[BUG] Advisor always "unavailable" with Fable 5 advisor (Opus 4.8 main) across all sessions (v2.1.198)

[telekraft1440-a11y]

Preflight Checklist

• I have searched existing issues and this hasn't been reported yet
• This is a single bug report (please file separate reports for different bugs)
• I am using the latest version of Claude Code

What's Wrong?

With the advisor set to Fable 5, the advisor tool returns The advisor tool is unavailable. Do not try to use it again. on the very first advisor call — in every session, regardless of transcript size or content (including small, fresh sessions).

• /advisor reports "Advisor set to Fable 5" (accepted, no error), but the first advisor() call immediately fails with the generic "unavailable" message.
• Switching the advisor to Opus works fine in the same setup.
• Per the docs, Opus-4.8 main + Fable advisor is a valid pairing, and v2.1.198 ≥ the required v2.1.170.

This is deterministic and size-/content-independent, which distinguishes it from #67609 (specific to >100K-token transcripts). It may be the same generic-"unavailable"/sticky-off surface as #67306 / #67411, or it may simply be missing Fable 5 access for the account — in which case the client should surface a specific reason instead of a generic "unavailable".

Open question for maintainers: is this missing Fable 5 access for the account/org, or a real bug? Either way, the generic "unavailable" message is not actionable.

Related: #67609, #67306, #67411, #66784

What Should Happen?

Either the Fable 5 advisor works, or Claude Code surfaces a clear, actionable error stating why Fable 5 cannot act as advisor (e.g. "Fable 5 is not available for your account" or "unsupported pairing"), instead of the generic "The advisor tool is unavailable. Do not try to use it again."

Error Messages/Logs

The advisor tool is unavailable. Do not try to use it again.

Steps to Reproduce

1. Environment: Claude Code v2.1.198, Windows 11, main model Opus 4.8 (claude-opus-4-8), Anthropic API / subscription billing (not Bedrock/Vertex/Foundry).
2. Run /advisor and select Fable 5 → CLI confirms "Advisor set to Fable 5".
3. In any session (including a brand-new one with a short transcript), have Claude call the advisor (e.g. "consult the advisor before continuing").
4. Observed: the advisor call fails immediately with The advisor tool is unavailable. Do not try to use it again. — every time, in every session.
5. Set the advisor to Opus instead (/advisor opus) → advisor works normally in the same setup, which isolates the problem to the Fable 5 advisor.

Claude Model

Opus

Is this a regression?

I don't know

Last Working Version

No response

Claude Code Version

2.1.198 (Claude Code)

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

PowerShell

Additional Information

No response

[rskvazh]

Same thing

[MishaKav]

also got the same

[ryaneggz]

🙏 https://x.com/JohnEggz/status/2073090659255525473?s=20

[marciogranzotto]

Same

[ogtega]

Right now, my workaround is just launching a Fable 5 agent. Not ideal since seamless handoff is preferred, but it works. Does anyone know if the advisor mechanism actually saves on Fable 5 tokens, considering how differently they run?

[shadow173]

-- Same

[josdyr]

-- Same

[telekraft1440-a11y]

aUpdate: this is context-size dependent — reproduced live within a single session (Fable 5 advisor)

Correction / refinement of my original report. I first wrote that the Fable 5 advisor fails deterministically regardless of transcript size, even in fresh short sessions. On re-testing today the picture is different: it works at small context and only starts failing once the context grows past a threshold — matching the behavior in #67609.

Reproduced inside one continuous session (advisor = Fable 5, main model = Opus 4.8 [1m], Windows 11, PowerShell, Anthropic subscription billing):

Point in session	Context size	Advisor (Fable 5)
First call, start of session	small (~a few K of transcript)	✅ worked — returned a correct answer that even quoted session-specific details
Later call, same session	grown	❌ The advisor tool is unavailable. Do not try to use it again.

Nothing changed between the two calls except the accumulated context (a handful of web searches / fetches / tool calls in between). The advisor stayed Fable 5 the whole time — I did not switch models.

Measured context at the failing call: the session transcript file was ~268 KB ≈ ~67K tokens of conversation (measured, chars/4), plus the (large) Claude Code system prompt on top — putting the total in the ~100–130K range, i.e. right around the ~100K threshold reported in #67609.

Error (verbatim):

The advisor tool is unavailable. Do not try to use it again.

Config note: my settings.json has advisorModel: "opus", yet the runtime advisor was actually Fable 5 (Fable 5 promo active through July 7). So the effective advisor model can differ from what settings.json states — worth flagging for repro.

Takeaway: the generic "unavailable" is masking a context-size limit specific to the Fable 5 advisor — not a hard "no access to Fable 5." Same root cause as #67609. The error should surface the real reason, e.g. "advisor transcript exceeds Fable 5 limit (~100K)" instead of a bare "unavailable."

Env: Claude Code v2.1.198, Windows 11, PowerShell, Anthropic API/subscription (not Bedrock/Vertex/Foundry).

[Xellzul]

Most likely a Fable 5 safety filter, so not a bug, but could be better explained:

[crixlet]

Dont think it' a safety feature, it happens for nearly any context