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.