From e69acead8dbee53a2990fe8df5bc12cebc31444a Mon Sep 17 00:00:00 2001 From: "openclaw-docs-sync[bot]" Date: Sat, 25 Apr 2026 17:07:58 +0000 Subject: [PATCH] chore(sync): mirror docs from openclaw/openclaw@6b3e4b88d687b2ab30fc6026f3ccffd6487d3faf --- .openclaw-sync/source.json | 4 +- docs/docs.json | 60 +++++++++++-------- ...gpt55-codex-agentic-parity-maintainers.md} | 22 +++---- ...arity.md => gpt55-codex-agentic-parity.md} | 54 ++++++++--------- 4 files changed, 74 insertions(+), 66 deletions(-) rename docs/help/{gpt54-codex-agentic-parity-maintainers.md => gpt55-codex-agentic-parity-maintainers.md} (91%) rename docs/help/{gpt54-codex-agentic-parity.md => gpt55-codex-agentic-parity.md} (87%) diff --git a/.openclaw-sync/source.json b/.openclaw-sync/source.json index 1a2d553ca..eb2d4d0b6 100644 --- a/.openclaw-sync/source.json +++ b/.openclaw-sync/source.json @@ -1,5 +1,5 @@ { "repository": "openclaw/openclaw", - "sha": "39343088edb8fe4e5d6e354539e12ff7968cb8ce", - "syncedAt": "2026-04-25T17:05:53.389Z" + "sha": "6b3e4b88d687b2ab30fc6026f3ccffd6487d3faf", + "syncedAt": "2026-04-25T17:06:28.288Z" } diff --git a/docs/docs.json b/docs/docs.json index 91b961082..781cb6ca8 100644 --- a/docs/docs.json +++ b/docs/docs.json @@ -52,6 +52,14 @@ ] }, "redirects": [ + { + "source": "/help/gpt54-codex-agentic-parity", + "destination": "/help/gpt55-codex-agentic-parity" + }, + { + "source": "/help/gpt54-codex-agentic-parity-maintainers", + "destination": "/help/gpt55-codex-agentic-parity-maintainers" + }, { "source": "/mcp", "destination": "/cli/mcp" @@ -1698,8 +1706,8 @@ "concepts/typing-indicators", "concepts/usage-tracking", "concepts/timezone", - "help/gpt54-codex-agentic-parity", - "help/gpt54-codex-agentic-parity-maintainers" + "help/gpt55-codex-agentic-parity", + "help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -3147,8 +3155,8 @@ "ja-JP/concepts/typing-indicators", "ja-JP/concepts/usage-tracking", "ja-JP/concepts/timezone", - "ja-JP/help/gpt54-codex-agentic-parity", - "ja-JP/help/gpt54-codex-agentic-parity-maintainers" + "ja-JP/help/gpt55-codex-agentic-parity", + "ja-JP/help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -3981,8 +3989,8 @@ "es/concepts/typing-indicators", "es/concepts/usage-tracking", "es/concepts/timezone", - "es/help/gpt54-codex-agentic-parity", - "es/help/gpt54-codex-agentic-parity-maintainers" + "es/help/gpt55-codex-agentic-parity", + "es/help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -4815,8 +4823,8 @@ "pt-BR/concepts/typing-indicators", "pt-BR/concepts/usage-tracking", "pt-BR/concepts/timezone", - "pt-BR/help/gpt54-codex-agentic-parity", - "pt-BR/help/gpt54-codex-agentic-parity-maintainers" + "pt-BR/help/gpt55-codex-agentic-parity", + "pt-BR/help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -5649,8 +5657,8 @@ "ko/concepts/typing-indicators", "ko/concepts/usage-tracking", "ko/concepts/timezone", - "ko/help/gpt54-codex-agentic-parity", - "ko/help/gpt54-codex-agentic-parity-maintainers" + "ko/help/gpt55-codex-agentic-parity", + "ko/help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -6483,8 +6491,8 @@ "de/concepts/typing-indicators", "de/concepts/usage-tracking", "de/concepts/timezone", - "de/help/gpt54-codex-agentic-parity", - "de/help/gpt54-codex-agentic-parity-maintainers" + "de/help/gpt55-codex-agentic-parity", + "de/help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -7317,8 +7325,8 @@ "fr/concepts/typing-indicators", "fr/concepts/usage-tracking", "fr/concepts/timezone", - "fr/help/gpt54-codex-agentic-parity", - "fr/help/gpt54-codex-agentic-parity-maintainers" + "fr/help/gpt55-codex-agentic-parity", + "fr/help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -8151,8 +8159,8 @@ "ar/concepts/typing-indicators", "ar/concepts/usage-tracking", "ar/concepts/timezone", - "ar/help/gpt54-codex-agentic-parity", - "ar/help/gpt54-codex-agentic-parity-maintainers" + "ar/help/gpt55-codex-agentic-parity", + "ar/help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -8985,8 +8993,8 @@ "it/concepts/typing-indicators", "it/concepts/usage-tracking", "it/concepts/timezone", - "it/help/gpt54-codex-agentic-parity", - "it/help/gpt54-codex-agentic-parity-maintainers" + "it/help/gpt55-codex-agentic-parity", + "it/help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -9819,8 +9827,8 @@ "tr/concepts/typing-indicators", "tr/concepts/usage-tracking", "tr/concepts/timezone", - "tr/help/gpt54-codex-agentic-parity", - "tr/help/gpt54-codex-agentic-parity-maintainers" + "tr/help/gpt55-codex-agentic-parity", + "tr/help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -10653,8 +10661,8 @@ "uk/concepts/typing-indicators", "uk/concepts/usage-tracking", "uk/concepts/timezone", - "uk/help/gpt54-codex-agentic-parity", - "uk/help/gpt54-codex-agentic-parity-maintainers" + "uk/help/gpt55-codex-agentic-parity", + "uk/help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -11487,8 +11495,8 @@ "id/concepts/typing-indicators", "id/concepts/usage-tracking", "id/concepts/timezone", - "id/help/gpt54-codex-agentic-parity", - "id/help/gpt54-codex-agentic-parity-maintainers" + "id/help/gpt55-codex-agentic-parity", + "id/help/gpt55-codex-agentic-parity-maintainers" ] }, { @@ -12321,8 +12329,8 @@ "pl/concepts/typing-indicators", "pl/concepts/usage-tracking", "pl/concepts/timezone", - "pl/help/gpt54-codex-agentic-parity", - "pl/help/gpt54-codex-agentic-parity-maintainers" + "pl/help/gpt55-codex-agentic-parity", + "pl/help/gpt55-codex-agentic-parity-maintainers" ] }, { diff --git a/docs/help/gpt54-codex-agentic-parity-maintainers.md b/docs/help/gpt55-codex-agentic-parity-maintainers.md similarity index 91% rename from docs/help/gpt54-codex-agentic-parity-maintainers.md rename to docs/help/gpt55-codex-agentic-parity-maintainers.md index c5e735642..3d9be9512 100644 --- a/docs/help/gpt54-codex-agentic-parity-maintainers.md +++ b/docs/help/gpt55-codex-agentic-parity-maintainers.md @@ -1,12 +1,12 @@ --- -summary: "How to review the GPT-5.4 / Codex parity program as four merge units" -title: "GPT-5.4 / Codex parity maintainer notes" +summary: "How to review the GPT-5.5 / Codex parity program as four merge units" +title: "GPT-5.5 / Codex parity maintainer notes" read_when: - - Reviewing the GPT-5.4 / Codex parity PR series + - Reviewing the GPT-5.5 / Codex parity PR series - Maintaining the six-contract agentic architecture behind the parity program --- -This note explains how to review the GPT-5.4 / Codex parity program as four merge units without losing the original six-contract architecture. +This note explains how to review the GPT-5.5 / Codex parity program as four merge units without losing the original six-contract architecture. ## Merge units @@ -59,7 +59,7 @@ Does not own: Owns: -- first-wave GPT-5.4 vs Opus 4.6 scenario pack +- first-wave GPT-5.5 vs Opus 4.6 scenario pack - parity documentation - parity report and release-gate mechanics @@ -123,7 +123,7 @@ Expected artifacts from PR D: ## Release gate -Do not claim GPT-5.4 parity or superiority over Opus 4.6 until: +Do not claim GPT-5.5 parity or superiority over Opus 4.6 until: - PR A, PR B, and PR C are merged - PR D runs the first-wave parity pack cleanly @@ -132,7 +132,7 @@ Do not claim GPT-5.4 parity or superiority over Opus 4.6 until: ```mermaid flowchart LR - A["PR A-C merged"] --> B["Run GPT-5.4 parity pack"] + A["PR A-C merged"] --> B["Run GPT-5.5 parity pack"] A --> C["Run Opus 4.6 parity pack"] B --> D["qa-suite-summary.json"] C --> E["qa-suite-summary.json"] @@ -146,7 +146,7 @@ flowchart LR The parity harness is not the only evidence source. Keep this split explicit in review: -- PR D owns the scenario-based GPT-5.4 vs Opus 4.6 comparison +- PR D owns the scenario-based GPT-5.5 vs Opus 4.6 comparison - PR B deterministic suites still own auth/proxy/DNS and full-access truthfulness evidence ## Quick maintainer merge workflow @@ -179,13 +179,13 @@ If any one of the evidence bar items is missing, request changes instead of merg | No fake progress or fake tool completion | PR A + PR D | parity fake-success count plus scenario-level report details | | No false `/elevated full` guidance | PR B | deterministic runtime-truthfulness suites | | Replay/liveness failures remain explicit | PR C + PR D | lifecycle/replay suites plus `compaction-retry-mutating-tool` | -| GPT-5.4 matches or beats Opus 4.6 | PR D | `qa-agentic-parity-report.md` and `qa-agentic-parity-summary.json` | +| GPT-5.5 matches or beats Opus 4.6 | PR D | `qa-agentic-parity-report.md` and `qa-agentic-parity-summary.json` | ## Reviewer shorthand: before vs after | User-visible problem before | Review signal after | | ----------------------------------------------------------- | --------------------------------------------------------------------------------------- | -| GPT-5.4 stopped after planning | PR A shows act-or-block behavior instead of commentary-only completion | +| GPT-5.5 stopped after planning | PR A shows act-or-block behavior instead of commentary-only completion | | Tool use felt brittle with strict OpenAI/Codex schemas | PR C keeps tool registration and parameter-free invocation predictable | | `/elevated full` hints were sometimes misleading | PR B ties guidance to actual runtime capability and blocked reasons | | Long tasks could disappear into replay/compaction ambiguity | PR C emits explicit paused, blocked, abandoned, and replay-invalid state | @@ -193,4 +193,4 @@ If any one of the evidence bar items is missing, request changes instead of merg ## Related -- [GPT-5.4 / Codex agentic parity](/help/gpt54-codex-agentic-parity) +- [GPT-5.5 / Codex agentic parity](/help/gpt55-codex-agentic-parity) diff --git a/docs/help/gpt54-codex-agentic-parity.md b/docs/help/gpt55-codex-agentic-parity.md similarity index 87% rename from docs/help/gpt54-codex-agentic-parity.md rename to docs/help/gpt55-codex-agentic-parity.md index 3457aeadd..38af2ef3c 100644 --- a/docs/help/gpt54-codex-agentic-parity.md +++ b/docs/help/gpt55-codex-agentic-parity.md @@ -1,15 +1,15 @@ --- -summary: "How OpenClaw closes agentic execution gaps for GPT-5.4 and Codex-style models" -title: "GPT-5.4 / Codex agentic parity" +summary: "How OpenClaw closes agentic execution gaps for GPT-5.5 and Codex-style models" +title: "GPT-5.5 / Codex agentic parity" read_when: - - Debugging GPT-5.4 or Codex agent behavior + - Debugging GPT-5.5 or Codex agent behavior - Comparing OpenClaw agentic behavior across frontier models - Reviewing the strict-agentic, tool-schema, elevation, and replay fixes --- -# GPT-5.4 / Codex Agentic Parity in OpenClaw +# GPT-5.5 / Codex Agentic Parity in OpenClaw -OpenClaw already worked well with tool-using frontier models, but GPT-5.4 and Codex-style models were still underperforming in a few practical ways: +OpenClaw already worked well with tool-using frontier models, but GPT-5.5 and Codex-style models were still underperforming in a few practical ways: - they could stop after planning instead of doing the work - they could use strict OpenAI/Codex tool schemas incorrectly @@ -27,7 +27,7 @@ This slice adds an opt-in `strict-agentic` execution contract for embedded Pi GP When enabled, OpenClaw stops accepting plan-only turns as “good enough” completion. If the model only says what it intends to do and does not actually use tools or make progress, OpenClaw retries with an act-now steer and then fails closed with an explicit blocked state instead of silently ending the task. -This improves the GPT-5.4 experience most on: +This improves the GPT-5.5 experience most on: - short “ok do it” follow-ups - code tasks where the first step is obvious @@ -40,7 +40,7 @@ This slice makes OpenClaw tell the truth about two things: - why the provider/runtime call failed - whether `/elevated full` is actually available -That means GPT-5.4 gets better runtime signals for missing scope, auth refresh failures, HTML 403 auth failures, proxy issues, DNS or timeout failures, and blocked full-access modes. The model is less likely to hallucinate the wrong remediation or keep asking for a permission mode the runtime cannot provide. +That means GPT-5.5 gets better runtime signals for missing scope, auth refresh failures, HTML 403 auth failures, proxy issues, DNS or timeout failures, and blocked full-access modes. The model is less likely to hallucinate the wrong remediation or keep asking for a permission mode the runtime cannot provide. ### PR C: execution correctness @@ -53,7 +53,7 @@ The tool-compat work reduces schema friction for strict OpenAI/Codex tool regist ### PR D: parity harness -This slice adds the first-wave QA-lab parity pack so GPT-5.4 and Opus 4.6 can be exercised through the same scenarios and compared using shared evidence. +This slice adds the first-wave QA-lab parity pack so GPT-5.5 and Opus 4.6 can be exercised through the same scenarios and compared using shared evidence. The parity pack is the proof layer. It does not change runtime behavior by itself. @@ -62,7 +62,7 @@ After you have two `qa-suite-summary.json` artifacts, generate the release-gate ```bash pnpm openclaw qa parity-report \ --repo-root . \ - --candidate-summary .artifacts/qa-e2e/gpt54/qa-suite-summary.json \ + --candidate-summary .artifacts/qa-e2e/gpt55/qa-suite-summary.json \ --baseline-summary .artifacts/qa-e2e/opus46/qa-suite-summary.json \ --output-dir .artifacts/qa-e2e/parity ``` @@ -73,16 +73,16 @@ That command writes: - a machine-readable JSON verdict - an explicit `pass` / `fail` gate result -## Why this improves GPT-5.4 in practice +## Why this improves GPT-5.5 in practice -Before this work, GPT-5.4 on OpenClaw could feel less agentic than Opus in real coding sessions because the runtime tolerated behaviors that are especially harmful for GPT-5-style models: +Before this work, GPT-5.5 on OpenClaw could feel less agentic than Opus in real coding sessions because the runtime tolerated behaviors that are especially harmful for GPT-5-style models: - commentary-only turns - schema friction around tools - vague permission feedback - silent replay or compaction breakage -The goal is not to make GPT-5.4 imitate Opus. The goal is to give GPT-5.4 a runtime contract that rewards real progress, supplies cleaner tool and permission semantics, and turns failure modes into explicit machine- and human-readable states. +The goal is not to make GPT-5.5 imitate Opus. The goal is to give GPT-5.5 a runtime contract that rewards real progress, supplies cleaner tool and permission semantics, and turns failure modes into explicit machine- and human-readable states. That changes the user experience from: @@ -92,15 +92,15 @@ to: - “the model either acted, or OpenClaw surfaced the exact reason it could not” -## Before vs after for GPT-5.4 users +## Before vs after for GPT-5.5 users | Before this program | After PR A-D | | ---------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- | -| GPT-5.4 could stop after a reasonable plan without taking the next tool step | PR A turns “plan only” into “act now or surface a blocked state” | +| GPT-5.5 could stop after a reasonable plan without taking the next tool step | PR A turns “plan only” into “act now or surface a blocked state” | | Strict tool schemas could reject parameter-free or OpenAI/Codex-shaped tools in confusing ways | PR C makes provider-owned tool registration and invocation more predictable | -| `/elevated full` guidance could be vague or wrong in blocked runtimes | PR B gives GPT-5.4 and the user truthful runtime and permission hints | +| `/elevated full` guidance could be vague or wrong in blocked runtimes | PR B gives GPT-5.5 and the user truthful runtime and permission hints | | Replay or compaction failures could feel like the task silently disappeared | PR C surfaces paused, blocked, abandoned, and replay-invalid outcomes explicitly | -| “GPT-5.4 feels worse than Opus” was mostly anecdotal | PR D turns that into the same scenario pack, the same metrics, and a hard pass/fail gate | +| “GPT-5.5 feels worse than Opus” was mostly anecdotal | PR D turns that into the same scenario pack, the same metrics, and a hard pass/fail gate | ## Architecture @@ -123,7 +123,7 @@ flowchart TD ```mermaid flowchart LR - A["Merged runtime slices (PR A-C)"] --> B["Run GPT-5.4 parity pack"] + A["Merged runtime slices (PR A-C)"] --> B["Run GPT-5.5 parity pack"] A --> C["Run Opus 4.6 parity pack"] B --> D["qa-suite-summary.json"] C --> E["qa-suite-summary.json"] @@ -162,7 +162,7 @@ Checks that a task with a real mutating write keeps replay-unsafety explicit ins ## Scenario matrix -| Scenario | What it tests | Good GPT-5.4 behavior | Failure signal | +| Scenario | What it tests | Good GPT-5.5 behavior | Failure signal | | ---------------------------------- | --------------------------------------- | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------ | | `approval-turn-tool-followthrough` | Short approval turns after a plan | Starts the first concrete tool action immediately instead of restating intent | plan-only follow-up, no tool activity, or blocked turn without a real blocker | | `model-switch-tool-continuity` | Runtime/model switching under tool use | Preserves task context and continues acting coherently | resets into commentary, loses tool context, or stops after switch | @@ -172,7 +172,7 @@ Checks that a task with a real mutating write keeps replay-unsafety explicit ins ## Release gate -GPT-5.4 can only be considered at parity or better when the merged runtime passes the parity pack and the runtime-truthfulness regressions at the same time. +GPT-5.5 can only be considered at parity or better when the merged runtime passes the parity pack and the runtime-truthfulness regressions at the same time. Required outcomes: @@ -191,24 +191,24 @@ For the first-wave harness, the gate compares: Parity evidence is intentionally split across two layers: -- PR D proves same-scenario GPT-5.4 vs Opus 4.6 behavior with QA-lab +- PR D proves same-scenario GPT-5.5 vs Opus 4.6 behavior with QA-lab - PR B deterministic suites prove auth, proxy, DNS, and `/elevated full` truthfulness outside the harness ## Goal-to-evidence matrix | Completion gate item | Owning PR | Evidence source | Pass signal | | -------------------------------------------------------- | ----------- | ------------------------------------------------------------------ | ---------------------------------------------------------------------------------------- | -| GPT-5.4 no longer stalls after planning | PR A | `approval-turn-tool-followthrough` plus PR A runtime suites | approval turns trigger real work or an explicit blocked state | -| GPT-5.4 no longer fakes progress or fake tool completion | PR A + PR D | parity report scenario outcomes and fake-success count | no suspicious pass results and no commentary-only completion | -| GPT-5.4 no longer gives false `/elevated full` guidance | PR B | deterministic truthfulness suites | blocked reasons and full-access hints stay runtime-accurate | +| GPT-5.5 no longer stalls after planning | PR A | `approval-turn-tool-followthrough` plus PR A runtime suites | approval turns trigger real work or an explicit blocked state | +| GPT-5.5 no longer fakes progress or fake tool completion | PR A + PR D | parity report scenario outcomes and fake-success count | no suspicious pass results and no commentary-only completion | +| GPT-5.5 no longer gives false `/elevated full` guidance | PR B | deterministic truthfulness suites | blocked reasons and full-access hints stay runtime-accurate | | Replay/liveness failures stay explicit | PR C + PR D | PR C lifecycle/replay suites plus `compaction-retry-mutating-tool` | mutating work keeps replay-unsafety explicit instead of silently disappearing | -| GPT-5.4 matches or beats Opus 4.6 on the agreed metrics | PR D | `qa-agentic-parity-report.md` and `qa-agentic-parity-summary.json` | same scenario coverage and no regression on completion, stop behavior, or valid tool use | +| GPT-5.5 matches or beats Opus 4.6 on the agreed metrics | PR D | `qa-agentic-parity-report.md` and `qa-agentic-parity-summary.json` | same scenario coverage and no regression on completion, stop behavior, or valid tool use | ## How to read the parity verdict Use the verdict in `qa-agentic-parity-summary.json` as the final machine-readable decision for the first-wave parity pack. -- `pass` means GPT-5.4 covered the same scenarios as Opus 4.6 and did not regress on the agreed aggregate metrics. +- `pass` means GPT-5.5 covered the same scenarios as Opus 4.6 and did not regress on the agreed aggregate metrics. - `fail` means at least one hard gate tripped: weaker completion, worse unintended stops, weaker valid tool use, any fake-success case, or mismatched scenario coverage. - “shared/base CI issue” is not itself a parity result. If CI noise outside PR D blocks a run, the verdict should wait for a clean merged-runtime execution instead of being inferred from branch-era logs. - Auth, proxy, DNS, and `/elevated full` truthfulness still come from PR B’s deterministic suites, so the final release claim needs both: a passing PR D parity verdict and green PR B truthfulness coverage. @@ -218,7 +218,7 @@ Use the verdict in `qa-agentic-parity-summary.json` as the final machine-readabl Use `strict-agentic` when: - the agent is expected to act immediately when a next step is obvious -- GPT-5.4 or Codex-family models are the primary runtime +- GPT-5.5 or Codex-family models are the primary runtime - you prefer explicit blocked states over “helpful” recap-only replies Keep the default contract when: @@ -229,4 +229,4 @@ Keep the default contract when: ## Related -- [GPT-5.4 / Codex parity maintainer notes](/help/gpt54-codex-agentic-parity-maintainers) +- [GPT-5.5 / Codex parity maintainer notes](/help/gpt55-codex-agentic-parity-maintainers)