Release history
Chameleon releases
All releases
166 shown
v4.5.12
Breaking risk
Breaking changes
- Changed behavior of "all/every/throughout" claim qualifiers to count from session records at write time instead of full aggregates.
Full changelog
Changed
- deep-work universal claims are transcriptions. The Rails graded round implemented
flawlessly and still dropped two dimensions to the same class: "read all 39 files" over a
transcript showing 24, and "ast/exact throughout" over one fallback injection. Any
"all/every/throughout" in the brief or report must be counted from the session record at
write time or weakened to the honest subset — the fates-line discipline, generalized to
every aggregate claim, in both completeness passes.
v3.0.0
Breaking risk
⚠ Upgrade required
- Refresh operation repairs missing .chameleon/conventions.md mirror after upgrades or profile changes.
- Kill switch CHAMELEON_CONVENTIONS_MD=0 disables the conventions file generation.
- Cache for interpreter resolution can be disabled with CHAMELEON_INTERP_CACHE=0.
Breaking changes
- MCP surface reduced from 48 tools to 19; all non‑comprehension tools now accessed via three dispatchers (chameleon_lifecycle, chameleon_review, chameleon_telemetry) with renamed actions.
- Repository restructured: marketplace source points at ./plugin directory only; tests/, docs/, and dev tooling are excluded from installed plugin bundles.
Notable features
- .chameleon/conventions.md added as a CLAUDE.md-channel mirror for bootstrap/refresh/teach‑unteach operations.
- Multi‑convention effectiveness campaign published with full study instrumentation and results.
- SessionStart injection reorders to lead context; `// chameleon-ignore` now scoped to human‑approved exceptions.
Full changelog
Added (2026-07-11)
.chameleon/conventions.md— the CLAUDE.md-channel mirror. Bootstrap,
refresh, and teach/unteach now maintain a rendered conventions file for the
repo to wire into Claude's memory channel. Measured motive: the identical
rules were followed 100% via this channel vs 40% as a hook advisory (see
tests/effectiveness/results-published/migration-ab-2026-07-11.md).
/chameleon-initoffers three consent-gated wirings, none of which edit an
existing file by default: a one-line.claude/rules/chameleon-conventions.md
(auto-loads for the whole team),CLAUDE.local.md(personal), or a
CLAUDE.mdimport on explicit preference. Kill switch
CHAMELEON_CONVENTIONS_MD=0. A refresh repairs a missing mirror
(_profile_needs_rederive), and any engine upgrade already forces the full
re-derive that writes it — existing profiles gain the file on their first
refresh after upgrading.- Multi-convention effectiveness campaign published (30 tasks x TS/Ruby/
Python x 4 arms x 2 models, deterministic scorer, the repo's own
cluster-bootstrap bar): chameleon 1.00 conformance on every task, every
language, both models; bar MET vs no-plugin on both models; MET vs
stale-CLAUDE.md on haiku; ceiling-tie vs perfectly-maintained CLAUDE.md.
Instruments committed (tests/study_*.py); all results in
tests/effectiveness/results-published/(including the null dogfood
retrospective and the unfavorable single-convention run, per policy). - Judge-panel calibration gate computed: kappa 1.000 on the 13-pair golden
set (Fable-reference labels, provenance in
tests/effectiveness/golden/LABELS_PROVENANCE.md— not human labels).
Changed (2026-07-11)
- SessionStart injection reorders: the
<chameleon-conventions>block now
leads the context (before the skill text) and carries explicit
anti-majority framing ("existing files may be mid-migration; never infer a
convention from sibling-file majority against a rule here"). - The
// chameleon-ignoreescape hatch is scoped to human-approved
exceptions in both the import-preference deny reason and the
using-chameleon skill: the model must not self-approve an override because
existing files still use the blocked pattern. - pr-review gains a mechanical dependency demotion sweep before verdict
rendering (a new-dependency's name alone can never be a BLOCK/FIX).
Fixed (2026-07-11)
- Journey act 12b phase-41 checker read the raw stream-json transcript, so
line-based assertions saw escaped\n— a structural false positive that
failed the dependency-ACK check on every run. Both historical "failures"
re-adjudicate as passes; live re-run green.
Breaking (v3)
-
MCP surface folded from 48 tools to 19. The 16 comprehension/conformance
tools stay top-level (detect_repo,get_pattern_context,get_archetype,
get_canonical_excerpt,get_rules,lint_file,search_codebase,
describe_codebase,get_callers,get_callees,get_blast_radius,
query_symbol_importers,get_crossfile_context,get_contract_breaks,
get_duplication_candidates,explain_edit); the remaining 32 operator
tools become actions on three dispatchers, called as
<dispatcher>(action="<old tool name>", params={...original arguments, names and values unchanged...}):| Old top-level tool | New dispatcher / action |
|---|---|
|bootstrap_repo|chameleon_lifecycle(action="bootstrap_repo")|
|refresh_repo|chameleon_lifecycle(action="refresh_repo")|
|trust_profile|chameleon_lifecycle(action="trust_profile")|
|list_profiles|chameleon_lifecycle(action="list_profiles")|
|merge_profiles|chameleon_lifecycle(action="merge_profiles")|
|teach_profile|chameleon_lifecycle(action="teach_profile")|
|teach_profile_structured|chameleon_lifecycle(action="teach_profile_structured")|
|teach_competing_import|chameleon_lifecycle(action="teach_competing_import")|
|unteach_competing_import|chameleon_lifecycle(action="unteach_competing_import")|
|propose_archetype_renames|chameleon_lifecycle(action="propose_archetype_renames")|
|apply_archetype_renames|chameleon_lifecycle(action="apply_archetype_renames")|
|disable_session|chameleon_lifecycle(action="disable_session")|
|pause_session|chameleon_lifecycle(action="pause_session")|
|get_autopass_verdict|chameleon_review(action="get_autopass_verdict")|
|refute_finding|chameleon_review(action="refute_finding")|
|record_review_verdict|chameleon_review(action="record_review_verdict")|
|record_finding_fate|chameleon_review(action="record_finding_fate")|
|get_review_history|chameleon_review(action="get_review_history")|
|scan_dependency_changes|chameleon_review(action="scan_dependency_changes")|
|dep_audit|chameleon_review(action="dep_audit")|
|get_status|chameleon_telemetry(action="get_status")|
|get_drift_status|chameleon_telemetry(action="get_drift_status")|
|get_drift_antipatterns|chameleon_telemetry(action="get_drift_antipatterns")|
|get_shadow_report|chameleon_telemetry(action="get_shadow_report")|
|get_override_audit|chameleon_telemetry(action="get_override_audit")|
|get_longitudinal_signals|chameleon_telemetry(action="get_longitudinal_signals")|
|get_finding_fate_stats|chameleon_telemetry(action="get_finding_fate_stats")|
|get_idiom_coverage|chameleon_telemetry(action="get_idiom_coverage")|
|check_idiom_candidates|chameleon_telemetry(action="check_idiom_candidates")|
|get_prose_rule_candidates|chameleon_telemetry(action="get_prose_rule_candidates")|
|daemon_status|chameleon_telemetry(action="daemon_status")|
|doctor|chameleon_telemetry(action="doctor")|Rationale: a context-lean tool surface — a session now loads 19 tool schemas
instead of 48; the underlying Python functions keep their names and
signatures, so direct imports (tests, QA batteries) are unaffected.
Changed
- Repository restructured around an installable
plugin/dir. The
marketplace source now points at./plugin(plugin.json, .mcp.json, hooks/,
skills/, agents/, bin/, mcp/, and the runtime scripts ts_dump.mjs,
prism_dump.rb, libcst_dump.py, chameleon-merge-driver.sh, setup.sh), so a
marketplace install copies only the runtime surface instead of the whole
repo (previously ~4.9MB of tests/ and docs/ shipped with every install).
tests/, docs/, and dev tooling (bump-version.sh, prune-plugin-cache.sh, ...)
stay outside the installed plugin; the release tarball likewise now packs
plugin/+ README/LICENSE/CHANGELOG only. No runtime behavior change —
everything in-plugin resolves viaCLAUDE_PLUGIN_ROOTas before. - Interpreter resolution is cached and the per-edit ladder is bounded. The
resolved interpreter argv persists to a version-keyed cache (validated on
read), and per-edit hooks cap the uv probe at 5s — bounded even where
timeout(1)is absent (Git Bash, coreutils-less macOS), previously uncapped.
Kill switchCHAMELEON_INTERP_CACHE=0. - pr-review skill split for progressive disclosure: a lean SKILL.md plus
lazyreferences/*.md, and the fixed reviewer/scout roles are now packaged
agents/(chameleon:pattern-reviewer,code-scout,web-researcher).
Fixed
- The daemon now starts under deep plugin-data paths. AF_UNIX caps
sun_pathat ~104 bytes, so a deepCHAMELEON_PLUGIN_DATAmade every bind
fail and the latency daemon silently never engaged (hooks fell back
in-process forever). The socket moved to a short user-private
<tmpdir>/chameleon-<uid>/d-<hash>.sock; pidfile and logs stay in the data
dir. - Python test files no longer bucket into production role archetypes.
python_role_for_pathroutedtests/api/routes/test_x.pytoroute, so the
per-edit hook injected a production route canonical when editing a test; it now
gates on the canonical test-path detector first. - Python linter config is read from sub-project dirs (a monorepo
backend/ pyproject.toml), matching the TypeScript workspace-config fallback. - Skill-surface fixes: the refresh skill's re-lock call now passes the
requiredpath; receiving-code-review gained anargument-hint; the
pr-review fan-out claim about reviewer tool grants is now an enforced in-agent
directive rather than an unenforceable grant statement.
Review required
v2.68.0
Breaking risk
Breaking upgrade
Auth
Linked worktree profile mapping fix
Review required
v2.38.32
Security relevant
Auth
Credential deny enforcement + index reporting fix
Review required
v2.38.28
Breaking risk
Breaking upgrade
Migration detection fixes + monorepo onboarding
Review required
v2.38.15
Bug fix
Crypto / TLS
Dependencies
Crypto gate + TS hash + install script + contract
Review required
v2.37.0
New feature
Auth
RCE / SSRF
Dependencies
+1 more
pr-review routing + adjudication grounding
Review required
v2.21.0
New feature
Dependencies
Supply‑chain checks + contract diffs + definition hydration
Review required
v2.18.0
Breaking risk
Auth
Breaking upgrade
Python >=3.11 requirement for hooks