ticket: use base32 project record ids

2026-06-09 22:10:47 +09:00
parent 0803bc3725
commit 4203988d74
798 changed files with 477 additions and 105 deletions
@@ -0,0 +1,37 @@
+---
+title: "Provider: make codex gpt-5.5 context window effective"
+state: "closed"
+created_at: "2026-05-31T00:37:43Z"
+updated_at: "2026-05-31T01:58:24Z"
+---
+
+## Background
+
+`refresh-builtin-model-catalog` updated the `codex-oauth/gpt-5.5` builtin entry to record OpenAI's advertised 1.05M context window while retaining `max_context_window = 272000` as an effective clamp. That made the catalog entry technically accurate to both OpenAI docs and observed Codex OAuth behavior, but it also made the model metadata harder to understand.
+
+For a provider-specific builtin entry, `context_window` should represent the effective window for that provider route. `codex-oauth/gpt-5.5` is not the generic OpenAI API route; it is the Codex OAuth / ChatGPT backend route. If that route effectively fails above ~272k input tokens, then the builtin catalog should say `context_window = 272000` directly and explain why in a comment.
+
+## Requirements
+
+- Change the builtin `codex-oauth/gpt-5.5` model entry so `context_window` is the effective Codex OAuth route limit (`272000`).
+- Remove `max_context_window = 272000` from that builtin entry.
+- Add a nearby TOML comment explaining that OpenAI documents GPT-5.5 with a 1.05M context window, but Codex OAuth / ChatGPT backend access has been observed/known to be effectively limited around 272k, so the provider-specific builtin entry records the effective limit.
+- Keep the default profile on `codex-oauth/gpt-5.5`.
+- Preserve the `max_context_window` manifest/config field and its code/tests if still useful for explicit inline overrides or future providers; do not remove the field globally in this ticket unless doing so is clearly tiny and mechanically safe.
+- Update provider/manifest tests that currently expect catalog-level `max_context_window` clamp for builtin `gpt-5.5`.
+- Do not change OpenRouter `openai/gpt-5.5` unless there is separate evidence for that route's effective limit; this ticket is about `codex-oauth`.
+
+## Non-goals
+
+- Re-refreshing the full model catalog.
+- Changing provider definitions or auth behavior.
+- Changing compaction/pruning algorithms beyond tests that derive known model context.
+- Removing `max_context_window` from public manifest/config types wholesale.
+
+## Acceptance criteria
+
+- `resources/models/builtin.toml` has `codex-oauth/gpt-5.5` with `context_window = 272000` and no `max_context_window` field.
+- The builtin catalog comment makes the 1.05M-vs-272k route distinction explicit.
+- Tests no longer rely on catalog-level `max_context_window` for `codex-oauth/gpt-5.5`.
+- Inline `max_context_window` clamp behavior remains tested if the field remains supported.
+- `cargo fmt --check`, focused provider/manifest tests, `./tickets.sh doctor`, and `git diff --check` pass.
@@ -0,0 +1 @@
+Updated the builtin `codex-oauth/gpt-5.5` entry so `context_window = 272000` directly represents the effective Codex OAuth / ChatGPT backend route limit, with a catalog comment explaining that generic OpenAI docs advertise 1.05M. Removed catalog-level `max_context_window` from that entry while preserving inline/config `max_context_window` support. External review approved and validation passed.
@@ -0,0 +1,94 @@
+<!-- event: create author: tickets.sh at: 2026-05-31T00:37:43Z -->
+
+## Created
+
+Created by tickets.sh create.
+
+---
+
+<!-- event: plan author: hare at: 2026-05-31T00:38:23Z -->
+
+## Plan
+
+Implementation plan:
+
+1. Update only the provider-specific builtin catalog entry for `codex-oauth/gpt-5.5`: set `context_window = 272000`, remove `max_context_window`, and add a clear comment about generic OpenAI docs vs Codex OAuth effective limit.
+2. Keep `resources/profiles/default.lua` unchanged.
+3. Adjust tests so builtin catalog expectations use effective `context_window`, while `max_context_window` behavior remains covered by an inline/config-specific test if the field remains supported.
+4. Validate with focused provider/manifest tests plus `cargo fmt --check`, `./tickets.sh doctor`, and `git diff --check`.
+
+
+---
+
+<!-- event: implementation_report author: hare at: 2026-05-31T01:57:37Z -->
+
+## Implementation report
+
+Implementation report from coder Pod `codex-gpt55-context-coder-20260531`:
+
+- Branch: `codex-gpt55-effective-context-window`
+- Commit: `ed3e97c22a8e21dce9223114526932a11b268589` (`provider: use codex gpt55 effective context`)
+- Updated `resources/models/builtin.toml` so `codex-oauth/gpt-5.5` records the effective Codex OAuth route limit directly as `context_window = 272000` and no longer has `max_context_window`.
+- Added a nearby comment explaining that OpenAI documents GPT-5.5 as 1.05M context, but Codex OAuth / ChatGPT backend access is effectively limited around 272k.
+- Kept default profile unchanged and did not change OpenRouter `openai/gpt-5.5`.
+- Preserved `max_context_window` support for inline/config overrides and updated tests accordingly.
+
+Validation reported by coder:
+
+- `cargo fmt --check` passed
+- `cargo test -p provider catalog` passed
+- `cargo test -p manifest model` passed
+- `cargo check -p provider -p manifest` passed
+- `./tickets.sh doctor` passed
+- `git diff --check` passed
+
+Unresolved issues: none.
+
+
+---
+
+<!-- event: review author: hare at: 2026-05-31T01:57:38Z status: approve -->
+
+## Review: approve
+
+External review by reviewer Pod `codex-gpt55-context-reviewer-20260531`: approve.
+
+Reviewer summary:
+
+- The change is correctly scoped to `codex-oauth/gpt-5.5` and relevant tests.
+- `context_window = 272000` now represents the effective Codex OAuth route limit directly.
+- The comment explains the distinction between OpenAI's advertised 1.05M context window and the observed/known Codex OAuth effective limit.
+- `max_context_window` support remains available for inline/config cases.
+- Default profile and OpenRouter `openai/gpt-5.5` were not changed.
+
+Blockers: none.
+
+
+---
+
+<!-- event: implementation_report author: hare at: 2026-05-31T01:58:24Z -->
+
+## Implementation report
+
+Main workspace validation after merge:
+
+- `cargo fmt --check` passed
+- `cargo test -p provider catalog` passed
+- `cargo test -p manifest model` passed
+- `cargo check -p provider -p manifest` passed
+- `./tickets.sh doctor` passed
+- `git diff --check` passed
+
+Warnings observed are pre-existing dead-code warnings in `llm-worker` / filtered manifest test helpers.
+
+
+---
+
+<!-- event: close author: hare at: 2026-05-31T01:58:24Z status: closed -->
+
+## Closed
+
+Updated the builtin `codex-oauth/gpt-5.5` entry so `context_window = 272000` directly represents the effective Codex OAuth / ChatGPT backend route limit, with a catalog comment explaining that generic OpenAI docs advertise 1.05M. Removed catalog-level `max_context_window` from that entry while preserving inline/config `max_context_window` support. External review approved and validation passed.
+
+
+---
				`@@ -0,0 +1 @@`
				Updated the builtin `codex-oauth/gpt-5.5` entry so `context_window = 272000` directly represents the effective Codex OAuth / ChatGPT backend route limit, with a catalog comment explaining that generic OpenAI docs advertise 1.05M. Removed catalog-level `max_context_window` from that entry while preserving inline/config `max_context_window` support. External review approved and validation passed.