage returned; billing unknown, never asserted zero.

Independent Reality Check 20261115-114338-90db02 confirmed denial evidence, installed identities and fallback settings, blocker investigation only, NOT meaningful successful behavioral qualification. Worker-local raw logs/receipts/report and hashes are retained for the assigned caller; they are not public links and are not uploaded here. Tool-reported investigation-model billing is separate from unknown candidate billing.

Explicit unmet gates

  • Successful exact-model public-library text, streaming and harmless tool/result continuation.
  • Actual exact-model CLI inference; loader evidence alone is insufficient.
  • Required maintained real vision, image behavior, and applicable thinking/cache/error/budget qualification.
  • Meaningful successful final-head Reality Check of public-library plus CLI behavior.
  • Repository-required current-head CI and required-check discovery/readback; local green does not substitute.
  • Actual owning-repository correctness-review-bot identity/PASS semantics and explicit PASS attributable to this current head. No such verdict observed before publication; missing review means blocked_review, never PASS inferred from CLA, tests or source review.

Bounded current-head CI/review observation and final head readback follow publication; this draft stays blocked regardless of green offline CI while access/behavioral gates remain unmet. Context Intelligence historical/current-run coverage is incomplete; no scheduler lock or exhaustive predecessor exclusion is claimed. Current scoped PR reconciliation found no relevant owned open Mythos baseline PR. No merge, ready conversion, default push, source edit, new DTU or third-party mutation is authorized by this publication.

Generated with Amplifier

Amplifier Resolve and others added 3 commits November 12, 2026 03:39
Add standard Decimal pricing, cold budget recognition preserving the
existing 1M-context policy, and reject forced tool choice after expert
wire overrides for the exact fixed model. Preserve other model behavior.

Focused regressions: 195 passed. Full maintained offline suite: 23 failed,
2549 passed, 1 deselected; offline-isolation child launch audit blocker.
No live or DTU qualification; unresolved correctness bot is not passed.

Generated with Amplifier

Co-Authored-By: Amplifier <240397093+microsoft-amplifier@users.noreply.github.com>
Add reviewed exact-model forced-tool refusal, cold budget recognition and standard/cache pricing while preserving older model behavior. Preserve malformed observed usage through SDK coercion and compressed SSE decoding so response, event and session costs remain honestly unknown.

Independent source acceptance: attempt2_anthropic_accepted_review.json. Fresh maintained focused offline suite passed; real vision and final-head live qualification remain unmet.

Generated with Amplifier

Co-Authored-By: Amplifier <240397093+microsoft-amplifier@users.noreply.github.com>
…d tree

First parent: d56d5d8 (approved Mythos candidate).
Second parent: 07131d2 (old scanner).
Approved identical tree: a038bee.

Merged143 (3204656) supersedes141: collaborator comment #141 (comment); original baseline tests are identical between old scanner and143.

Normal merge, not ours strategy. Resolve only examined conflicts from approved first parent: __init__.py retains Fable guards/budget and reviewed exact Mythos extensions; _cost.py retains identical Fable rates plus143 accounting and reviewed Mythos row; test_fable52_baseline.py retains143 original coverage extended by approved Mythos and override regressions. All other paths merge unchanged. Entire tree equality checked before commit. Preserve143/144 and both original histories; no new semantic changes.

Local reconciliation only; no publication or live qualification claimed.

Generated with Amplifier

Co-Authored-By: Amplifier <240397093+microsoft-amplifier@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

0 participants