wowdespacito/anthropics_skills
1
0
Fork 0
mirror of https://github.com/anthropics/skills.git synced 2026-08-02 21:15:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update claude-api skill: Claude Fable 5 and Claude Mythos 5 (#1294)

Browse Source 
- Add Claude Fable 5 and Claude Mythos 5 to the model tables with pricing,
  context window, and model-selection guidance
- Document Fable-specific API behavior: always-on adaptive thinking (explicit
  disabled returns 400), protected-thinking display and replay rules, new
  tokenizer (~30% more tokens), refusal stop reason with server-side fallbacks
  and SDK fallback middleware, 30-day data-retention requirement
- Add the full Migrating to Claude Fable 5 guide section and checklist,
  including the Mythos Preview migration path
- Refresh skill trigger description, effort/compaction/task-budget notes,
  caching minimums, structured-output and dynamic-filtering support tables
This commit is contained in:
Lance Martin
2026-06-09 10:34:55 -07:00
committed by GitHub
parent c30d329f58
commit 5d25128289
13 changed files with 306 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/claude-api/python/claude-api/README.md
+3 -3
View File
@@ -250,11 +250,11 @@ If `cache_read_input_tokens` is zero across repeated identical-prefix requests,
## Extended Thinking
> **Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6:** Use adaptive thinking. `budget_tokens` is removed on Opus 4.8 and 4.7 (400 if sent); deprecated on Opus 4.6 and Sonnet 4.6.
> **Fable 5, Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6:** Use adaptive thinking. `budget_tokens` is removed on Fable 5, Opus 4.8, and 4.7 (400 if sent); deprecated on Opus 4.6 and Sonnet 4.6.
> **Older models:** Use `thinking: {type: "enabled", budget_tokens: N}` (must be < `max_tokens`, min 1024).
```python
# Opus 4.8 / 4.7 / 4.6: adaptive thinking (recommended)
# Fable 5 / Opus 4.8 / 4.7 / 4.6: adaptive thinking (recommended)
response = client.messages.create(
model="claude-opus-4-8",
max_tokens=16000,
@@ -381,7 +381,7 @@ response2 = conversation.send("What's my name?") # Claude remembers "Alice"
### Compaction (long conversations)
> **Beta, Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6.** When conversations approach the 200K context window, compaction automatically summarizes earlier context server-side. The API returns a `compaction` block; you must pass it back on subsequent requests — append `response.content`, not just the text.
> **Beta, Fable 5, Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6.** When conversations approach the 200K context window, compaction automatically summarizes earlier context server-side. The API returns a `compaction` block; you must pass it back on subsequent requests — append `response.content`, not just the text.
```python
import anthropic
skills/claude-api/python/claude-api/streaming.md
+1 -1
View File
@@ -46,7 +46,7 @@ No final-message accumulation is done for you in this form.
Claude may return text, thinking blocks, or tool use. Handle each appropriately:
> **Opus 4.8 / Opus 4.7 / Opus 4.6:** Use `thinking: {type: "adaptive"}`. On older models, use `thinking: {type: "enabled", budget_tokens: N}` instead.
> **Fable 5 / Opus 4.8 / Opus 4.7 / Opus 4.6:** Use `thinking: {type: "adaptive"}`. On older models, use `thinking: {type: "enabled", budget_tokens: N}` instead.
```python
with client.messages.stream(