docs(knowledge): refresh corpus to Opus 4.8 era (CC 2.1.114->181 Batch 3)
The knowledge base was frozen at ~v2.1.111, describing an Opus-4.7 world after CC shipped Opus 4.8 and Fable 5. Refreshed three agent-facing knowledge files; every fact re-verified against the official changelog (~/.claude/cache/changelog.md, CC 2.1.181) on 2026-06-18. - feature-evolution.md: new Opus-4.8-era rows above the v2.1.111 freeze -- Opus 4.8 default + /effort xhigh (2.1.154), Fable 5 Mythos-class (2.1.170), post-session hook (2.1.169), MessageDisplay (2.1.152), /simplify -> /code-review (2.1.147), /config key=value (2.1.181). - hook-events-reference.md: 26 -> 28 events (+MessageDisplay, +post-session); documented Stop/SubagentStop additionalContext output field. - claude-code-capabilities.md: 2026-06 model/effort lineup table; bundled skills /simplify -> /code-review; documented /config key=value. - cc-2.1.x-changelog-delta.md: marked SUPERSEDED by the gap-matrix. Verification caught two version errors in STATE/matrix, corrected to the changelog: - Stop/SubagentStop additionalContext is 2.1.163, not 2.1.165 (2.1.165 was "Bug fixes" only; matrix row 109 already said 2.1.163). - settings `agent` field introduced 2.0.59; 2.1.157 = honored for dispatched `claude agents` sessions, not the introduction. New tests/knowledge/knowledge-staleness.test.mjs (8 tests) encodes the verified facts as a re-freeze guard (RED before edits, GREEN after). Full suite: 850/850 green (+8). self-audit PASS, A(100)/A(97).
This commit is contained in:
parent
feaa7ed2e4
commit
624f5edabc
5 changed files with 119 additions and 8 deletions
|
|
@ -2,6 +2,7 @@
|
|||
|
||||
> Source: Official Claude Code documentation (code.claude.com/docs), 75 pages, verified 2026-04-03.
|
||||
> Delta layer: research/03-claude-code-changes-config-surfaces.md (verified 2026-04-19) — sandbox/managed-only/prompt-cache surfaces added between v2.1.14 and v2.1.114.
|
||||
> 2026-06 model/effort lineup (below) re-verified against the official changelog on 2026-06-18 (window v2.1.114–v2.1.181).
|
||||
|
||||
## 2026-04 deltas (research/03)
|
||||
|
||||
|
|
@ -18,6 +19,18 @@
|
|||
| Env: `ENABLE_PROMPT_CACHING_1H`, `FORCE_PROMPT_CACHING_5M` | v2.1.108 | Explicit prompt-cache TTL control. |
|
||||
| Env: `CLAUDE_CODE_DISABLE_1M_CONTEXT`, `CLAUDE_CODE_DISABLE_ADAPTIVE_THINKING` | 2026-04 | Behavior opt-outs for new defaults. |
|
||||
|
||||
## 2026-06 model & effort lineup (changelog, verified 2026-06-18)
|
||||
|
||||
> Window v2.1.114–v2.1.181. The Opus-4.7 framing elsewhere in the corpus predates these.
|
||||
|
||||
| Item | Added in | Notes |
|
||||
|------|---------|-------|
|
||||
| **Opus 4.8 — new default** | v2.1.154 | Defaults to high effort. `/effort xhigh` (`effortLevel: "xhigh"`) is the new top tier for the hardest tasks. |
|
||||
| Lean system prompt now default | v2.1.154 | Default for all models except Haiku, Sonnet, and Opus 4.7 and earlier — lowers baseline system-prompt token cost. |
|
||||
| **Claude Fable 5** (Mythos-class) | v2.1.170 | New top-capability model family; 1M context by default (a `[1m]` id suffix is normalised away). Auto mode falls back to the best available Opus for orgs without Opus 4.8. |
|
||||
| `/code-review` bundled review skill | v2.1.147 | Renamed from the former cleanup skill; reports correctness bugs at a chosen effort (`/code-review high`), `--comment` posts inline PR comments. |
|
||||
| `/config key=value` | v2.1.181 | Apply any setting from the prompt (e.g. `/config thinking=false`) — interactive, `-p`, and Remote Control. Lets `/config-audit` settings recommendations be applied without hand-editing settings.json. |
|
||||
|
||||
## Official Configuration Guidance (Anthropic)
|
||||
|
||||
These principles are backed by official docs and verified community reports. Use them to ground recommendations.
|
||||
|
|
@ -291,7 +304,7 @@ paths: ["src/**/*.ts"]
|
|||
|
||||
**Dynamic context:** `` !`command` `` executes shell command and inlines output.
|
||||
|
||||
**Bundled skills:** `/batch`, `/claude-api`, `/debug`, `/loop`, `/simplify`
|
||||
**Bundled skills:** `/batch`, `/claude-api`, `/debug`, `/loop`, `/code-review` (renamed from the former cleanup skill, v2.1.147)
|
||||
|
||||
**Fully utilizing:** Custom deploy/review workflows; `disable-model-invocation: true` on side-effect skills; `context: fork` for isolated research; `!`git diff HEAD`` for dynamic context; `argument-hint` for UX.
|
||||
|
||||
|
|
|
|||
|
|
@ -2,6 +2,7 @@
|
|||
|
||||
> Timeline of major features, most recent first. Covers features with configuration impact.
|
||||
> Source: Official Claude Code documentation, verified 2026-04-03; 2026-04 entries verified via research/03-claude-code-changes-config-surfaces.md (2026-04-19).
|
||||
> 2026-06 entries (window v2.1.114–v2.1.181) re-verified against the official Claude Code changelog on 2026-06-18.
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -9,6 +10,12 @@
|
|||
|
||||
| Approx. Date | Feature | Config Impact |
|
||||
|-------------|---------|---------------|
|
||||
| 2026-06 (v2.1.181) | **`/config key=value` in-session settings** | Set any setting from the prompt — `/config thinking=false` — in interactive, `-p`, and Remote Control. Lets `/config-audit` settings recommendations be applied without hand-editing settings.json. |
|
||||
| 2026-05 (v2.1.170) | **Claude Fable 5 (Mythos-class)** | New top-capability model family; 1M context by default (a `[1m]` id suffix is normalised away). Auto mode falls back to the best available Opus for orgs without Opus 4.8 enabled. |
|
||||
| 2026-05 (v2.1.169) | **`post-session` lifecycle hook** | Runs after the session ends and before the workspace is deleted — snapshot uncommitted work or export logs (self-hosted runner). Kebab-case, distinct from `SessionEnd`. |
|
||||
| 2026-04 (v2.1.154) | **Opus 4.8 — new default model** | Defaults to high effort; `/effort xhigh` (`effortLevel: "xhigh"`) is the new top tier for the hardest tasks. The lean system prompt is now the default for all models except Haiku, Sonnet, and Opus 4.7 and earlier. The settings `agent` field is honored for dispatched `claude agents` sessions (v2.1.157). |
|
||||
| 2026-04 (v2.1.152) | **`MessageDisplay` hook event** | Hooks can transform or hide assistant message text as it is displayed. |
|
||||
| 2026-04 (v2.1.147) | **`/simplify` renamed to `/code-review`** | Reports correctness bugs at a chosen effort (`/code-review high`); `--comment` posts inline PR comments. The old cleanup-and-fix behaviour was removed. |
|
||||
| 2026-04 (v2.1.111) | **Opus 4.7 + token-efficiency surfaces** | New env vars `ENABLE_PROMPT_CACHING_1H`, `FORCE_PROMPT_CACHING_5M`, `CLAUDE_CODE_DISABLE_1M_CONTEXT`. New settings keys around `tui` / `autoScrollEnabled`. Granular commit attribution via `attribution.commit` / `attribution.pr` (replaces `includeCoAuthoredBy`). |
|
||||
| 2026-04 (v2.1.83+) | **Sandbox + managed-only enterprise lockdown** | Added settings keys: `sandbox.enabled`, `sandbox.failIfUnavailable`, `sandbox.allowUnsandboxedCommands`, `sandbox.filesystem.allowRead/denyRead`, `sandbox.network.deniedDomains/allowedDomains`, `sandbox.enableWeakerNetworkIsolation`. Managed-only flags: `allowManagedHooksOnly`, `allowManagedMcpServersOnly`, `allowManagedPermissionRulesOnly`. |
|
||||
| 2026-03 (v2.1.91) | **`disableSkillShellExecution`** | Blocks inline `!command` shell expansion in skills. Mitigates skill-side prompt-injection vector. |
|
||||
|
|
|
|||
|
|
@ -1,7 +1,8 @@
|
|||
# Hook Events Reference
|
||||
|
||||
> All 26 hook events as of April 2026. Source: code.claude.com/docs/en/hooks.md
|
||||
> All 28 hook events as of June 2026. Source: code.claude.com/docs/en/hooks.md
|
||||
> Verified 2026-04-19 against research/03-claude-code-changes-config-surfaces.md — no new hook events introduced in v2.1.83–v2.1.111. Sandbox + managed-only flags (2026-04) operate at the settings layer, not as new hook events.
|
||||
> Re-verified 2026-06-18 against the official changelog (window v2.1.114–v2.1.181): added `MessageDisplay` (v2.1.152) and `post-session` (v2.1.169), bringing the count from 26 to 28.
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -25,6 +26,7 @@
|
|||
| `StopFailure` | Turn ends in an API error | No | Error type | Alert on API errors; retry logic; log error context |
|
||||
| `TeammateIdle` | An agent team member has no tasks | Yes | No matcher | Assign next task (exit 2 to keep working); log team status; rebalance work |
|
||||
| `Notification` | A notification is sent (permission prompt, idle, auth) | No | `permission_prompt`, `idle_prompt`, `auth_success`, `elicitation_dialog` | Desktop notifications; Slack/webhook alerts; mobile push; audio cues |
|
||||
| `MessageDisplay` | Assistant message text is about to be displayed (v2.1.152) | Yes (transforms) | No matcher | Transform or hide assistant output before it reaches the terminal — redact secrets, rewrite text |
|
||||
| `ConfigChange` | A config file changes on disk | Yes | `user_settings`, `project_settings`, `local_settings`, `policy_settings`, `skills` | Validate config changes; block invalid edits; reload dependent processes |
|
||||
| `CwdChanged` | Working directory changes | No | No matcher | Inject new directory context; update env vars via `$CLAUDE_ENV_FILE`; log navigation |
|
||||
| `FileChanged` | A watched file changes | No | Filename pattern | Auto-reload when config changes; trigger builds on source change; sync state |
|
||||
|
|
@ -35,6 +37,7 @@
|
|||
| `Elicitation` | An MCP server requests user input | Yes | MCP server name | Control which servers can request input; log elicitations; pre-fill responses |
|
||||
| `ElicitationResult` | User responds to MCP elicitation | Yes | MCP server name | Validate responses; log user input; transform before sending to MCP |
|
||||
| `SessionEnd` | Session terminates | No | `clear`, `resume`, `logout`, `prompt_input_exit`, `other` | Final session summary; save state; cleanup temp files; send end-of-session report |
|
||||
| `post-session` | Session has ended, before the workspace is deleted (v2.1.169) | No | No matcher | Snapshot uncommitted work; export logs; cleanup (self-hosted runner). Kebab-case, distinct from `SessionEnd`. |
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -94,6 +97,9 @@
|
|||
- `additionalContext`: string injected into context
|
||||
- Or: write env vars to `$CLAUDE_ENV_FILE`
|
||||
|
||||
**Stop / SubagentStop** (exit 0, since v2.1.163):
|
||||
- `hookSpecificOutput.additionalContext`: feedback string that keeps the turn going without being treated as a hook error
|
||||
|
||||
---
|
||||
|
||||
## Environment Variables Available in Hooks
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue