fix: declare long-context Claude and GPT metadata

[dgokeeffe]

Summary

Fixes long-context metadata for Claude and GPT gateway models and centralizes Claude capability policy across agents.

Closes #222.

Changes

• Pi emits explicit Claude contextWindow, maxTokens, reasoning, image, and adaptive-thinking metadata instead of accepting Pi's 128k/4k custom-model defaults.
• Pi emits model-specific GPT limits, including the opt-in 1.05M windows for supported GPT tiers.
• Claude family/version parsing and capability thresholds now live in one shared helper in databricks.py.
• Pi metadata, Pi adaptive-thinking compatibility, and Claude Code's [1m] selector consume the same capability result.
• Handles dotted, system.ai.*, databricks-*, provider-qualified, [1m]-suffixed, and future major-version IDs.
• Opus 4.5, Haiku, and unknown models retain the conservative 200k fallback; Fable 5 uses its verified native 1M/128k capability without an added [1m] suffix.

Claude Code behavior

This PR intentionally changes Claude Code, not only Pi: Sonnet 4.5+ receives the [1m] suffix, while Opus receives it from 4.6 onward. Sonnet 4.5 has the 1M beta window with a 64k output cap. The PR description calls this out explicitly so the Claude agent behavior is reviewed as part of the change.

Review follow-up

The duplicated version policy previously split between agents/claude.py and databricks.py has been removed. Table-driven coverage now checks Opus 4.5/4.6/5, Sonnet 4.4/4.5/4.6/5, Haiku, Fable, malformed IDs, prefixes, and existing [1m] suffixes.

Validation

• uv run pytest tests/test_databricks.py tests/test_agent_claude.py tests/test_agent_pi.py -q — passed in the final review loop
• uv run ruff check src/ucode/databricks.py src/ucode/agents/claude.py src/ucode/agents/pi.py tests/test_databricks.py tests/test_agent_claude.py tests/test_agent_pi.py

Stacking / review scope

This PR is stacked on #217. Review the incremental commit/diff from 65b4609 to 636c3b6:

65b4609...636c3b6

After #217 merges, this branch can be rebased directly onto main.

[dgokeeffe]

@rohita5l I refreshed this stacked PR: Claude capability/version policy is now shared by Pi and Claude Code, the Sonnet 4.5 Claude Code behavior is explicit in the description, and both threads have detailed replies and are resolved. Could you re-review and approve the fork CI run when convenient?

[dgokeeffe]

Post-review update: shared capability policy now reflects Sonnet 4.6 at 1M/64k and Fable 5 at native 1M/128k with adaptive thinking but no [1m] suffix. GPT matching is boundary-safe/case-insensitive, excludes GPT-OSS from Responses selection, and preserves generic Responses endpoints while preferring the newest semantic GPT. PR body/comparison link updated.

[dgokeeffe]

Pushed 8d66253 to fix a 400 this PR would otherwise introduce.

_pi_gpt_model_entry set reasoning: True without a thinkingLevelMap. Pi's Responses builder treats a missing off-state as effort: "none" (pi-ai/dist/api/openai-responses.js, the thinkingLevelMap?.off !== null branch):

else if (model.provider !== "github-copilot" && model.thinkingLevelMap?.off !== null) {
    params.reasoning = { effort: (model.thinkingLevelMap?.off ?? "none") };
}

"none" is only valid on gpt-5.1+, so with thinking off, four ids rejected every request:

BAD_REQUEST: Unsupported value: 'none' is not supported with the 'gpt-5' model.
Supported values are: 'minimal', 'low', 'medium', and 'high'.

Measured against /ai-gateway/codex/v1/responses:

Model	effort:"none"	effort:"minimal"	omitted
gpt-5, gpt-5-mini, gpt-5-nano	400	200	200
gpt-5-5-pro	400	400	200
gpt-5-1/-2/-3-codex/-4/-4-mini/-4-nano/-5/-6-luna/-6-sol/-6-terra	200	200	200

Fix is entry["thinkingLevelMap"] = {"off": None}, which makes Pi omit reasoning entirely — 200 on all 14 ids. {"off": "minimal"} was the other option but gpt-5-5-pro rejects it too, so it would need a hardcoded per-model exclusion list against a dynamically discovered model set. Same {"off": None} pattern we already use for the Gemini 3.x entries.

Also bisected the rest of Pi's Responses payload against the gateway; all 200, no other compat flags needed: store:false, prompt_cache_key, prompt_cache_retention:"24h", prompt_cache_options, include:["reasoning.encrypted_content"], developer role, flat tool schemas with additionalProperties:false, and the underscore session_id / x-client-request-id affinity headers.

Added two regression tests in tests/test_agent_pi.py (every gpt-5 entry pins {"off": None}; non-gpt codex entries stay bare) plus a docstring note on why the override is mandatory whenever reasoning: True is declared.

uv run pytest --ignore=tests/test_e2e.py --ignore=tests/test_e2e_tracing.py → 1102 passed, 6 skipped. The two test_e2e_user_agent failures I see locally are pre-existing on this branch (identical at 4984d37 without my commit) and need local agent binaries, so they skip in the test job.

Two things for reviewers:

1. _pi_claude_model_entry in this same diff has the same shape — reasoning: True, no thinkingLevelMap. It doesn't bite today because Claude goes through anthropic-messages, which never reaches the Responses reasoning branch. Left alone deliberately, but it's a latent trap if that ever moves.
2. The trade in this fix: thinking-off is now delegated to the gateway default rather than explicitly requested as zero reasoning. That seemed clearly better than 400ing, but flagging it in case exact off-semantics matter.

Worth noting this was painful to diagnose because the gateway returns {"error_code","message"} instead of OpenAI's {"error":{...}}, so Pi's error-body.js recovery no-ops and every 400 renders as OpenAI API error (400): 400 status code (no body). Reported upstream: earendil-works/pi#7748. Tracking issue: #286.

[dgokeeffe]

Rebased this PR stack onto current main (67429ec) and force-pushed the existing branch. New head: 94fe107.

Stack dependency

This is 2 of 3 and must land after #217:

1. feat(pi): add validated GLM/Kimi MLflow provider #217 — Pi MLflow OSS provider
2. fix: declare long-context Claude and GPT metadata #223 — shared Claude/GPT metadata + Pi GPT thinking-off fix (this PR)
3. fix(opencode): add GPT routing alongside OSS discovery #239 — OpenCode GPT routing + OSS discovery fallback

The rebase preserves main's #282 contract: Pi pins codex_models[0] verbatim; it does not re-sort for the newest GPT. The preferred_gpt_model helper is not part of this PR anymore—it is introduced with its OpenCode consumer in #239.

94fe107 contains the thinkingLevelMap: {"off": None} fix discussed above and tracked in #286. It prevents Pi from sending unsupported reasoning: {effort: "none"} to gpt-5/-mini/-nano/-5-5-pro.

If #217 is squash-merged, please rebase this branch onto the updated main before merging.

Validation

• CI-parity suite: 1,648 passed, 6 skipped
• Only local failures: the two pre-existing CLI capture-server tests (TestClaudeUserAgent, TestPiUserAgent), which skip in CI's unit-test job
• ruff check and ruff format --check: clean
• No committed uv.lock churn or conflict markers

Managed allowlist × live-discovery intersection is deliberately outside this PR and tracked in #290.