agentforce314 · ericleepi314 · Jul 12, 2026 · Jul 12, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -7,8 +7,31 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.1.0] - 2026-07-12
+
 ### Added
 
+- **Sign in with ChatGPT — use OpenAI models on a ChatGPT Plus/Pro
+  subscription instead of metered API billing** (#698). `clawcodex login →
+  openai → subscription` runs an OAuth login (browser loopback,
+  device-code, or import from an existing Codex CLI login) and routes
+  requests through the ChatGPT Codex backend's Responses API. Subscription
+  models: `gpt-5.5`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.3-codex-spark`, with
+  encrypted-reasoning replay across turns; a configured `OPENAI_API_KEY`
+  always wins, and subscription usage reports `billing_mode: subscription`
+  (billed as `$0`).
+- **Claude Pro/Max subscription login** (#697). `clawcodex login →
+  anthropic → subscription` connects a Claude subscription over OAuth
+  (PKCE), with automatic token refresh, `mcp_`-prefixed tool adaptation,
+  and the same `$0` accounting.
+- **Meta provider + `muse-spark-1.1`** (#692) — the `api.meta.ai`
+  OpenAI-compatible reasoning model with a 1M-token context window, added
+  as a one-row `ProviderSpec`.
+- **`/plan` mode** with implicit plan-mode entry/exit
+  (`EnterPlanMode`/`ExitPlanMode`), ported from the reference (#676).
+- **`--worktree` / `-w` session isolation** — run parallel sessions in
+  isolated git worktrees, wired through the launcher, backend, and TUI
+  (#672).
 - **`/loop` scheduled tasks now actually fire — full port of Claude Code's
   session-scoped scheduler** (docs/en/scheduled-tasks). A new
   `src/scheduled_tasks` engine parses standard 5-field vixie cron
@@ -64,6 +87,23 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- **Claude subscription login repaired** (#702). The Anthropic OAuth login
+  migrated off `console.anthropic.com` to `platform.claude.com`, and the
+  token exchange sent no `User-Agent` — so `urllib`'s default signature was
+  Cloudflare bot-blocked (`error code: 1010`) before it reached OAuth.
+  Updated the token/authorize/redirect endpoints and scopes to the current
+  upstream config (subscriber authorize base `claude.com/cai/oauth/authorize`)
+  and send a genuine `User-Agent`.
+- **Adaptive thinking is only sent to models that support it** (#699).
+  Requests previously sent `thinking={"type":"adaptive"}` to every Claude
+  4.x model, which the API rejects for all but Opus 4.6/4.7 and Sonnet 4.6
+  ("adaptive thinking is not supported on this model"). Models that support
+  thinking but not adaptive now get a token budget instead; `output_config`
+  effort is gated to the models that accept it.
+- **Semantic tool-input coercion + parity validation errors** (#700) —
+  string-coerce boolean/number tool arguments (mirroring the reference's
+  `semanticBoolean`/`semanticNumber`) and format schema-validation failures
+  to match `formatZodValidationError`.
 - Bounded the ESC-cancel worker-thread queue in `OpenAICompatibleProvider.chat_stream_response` (`src/providers/openai_compatible.py`) to `maxsize=64`. Previously an unbounded `queue.Queue` let an orphaned worker accumulate chunks in memory indefinitely when a proxy kept sending bytes after abort without closing the SDK iterator (#278).
 - **URLs the agent prints are clickable again.** The TUI markdown renderer
   (`ui-tui/src/components/markdown.tsx`) replaced every visible URL with a

diff --git a/README.md b/README.md
@@ -101,6 +101,7 @@ The `session`, `settings`, and `env` blocks are optional — sensible defaults a
 
 ## 📰 News
 
+- **2026-07-12 (v1.1.0):** **ClawCodex v1.1.0 — run OpenAI *and* Claude models on your subscription, not metered API billing** — the headline of 1.1.0 is **subscription auth for the two biggest model families**, so you can point ClawCodex at a plan you already pay for. **Sign in with ChatGPT (#698):** `clawcodex login → openai → subscription` (browser, device-code, or import from an existing Codex CLI login) routes requests through the ChatGPT Codex backend's Responses API — `gpt-5.5`, `gpt-5.4`, `gpt-5.4-mini`, and `gpt-5.3-codex-spark` on your Plus/Pro allowance, with encrypted-reasoning replay across turns and **$0** metered cost. **Claude Pro/Max (#697):** `clawcodex login → anthropic → subscription` connects a Claude subscription via OAuth (PKCE) with automatic token refresh and the same $0 accounting; follow-ups repaired the login after Anthropic moved its OAuth endpoints to `platform.claude.com` (#702) and stopped sending adaptive thinking to models that don't support it (#699). A configured API key always wins, and subscription usage reports `billing_mode: subscription`. **More models:** a Meta (`api.meta.ai`) provider with the 1M-context `muse-spark-1.1` reasoning model (#692) and refreshed MiniMax parameters (#696). **Workflow & TUI:** `/plan` mode with implicit plan-mode entry/exit (#676), `--worktree/-w` session isolation for parallel runs in separate git worktrees (#672), the `/memory` picker + `$EDITOR` spawn (#693), config/state directories rebranded `.claude → .clawcodex` with a one-time migration (#678), `/logo` startup color schemes (#677), plus TUI polish — Tab accepts the suggested placeholder (#690), past inputs get the Claude-Code highlight band (#691), clickable agent URLs (#694), and a per-terminal link-open affordance (#701). **Quality:** semantic tool-input coercion with parity validation errors (#700) and looser, Claude-Code-faithful permission granting (#673).
 - **2026-07-07:** **`/loop` scheduled tasks now actually fire — full port of Claude Code's session-scoped scheduler (#680)** — the bundled `/loop` skill finally has a real engine behind it: a new `src/scheduled_tasks` module parses standard 5-field cron expressions and fires due prompts **between turns** from the agent-server's idle poll. `CronCreate`/`CronList`/`CronDelete` register real firing jobs (8-char IDs, 50-job cap, deterministic jitter, 7-day recurring expiry with one final fire), and the new **`ScheduleWakeup`** tool drives self-paced `/loop` mode — the model picks each next delay (1 min–1 hr), `stop: true` ends the loop, and a ~20-minute fallback wakeup catches iterations that forget to reschedule. Typed skill slash commands now reach the backend (new `skill_command` control), so `/loop 5m check ci` works from the composer with completion + argument hint; the TUI shows a live countdown indicator (`⟳ loop wakeup in 2m 14s · ⏰ 1 scheduled`) and **Esc while idle stops a waiting loop**. `/clear` drops session tasks, `--resume` restores unexpired ones, `CLAWCODEX_DISABLE_CRON=1` disables the scheduler. 117 new tests; verified live over stdio NDJSON and a real PTY TUI drive (typed dispatch → CronCreate → a real wakeup fire between turns → Esc-stop).
 - **2026-07-07:** **Bounded the ESC-cancel chunk queue in OpenAI-compatible streaming (#278)** — `OpenAICompatibleProvider.chat_stream_response`'s worker-thread queue (added in #148) was an unbounded `queue.Queue`. A non-graceful disconnect from a proxy that keeps sending bytes after ESC (and never closes the SDK iterator) let the orphaned worker thread accumulate chunks in memory indefinitely. The queue is now capped at 64 chunks, so `put()` blocks the worker once full instead of growing without bound.
 - **2026-07-06 (v1.0.0):** **ClawCodex v1.0.0 — the 1.0 release: goal-directed autonomy, hooks & MCP wired for production, and a hardened permission system** — 86 commits since v0.7.0 (#580–#668) finish wiring the big subsystems end-to-end and graduate ClawCodex to 1.0. **Goal-directed autonomy:** the `/goal` + `/subgoal` completion-condition loop keeps the agent working until an LLM judge confirms the goal is actually met (#664), the new Monitor tool streams long-running shell output with backpressure (#665), background-bash completion notifications (#663), coordinator mode wired end-to-end on the live paths (#634), and `/advisor` token-efficient worker/reviewer pairing restored on the Ink TUI (#668). **Hooks live in production:** configured hooks now actually fire — bootstrap Hooks abstraction (#583), UserPromptSubmit (#597), multi-scope + lifecycle hooks (#595), `if` pre-filters (#643), PreToolUse `permissionDecision` (#655), PermissionRequest hooks at the ask seam (#637), MCP elicitation hooks (#659), and teammate TaskCompleted / TeammateIdle stop hooks (#642). **MCP completion:** OAuth server auth via the `/mcp` flow (#662), live `tools/list_changed` refresh (#598, #604), server instructions injected into the system prompt (#654), and `clawcodex mcp serve` re-exposes ClawCodex tools as an MCP stdio server (#635). **Permission hardening:** readable approval boxes with broadenable, persistent session grants (#608–#611), compound-command permission parity (#622), Bash normalization hardening (#626), `disableBypassPermissionsMode` lockdown (#660), an honest refuse-to-start unsandboxed guard (#658), subprocess secret-scrubbing (#650), and a flag-gated LLM security-classifier lane for auto mode (#589). **TUI maturity:** faithful Claude Code look & feel — diff rendering, tool-call transcript, task list, composer + permission-mode badge, busy line (#612–#616) — plus a minimal vim editing engine (#667), Esc-interrupt with a defanged Ctrl+C (#625), fully editable multi-line input (#621), slash-command argument hints (#631), a persistent session-stats line (#657), and restored `/cost`, `/skills`, and `/model` (#627, #629, #630). **Reliability:** the production compaction pipeline is wired and auto-compact actually applies its result (#587, #607), full retry lane + model fallback + message-history caching (#586), parallel Agent fan-out with the concurrency-cap deadlock fixed (#590), killing a background agent really stops the run (#606), and output styles work end-to-end (#640). Codebase stats: 1,170 Python files, **256,909 lines** (up from 233,520 lines on 2026-06-11).
@@ -110,8 +111,6 @@ The `session`, `settings`, and `env` blocks are optional — sensible defaults a
 - **2026-06-21:** **18 new LLM providers — the registry grows 7 → 25 (#377)** — a data-driven `ProviderSpec` registry adds 18 OpenAI-compatible backends (nvidia-nim, fireworks, together, moonshot/Kimi, novita, siliconflow, deepinfra, stepfun, arcee, huggingface, volcengine, xiaomi-mimo, atlascloud, wanjie-ark, plus local ollama / vllm / sglang) alongside the hand-written providers; alias-aware config resolution, standard env-var key fallback (e.g. `TOGETHER_API_KEY`), and keyless local servers.
 - **2026-06-18:** **DeepSeek prefix-cache exploitation — a HUGE token-cost win (#363)** — ClawCodex now keeps its request prefix **byte-stable** across turns so DeepSeek's automatic prompt-prefix cache covers the entire `system + tools + history` span. Per-request-volatile sections (env, the mutable `MEMORY.md` body, plan-mode, etc.) are relocated to a trailing `<system-reminder>` *after* the conversation history, so the cached prefix never breaks even when memory/env change. We also register DeepSeek's **1M-token context window**, map its prompt-cache usage onto the Anthropic `cache_read_input_tokens` convention, and surface a per-model **prompt-cache hit-rate** + cost in `/cost`. **Why this is enormous — the token economics:** Claude Fable 5 runs **$10 / $50** per 1M input/output tokens, while **DeepSeek-V4-Pro is just $0.435 / $0.87** — already **~23× cheaper on input** and **~57× cheaper on output**. And because **cache-hit input is billed at only 10%** of the normal input rate, the long, context-heavy sessions that agentic coding actually produces pay just **~$0.0435 per 1M input tokens** — roughly **230× cheaper than Fable 5 input**. The token efficiency ClawCodex unlocks here is **HUGE**. Everything is gated to the `deepseek` provider — every other provider's request is byte-for-byte unchanged. Follow-up: truncated tool-call argument JSON is now best-effort recovered in the shared OpenAI-compatible layer, so an interrupted DeepSeek stream keeps its partial tool args instead of dropping them to `{}` (#364).
 - **2026-06-16:** **Z.ai GLM-5.2 support (#343)** — new `zai` provider for Z.ai's OpenAI-compatible GLM Coding Plan (`https://api.z.ai/api/coding/paas/v4`), shipping `GLM-5.1` and the `GLM-5.2` preview; GLM-5.2 delivers coding capability comparable to Claude Opus 4.7. First app built end-to-end with GLM-5.2 — a [FIFA World Cup 2026 intro page](demos/wc26-intro/index.html) (animated hero + live countdown, three host nations, 16 stadiums, tournament format, and record-breaking facts).
-- **2026-06-11:** **Codebase stats** — Total Python files: 1,093 files; Total Lines of Python Code: **233,520 lines** (up from 213,777 lines on 2026-05-29; ~+19.7k lines from the interactive command-system batch, the dynamic workflow engine + `/deep-research`, and the Tavily web-tooling refresh).
-- **2026-06-10 to 2026-06-11:** **Dynamic workflow engine + `/deep-research` (#262–#264, #266–#271)** — Python workflow engine core (`agent()`/`parallel()`/`pipeline()`/`phase()`, journaling, resume) wired end-to-end: Workflow tool, `/workflows` TUI dialog + status-line pill, per-agent retry, worktree isolation, result delivery, and the bundled `/deep-research` harness registered as a slash command. Reliability: LLM read timeout applied centrally to all openai-compatible providers (#269), parallel agents no longer serialize on the event loop (#270), and the deep-research synthesize step forbids tools so the report-writer can't loop (#271). Follow-ups: workflow max-turns cap fix (#272), deep-research verdict-enum fix (#273), rich `/workflows` live monitor with phase progress + per-agent stats (#287).
 📚 Older items have moved to the full **[News archive](docs/NEWS.md)**.
 
 ***

diff --git a/docs/NEWS.md b/docs/NEWS.md
@@ -2,6 +2,7 @@
 
 Full news history for ClawCodex. The [README News section](../README.md#-news) keeps only the 10 most recent items.
 
+- **2026-07-12 (v1.1.0):** **ClawCodex v1.1.0 — run OpenAI *and* Claude models on your subscription, not metered API billing** — the headline of 1.1.0 is **subscription auth for the two biggest model families**, so you can point ClawCodex at a plan you already pay for. **Sign in with ChatGPT (#698):** `clawcodex login → openai → subscription` (browser, device-code, or import from an existing Codex CLI login) routes requests through the ChatGPT Codex backend's Responses API — `gpt-5.5`, `gpt-5.4`, `gpt-5.4-mini`, and `gpt-5.3-codex-spark` on your Plus/Pro allowance, with encrypted-reasoning replay across turns and **$0** metered cost. **Claude Pro/Max (#697):** `clawcodex login → anthropic → subscription` connects a Claude subscription via OAuth (PKCE) with automatic token refresh and the same $0 accounting; follow-ups repaired the login after Anthropic moved its OAuth endpoints to `platform.claude.com` (#702) and stopped sending adaptive thinking to models that don't support it (#699). A configured API key always wins, and subscription usage reports `billing_mode: subscription`. **More models:** a Meta (`api.meta.ai`) provider with the 1M-context `muse-spark-1.1` reasoning model (#692) and refreshed MiniMax parameters (#696). **Workflow & TUI:** `/plan` mode with implicit plan-mode entry/exit (#676), `--worktree/-w` session isolation for parallel runs in separate git worktrees (#672), the `/memory` picker + `$EDITOR` spawn (#693), config/state directories rebranded `.claude → .clawcodex` with a one-time migration (#678), `/logo` startup color schemes (#677), plus TUI polish — Tab accepts the suggested placeholder (#690), past inputs get the Claude-Code highlight band (#691), clickable agent URLs (#694), and a per-terminal link-open affordance (#701). **Quality:** semantic tool-input coercion with parity validation errors (#700) and looser, Claude-Code-faithful permission granting (#673).
 - **2026-07-07:** **`/loop` scheduled tasks now actually fire — full port of Claude Code's session-scoped scheduler (#680)** — the bundled `/loop` skill finally has a real engine behind it: a new `src/scheduled_tasks` module parses standard 5-field cron expressions and fires due prompts **between turns** from the agent-server's idle poll. `CronCreate`/`CronList`/`CronDelete` register real firing jobs (8-char IDs, 50-job cap, deterministic jitter, 7-day recurring expiry with one final fire), and the new **`ScheduleWakeup`** tool drives self-paced `/loop` mode — the model picks each next delay (1 min–1 hr), `stop: true` ends the loop, and a ~20-minute fallback wakeup catches iterations that forget to reschedule. Typed skill slash commands now reach the backend (new `skill_command` control), so `/loop 5m check ci` works from the composer with completion + argument hint; the TUI shows a live countdown indicator (`⟳ loop wakeup in 2m 14s · ⏰ 1 scheduled`) and **Esc while idle stops a waiting loop**. `/clear` drops session tasks, `--resume` restores unexpired ones, `CLAWCODEX_DISABLE_CRON=1` disables the scheduler. 117 new tests; verified live over stdio NDJSON and a real PTY TUI drive (typed dispatch → CronCreate → a real wakeup fire between turns → Esc-stop).
 - **2026-07-07:** **Bounded the ESC-cancel chunk queue in OpenAI-compatible streaming (#278)** — `OpenAICompatibleProvider.chat_stream_response`'s worker-thread queue (added in #148) was an unbounded `queue.Queue`. A non-graceful disconnect from a proxy that keeps sending bytes after ESC (and never closes the SDK iterator) let the orphaned worker thread accumulate chunks in memory indefinitely. The queue is now capped at 64 chunks, so `put()` blocks the worker once full instead of growing without bound.
 - **2026-07-06 (v1.0.0):** **ClawCodex v1.0.0 — the 1.0 release: goal-directed autonomy, hooks & MCP wired for production, and a hardened permission system** — 86 commits since v0.7.0 (#580–#668) finish wiring the big subsystems end-to-end and graduate ClawCodex to 1.0. **Goal-directed autonomy:** the `/goal` + `/subgoal` completion-condition loop keeps the agent working until an LLM judge confirms the goal is actually met (#664), the new Monitor tool streams long-running shell output with backpressure (#665), background-bash completion notifications (#663), coordinator mode wired end-to-end on the live paths (#634), and `/advisor` token-efficient worker/reviewer pairing restored on the Ink TUI (#668). **Hooks live in production:** configured hooks now actually fire — bootstrap Hooks abstraction (#583), UserPromptSubmit (#597), multi-scope + lifecycle hooks (#595), `if` pre-filters (#643), PreToolUse `permissionDecision` (#655), PermissionRequest hooks at the ask seam (#637), MCP elicitation hooks (#659), and teammate TaskCompleted / TeammateIdle stop hooks (#642). **MCP completion:** OAuth server auth via the `/mcp` flow (#662), live `tools/list_changed` refresh (#598, #604), server instructions injected into the system prompt (#654), and `clawcodex mcp serve` re-exposes ClawCodex tools as an MCP stdio server (#635). **Permission hardening:** readable approval boxes with broadenable, persistent session grants (#608–#611), compound-command permission parity (#622), Bash normalization hardening (#626), `disableBypassPermissionsMode` lockdown (#660), an honest refuse-to-start unsandboxed guard (#658), subprocess secret-scrubbing (#650), and a flag-gated LLM security-classifier lane for auto mode (#589). **TUI maturity:** faithful Claude Code look & feel — diff rendering, tool-call transcript, task list, composer + permission-mode badge, busy line (#612–#616) — plus a minimal vim editing engine (#667), Esc-interrupt with a defanged Ctrl+C (#625), fully editable multi-line input (#621), slash-command argument hints (#631), a persistent session-stats line (#657), and restored `/cost`, `/skills`, and `/model` (#627, #629, #630). **Reliability:** the production compaction pipeline is wired and auto-compact actually applies its result (#587, #607), full retry lane + model fallback + message-history caching (#586), parallel Agent fan-out with the concurrency-cap deadlock fixed (#590), killing a background agent really stops the run (#606), and output styles work end-to-end (#640). Codebase stats: 1,170 Python files, **256,909 lines** (up from 233,520 lines on 2026-06-11).