… extras from [all] (#24515)

* fix(install): use `--extra all` not `--all-extras`; drop lazy-covered extras from [all]

Two coupled fixes for the Windows install hang where uv sync built
python-olm from sdist and failed on missing make.

# Root cause: --all-extras vs --extra all (credit: ethernet)

`uv sync --all-extras` installs every key in [project.optional-
dependencies], bypassing the curated [all] extra entirely. So even
when [all] excluded [matrix], [rl], [yc-bench], etc., the installer
pulled them anyway because they were still defined as extras. On
Windows that meant python-olm (no wheel, needs make to build from
sdist) and the install died there.

The right flag is `--extra all` — install just the [all] extra's
contents, respecting curation. Empirically verified via dry-run:

  --all-extras: pulls python-olm, mautrix, ctranslate2, onnxruntime,
                atroposlib, tinker, wandb, modal, daytona, vercel,
                python-telegram-bot, discord.py, slack-bolt,
                dingtalk-stream, lark-oapi, anthropic, boto3,
                edge-tts, elevenlabs, exa-py, fal-client, faster-
                whisper, firecrawl-py, honcho-ai, parallel-web
  --extra all:  pulls none of those — just [all]'s curated set

Dockerfile already uses `--extra all` (with comment explaining the
gotcha) — knowledge existed; the gap was install.sh / install.ps1 /
setup-hermes.sh.

Sites fixed: scripts/install.sh L1118, scripts/install.ps1 L809,
setup-hermes.sh L245.

# Companion fix: drop lazy-covered extras from [all]

`tools/lazy_deps.py` already covers anthropic, bedrock, exa,
firecrawl, parallel-web, fal, edge-tts, elevenlabs, modal, daytona,
vercel, all messaging platforms (telegram/discord/slack/matrix/
dingtalk/feishu), honcho, and faster-whisper. They were ALSO in
[all], which defeats the whole point of lazy-install — fresh
installs eager-pulled them and inherited whatever was broken
upstream (the matrix → python-olm → no Windows wheel chain being
the proximate symptom).

[all] now contains only what genuinely can't be lazy-installed:
cron, cli, dev, pty, mcp, homeassistant, sms, acp, google, web,
youtube. Same trim applied to [termux-all]. New regression test
asserts the contract: every extra in LAZY_DEPS must NOT also appear
in [all].

# Companion fix: surface uv progress + errors

setup-hermes.sh's hash-verified path swallowed uv's stderr to a
tempfile, identical to the install.sh bug fixed in PR #24504. Same
fix applied: stream stderr through directly so users see live
progress instead of staring at a frozen prompt.

# Files

- pyproject.toml: trim [all] and [termux-all] to non-lazy extras only.
- scripts/install.sh: --all-extras → --extra all; trim _ALL_EXTRAS /
  _PYPI_EXTRAS to match.
- scripts/install.ps1: --all-extras → --extra all; trim $allExtras /
  $pypiExtras to match.
- setup-hermes.sh: --all-extras → --extra all; stream stderr.
- tests/test_project_metadata.py: invert matrix-in-[all] assertion;
  add lazy-coverage contract test.
- uv.lock: regenerated.

# Validation

5/5 metadata tests pass. 37/37 in update_autostash + tool_token_
estimation. `uv lock --check` passes. Empirical dry-run confirms
`--extra all` excludes python-olm + RL chain on the new lockfile.

* fix(install): parse [all] from pyproject.toml instead of mirroring it

ethernet's review point: the previous patch left two hand-mirrored
copies of [all]'s contents (in install.sh's $_ALL_EXTRAS and
install.ps1's $allExtras). That guarantees future drift the next
time pyproject.toml's [all] changes.

Now both scripts parse pyproject.toml at install time using stdlib
tomllib (Python 3.11+, which the bootstrap step already requires).
Single source of truth. The only purpose of the parsed list is to
build the 'Tier 2: [all] minus broken extras' fallback spec — so we
parse, filter against $brokenExtras, and rebuild the .[a,b,c] spec.

Also: removed redundant fallback tiers.

  Before:   Tier 1 [all]
            Tier 2 [all] minus broken
            Tier 3 PyPI-only extras (no git deps)
            Tier 4 [web,mcp,cron,cli,messaging,dev]
            Tier 5 .

  After:    Tier 1 [all]
            Tier 2 [all] minus broken
            Tier 3 .

Tier 3 (PyPI-only) and Tier 4 (dashboard+core) used to dodge the [rl]
git+sdist deps and the [matrix] python-olm build. Both are no longer
in [all] post-2026-05-12 lazy-install migration, so the carve-out
tiers had no remaining content. Tier 4 also referenced [messaging],
which is now lazy-installed — the hardcoded fallback was actually
inconsistent with the new policy.

Defensive fallback: if tomllib parse fails (corrupted pyproject,
unexpected schema), Tier 2 collapses to '.[all]' (same as Tier 1) so
the broken-extras path becomes a no-op rather than crashing.

* fix(gateway): hide Matrix from setup picker on Windows

Matrix is the one messaging platform that has no working install path
on Windows: [matrix] -> mautrix[encryption] -> python-olm, which has
Linux-only wheels and needs make + libolm to build from sdist. The
[all] cleanup in this PR keeps mautrix out of fresh installs, but a
user who picked Matrix in 'hermes setup gateway' would still walk
into the same sdist build failure when the wizard tried to install
the extra.

Hide the option at the picker so users never get the chance to try.
The gate lives in _all_platforms() — single source of truth for the
setup wizard, the curses gateway-config menu, and any future picker.

Adapter loading at runtime is intentionally NOT gated: users who
already have MATRIX_* env vars set (e.g. config copied from a Linux
install) keep working if they somehow have python-olm available.
This is the lowest-friction fix — picker visibility only.

Tests cover linux/darwin/win32 and verify other platforms aren't
collateral damage.

…ently hanging (NousResearch#24504)

The 4d54a54 tiered installer made two install paths look frozen on
slow networks or broken environments because both swallowed the
underlying tool's stderr.

scripts/install.sh, setup-hermes.sh:
  curl -LsSf https://astral.sh/uv/install.sh | sh 2>/dev/null
  printed only '✗ Failed to install uv' on failure with no diagnostic.
  Common real causes (glibc mismatch on old distros, corp proxy / TLS
  interception, missing curl, ~/.local/bin not writable, disk full)
  were invisible. Also: piping curl into sh masks curl failures under
  set -e (no pipefail) — sh exits 0 on empty stdin, so a network error
  succeeded silently.
  Fix: download installer to a tempfile first, then run it. Capture
  curl + installer output to a log; on failure, indent and print it.

scripts/install.sh hash-verified tier:
  uv sync --all-extras --locked 2>"$(mktemp)" silenced uv's progress
  output, making a fresh-venv install (~50 transitives including
  torch-class deps) look hung for 1-5 minutes — users see 'Trying tier:
  hash-verified (uv.lock) ...' and assume it's frozen. The mktemp
  substitution also wasn't saved to a variable, so the uv error on
  failure was unreachable.
  Fix: stream uv's stderr directly so users see live 'Resolved N /
  Prepared / Installed' progress. Print an upfront note that the first
  run takes 1-5 minutes.

… extras from [all] (NousResearch#24515)

* fix(install): use `--extra all` not `--all-extras`; drop lazy-covered extras from [all]

Two coupled fixes for the Windows install hang where uv sync built
python-olm from sdist and failed on missing make.

# Root cause: --all-extras vs --extra all (credit: ethernet)

`uv sync --all-extras` installs every key in [project.optional-
dependencies], bypassing the curated [all] extra entirely. So even
when [all] excluded [matrix], [rl], [yc-bench], etc., the installer
pulled them anyway because they were still defined as extras. On
Windows that meant python-olm (no wheel, needs make to build from
sdist) and the install died there.

The right flag is `--extra all` — install just the [all] extra's
contents, respecting curation. Empirically verified via dry-run:

  --all-extras: pulls python-olm, mautrix, ctranslate2, onnxruntime,
                atroposlib, tinker, wandb, modal, daytona, vercel,
                python-telegram-bot, discord.py, slack-bolt,
                dingtalk-stream, lark-oapi, anthropic, boto3,
                edge-tts, elevenlabs, exa-py, fal-client, faster-
                whisper, firecrawl-py, honcho-ai, parallel-web
  --extra all:  pulls none of those — just [all]'s curated set

Dockerfile already uses `--extra all` (with comment explaining the
gotcha) — knowledge existed; the gap was install.sh / install.ps1 /
setup-hermes.sh.

Sites fixed: scripts/install.sh L1118, scripts/install.ps1 L809,
setup-hermes.sh L245.

# Companion fix: drop lazy-covered extras from [all]

`tools/lazy_deps.py` already covers anthropic, bedrock, exa,
firecrawl, parallel-web, fal, edge-tts, elevenlabs, modal, daytona,
vercel, all messaging platforms (telegram/discord/slack/matrix/
dingtalk/feishu), honcho, and faster-whisper. They were ALSO in
[all], which defeats the whole point of lazy-install — fresh
installs eager-pulled them and inherited whatever was broken
upstream (the matrix → python-olm → no Windows wheel chain being
the proximate symptom).

[all] now contains only what genuinely can't be lazy-installed:
cron, cli, dev, pty, mcp, homeassistant, sms, acp, google, web,
youtube. Same trim applied to [termux-all]. New regression test
asserts the contract: every extra in LAZY_DEPS must NOT also appear
in [all].

# Companion fix: surface uv progress + errors

setup-hermes.sh's hash-verified path swallowed uv's stderr to a
tempfile, identical to the install.sh bug fixed in PR NousResearch#24504. Same
fix applied: stream stderr through directly so users see live
progress instead of staring at a frozen prompt.

# Files

- pyproject.toml: trim [all] and [termux-all] to non-lazy extras only.
- scripts/install.sh: --all-extras → --extra all; trim _ALL_EXTRAS /
  _PYPI_EXTRAS to match.
- scripts/install.ps1: --all-extras → --extra all; trim $allExtras /
  $pypiExtras to match.
- setup-hermes.sh: --all-extras → --extra all; stream stderr.
- tests/test_project_metadata.py: invert matrix-in-[all] assertion;
  add lazy-coverage contract test.
- uv.lock: regenerated.

# Validation

5/5 metadata tests pass. 37/37 in update_autostash + tool_token_
estimation. `uv lock --check` passes. Empirical dry-run confirms
`--extra all` excludes python-olm + RL chain on the new lockfile.

* fix(install): parse [all] from pyproject.toml instead of mirroring it

ethernet's review point: the previous patch left two hand-mirrored
copies of [all]'s contents (in install.sh's $_ALL_EXTRAS and
install.ps1's $allExtras). That guarantees future drift the next
time pyproject.toml's [all] changes.

Now both scripts parse pyproject.toml at install time using stdlib
tomllib (Python 3.11+, which the bootstrap step already requires).
Single source of truth. The only purpose of the parsed list is to
build the 'Tier 2: [all] minus broken extras' fallback spec — so we
parse, filter against $brokenExtras, and rebuild the .[a,b,c] spec.

Also: removed redundant fallback tiers.

  Before:   Tier 1 [all]
            Tier 2 [all] minus broken
            Tier 3 PyPI-only extras (no git deps)
            Tier 4 [web,mcp,cron,cli,messaging,dev]
            Tier 5 .

  After:    Tier 1 [all]
            Tier 2 [all] minus broken
            Tier 3 .

Tier 3 (PyPI-only) and Tier 4 (dashboard+core) used to dodge the [rl]
git+sdist deps and the [matrix] python-olm build. Both are no longer
in [all] post-2026-05-12 lazy-install migration, so the carve-out
tiers had no remaining content. Tier 4 also referenced [messaging],
which is now lazy-installed — the hardcoded fallback was actually
inconsistent with the new policy.

Defensive fallback: if tomllib parse fails (corrupted pyproject,
unexpected schema), Tier 2 collapses to '.[all]' (same as Tier 1) so
the broken-extras path becomes a no-op rather than crashing.

* fix(gateway): hide Matrix from setup picker on Windows

Matrix is the one messaging platform that has no working install path
on Windows: [matrix] -> mautrix[encryption] -> python-olm, which has
Linux-only wheels and needs make + libolm to build from sdist. The
[all] cleanup in this PR keeps mautrix out of fresh installs, but a
user who picked Matrix in 'hermes setup gateway' would still walk
into the same sdist build failure when the wizard tried to install
the extra.

Hide the option at the picker so users never get the chance to try.
The gate lives in _all_platforms() — single source of truth for the
setup wizard, the curses gateway-config menu, and any future picker.

Adapter loading at runtime is intentionally NOT gated: users who
already have MATRIX_* env vars set (e.g. config copied from a Linux
install) keep working if they somehow have python-olm available.
This is the lowest-friction fix — picker visibility only.

Tests cover linux/darwin/win32 and verify other platforms aren't
collateral damage.

…ently hanging (NousResearch#24504)

The c1eb2dc tiered installer made two install paths look frozen on
slow networks or broken environments because both swallowed the
underlying tool's stderr.

scripts/install.sh, setup-hermes.sh:
  curl -LsSf https://astral.sh/uv/install.sh | sh 2>/dev/null
  printed only '✗ Failed to install uv' on failure with no diagnostic.
  Common real causes (glibc mismatch on old distros, corp proxy / TLS
  interception, missing curl, ~/.local/bin not writable, disk full)
  were invisible. Also: piping curl into sh masks curl failures under
  set -e (no pipefail) — sh exits 0 on empty stdin, so a network error
  succeeded silently.
  Fix: download installer to a tempfile first, then run it. Capture
  curl + installer output to a log; on failure, indent and print it.

scripts/install.sh hash-verified tier:
  uv sync --all-extras --locked 2>"$(mktemp)" silenced uv's progress
  output, making a fresh-venv install (~50 transitives including
  torch-class deps) look hung for 1-5 minutes — users see 'Trying tier:
  hash-verified (uv.lock) ...' and assume it's frozen. The mktemp
  substitution also wasn't saved to a variable, so the uv error on
  failure was unreachable.
  Fix: stream uv's stderr directly so users see live 'Resolved N /
  Prepared / Installed' progress. Print an upfront note that the first
  run takes 1-5 minutes.

… extras from [all] (NousResearch#24515)

* fix(install): use `--extra all` not `--all-extras`; drop lazy-covered extras from [all]

Two coupled fixes for the Windows install hang where uv sync built
python-olm from sdist and failed on missing make.

# Root cause: --all-extras vs --extra all (credit: ethernet)

`uv sync --all-extras` installs every key in [project.optional-
dependencies], bypassing the curated [all] extra entirely. So even
when [all] excluded [matrix], [rl], [yc-bench], etc., the installer
pulled them anyway because they were still defined as extras. On
Windows that meant python-olm (no wheel, needs make to build from
sdist) and the install died there.

The right flag is `--extra all` — install just the [all] extra's
contents, respecting curation. Empirically verified via dry-run:

  --all-extras: pulls python-olm, mautrix, ctranslate2, onnxruntime,
                atroposlib, tinker, wandb, modal, daytona, vercel,
                python-telegram-bot, discord.py, slack-bolt,
                dingtalk-stream, lark-oapi, anthropic, boto3,
                edge-tts, elevenlabs, exa-py, fal-client, faster-
                whisper, firecrawl-py, honcho-ai, parallel-web
  --extra all:  pulls none of those — just [all]'s curated set

Dockerfile already uses `--extra all` (with comment explaining the
gotcha) — knowledge existed; the gap was install.sh / install.ps1 /
setup-hermes.sh.

Sites fixed: scripts/install.sh L1118, scripts/install.ps1 L809,
setup-hermes.sh L245.

# Companion fix: drop lazy-covered extras from [all]

`tools/lazy_deps.py` already covers anthropic, bedrock, exa,
firecrawl, parallel-web, fal, edge-tts, elevenlabs, modal, daytona,
vercel, all messaging platforms (telegram/discord/slack/matrix/
dingtalk/feishu), honcho, and faster-whisper. They were ALSO in
[all], which defeats the whole point of lazy-install — fresh
installs eager-pulled them and inherited whatever was broken
upstream (the matrix → python-olm → no Windows wheel chain being
the proximate symptom).

[all] now contains only what genuinely can't be lazy-installed:
cron, cli, dev, pty, mcp, homeassistant, sms, acp, google, web,
youtube. Same trim applied to [termux-all]. New regression test
asserts the contract: every extra in LAZY_DEPS must NOT also appear
in [all].

# Companion fix: surface uv progress + errors

setup-hermes.sh's hash-verified path swallowed uv's stderr to a
tempfile, identical to the install.sh bug fixed in PR NousResearch#24504. Same
fix applied: stream stderr through directly so users see live
progress instead of staring at a frozen prompt.

# Files

- pyproject.toml: trim [all] and [termux-all] to non-lazy extras only.
- scripts/install.sh: --all-extras → --extra all; trim _ALL_EXTRAS /
  _PYPI_EXTRAS to match.
- scripts/install.ps1: --all-extras → --extra all; trim $allExtras /
  $pypiExtras to match.
- setup-hermes.sh: --all-extras → --extra all; stream stderr.
- tests/test_project_metadata.py: invert matrix-in-[all] assertion;
  add lazy-coverage contract test.
- uv.lock: regenerated.

# Validation

5/5 metadata tests pass. 37/37 in update_autostash + tool_token_
estimation. `uv lock --check` passes. Empirical dry-run confirms
`--extra all` excludes python-olm + RL chain on the new lockfile.

* fix(install): parse [all] from pyproject.toml instead of mirroring it

ethernet's review point: the previous patch left two hand-mirrored
copies of [all]'s contents (in install.sh's $_ALL_EXTRAS and
install.ps1's $allExtras). That guarantees future drift the next
time pyproject.toml's [all] changes.

Now both scripts parse pyproject.toml at install time using stdlib
tomllib (Python 3.11+, which the bootstrap step already requires).
Single source of truth. The only purpose of the parsed list is to
build the 'Tier 2: [all] minus broken extras' fallback spec — so we
parse, filter against $brokenExtras, and rebuild the .[a,b,c] spec.

Also: removed redundant fallback tiers.

  Before:   Tier 1 [all]
            Tier 2 [all] minus broken
            Tier 3 PyPI-only extras (no git deps)
            Tier 4 [web,mcp,cron,cli,messaging,dev]
            Tier 5 .

  After:    Tier 1 [all]
            Tier 2 [all] minus broken
            Tier 3 .

Tier 3 (PyPI-only) and Tier 4 (dashboard+core) used to dodge the [rl]
git+sdist deps and the [matrix] python-olm build. Both are no longer
in [all] post-2026-05-12 lazy-install migration, so the carve-out
tiers had no remaining content. Tier 4 also referenced [messaging],
which is now lazy-installed — the hardcoded fallback was actually
inconsistent with the new policy.

Defensive fallback: if tomllib parse fails (corrupted pyproject,
unexpected schema), Tier 2 collapses to '.[all]' (same as Tier 1) so
the broken-extras path becomes a no-op rather than crashing.

* fix(gateway): hide Matrix from setup picker on Windows

Matrix is the one messaging platform that has no working install path
on Windows: [matrix] -> mautrix[encryption] -> python-olm, which has
Linux-only wheels and needs make + libolm to build from sdist. The
[all] cleanup in this PR keeps mautrix out of fresh installs, but a
user who picked Matrix in 'hermes setup gateway' would still walk
into the same sdist build failure when the wizard tried to install
the extra.

Hide the option at the picker so users never get the chance to try.
The gate lives in _all_platforms() — single source of truth for the
setup wizard, the curses gateway-config menu, and any future picker.

Adapter loading at runtime is intentionally NOT gated: users who
already have MATRIX_* env vars set (e.g. config copied from a Linux
install) keep working if they somehow have python-olm available.
This is the lowest-friction fix — picker visibility only.

Tests cover linux/darwin/win32 and verify other platforms aren't
collateral damage.

…ently hanging (NousResearch#24504)

The c1eb2dc tiered installer made two install paths look frozen on
slow networks or broken environments because both swallowed the
underlying tool's stderr.

scripts/install.sh, setup-hermes.sh:
  curl -LsSf https://astral.sh/uv/install.sh | sh 2>/dev/null
  printed only '✗ Failed to install uv' on failure with no diagnostic.
  Common real causes (glibc mismatch on old distros, corp proxy / TLS
  interception, missing curl, ~/.local/bin not writable, disk full)
  were invisible. Also: piping curl into sh masks curl failures under
  set -e (no pipefail) — sh exits 0 on empty stdin, so a network error
  succeeded silently.
  Fix: download installer to a tempfile first, then run it. Capture
  curl + installer output to a log; on failure, indent and print it.

scripts/install.sh hash-verified tier:
  uv sync --all-extras --locked 2>"$(mktemp)" silenced uv's progress
  output, making a fresh-venv install (~50 transitives including
  torch-class deps) look hung for 1-5 minutes — users see 'Trying tier:
  hash-verified (uv.lock) ...' and assume it's frozen. The mktemp
  substitution also wasn't saved to a variable, so the uv error on
  failure was unreachable.
  Fix: stream uv's stderr directly so users see live 'Resolved N /
  Prepared / Installed' progress. Print an upfront note that the first
  run takes 1-5 minutes.

… extras from [all] (NousResearch#24515)

* fix(install): use `--extra all` not `--all-extras`; drop lazy-covered extras from [all]

Two coupled fixes for the Windows install hang where uv sync built
python-olm from sdist and failed on missing make.

# Root cause: --all-extras vs --extra all (credit: ethernet)

`uv sync --all-extras` installs every key in [project.optional-
dependencies], bypassing the curated [all] extra entirely. So even
when [all] excluded [matrix], [rl], [yc-bench], etc., the installer
pulled them anyway because they were still defined as extras. On
Windows that meant python-olm (no wheel, needs make to build from
sdist) and the install died there.

The right flag is `--extra all` — install just the [all] extra's
contents, respecting curation. Empirically verified via dry-run:

  --all-extras: pulls python-olm, mautrix, ctranslate2, onnxruntime,
                atroposlib, tinker, wandb, modal, daytona, vercel,
                python-telegram-bot, discord.py, slack-bolt,
                dingtalk-stream, lark-oapi, anthropic, boto3,
                edge-tts, elevenlabs, exa-py, fal-client, faster-
                whisper, firecrawl-py, honcho-ai, parallel-web
  --extra all:  pulls none of those — just [all]'s curated set

Dockerfile already uses `--extra all` (with comment explaining the
gotcha) — knowledge existed; the gap was install.sh / install.ps1 /
setup-hermes.sh.

Sites fixed: scripts/install.sh L1118, scripts/install.ps1 L809,
setup-hermes.sh L245.

# Companion fix: drop lazy-covered extras from [all]

`tools/lazy_deps.py` already covers anthropic, bedrock, exa,
firecrawl, parallel-web, fal, edge-tts, elevenlabs, modal, daytona,
vercel, all messaging platforms (telegram/discord/slack/matrix/
dingtalk/feishu), honcho, and faster-whisper. They were ALSO in
[all], which defeats the whole point of lazy-install — fresh
installs eager-pulled them and inherited whatever was broken
upstream (the matrix → python-olm → no Windows wheel chain being
the proximate symptom).

[all] now contains only what genuinely can't be lazy-installed:
cron, cli, dev, pty, mcp, homeassistant, sms, acp, google, web,
youtube. Same trim applied to [termux-all]. New regression test
asserts the contract: every extra in LAZY_DEPS must NOT also appear
in [all].

# Companion fix: surface uv progress + errors

setup-hermes.sh's hash-verified path swallowed uv's stderr to a
tempfile, identical to the install.sh bug fixed in PR NousResearch#24504. Same
fix applied: stream stderr through directly so users see live
progress instead of staring at a frozen prompt.

# Files

- pyproject.toml: trim [all] and [termux-all] to non-lazy extras only.
- scripts/install.sh: --all-extras → --extra all; trim _ALL_EXTRAS /
  _PYPI_EXTRAS to match.
- scripts/install.ps1: --all-extras → --extra all; trim $allExtras /
  $pypiExtras to match.
- setup-hermes.sh: --all-extras → --extra all; stream stderr.
- tests/test_project_metadata.py: invert matrix-in-[all] assertion;
  add lazy-coverage contract test.
- uv.lock: regenerated.

# Validation

5/5 metadata tests pass. 37/37 in update_autostash + tool_token_
estimation. `uv lock --check` passes. Empirical dry-run confirms
`--extra all` excludes python-olm + RL chain on the new lockfile.

* fix(install): parse [all] from pyproject.toml instead of mirroring it

ethernet's review point: the previous patch left two hand-mirrored
copies of [all]'s contents (in install.sh's $_ALL_EXTRAS and
install.ps1's $allExtras). That guarantees future drift the next
time pyproject.toml's [all] changes.

Now both scripts parse pyproject.toml at install time using stdlib
tomllib (Python 3.11+, which the bootstrap step already requires).
Single source of truth. The only purpose of the parsed list is to
build the 'Tier 2: [all] minus broken extras' fallback spec — so we
parse, filter against $brokenExtras, and rebuild the .[a,b,c] spec.

Also: removed redundant fallback tiers.

  Before:   Tier 1 [all]
            Tier 2 [all] minus broken
            Tier 3 PyPI-only extras (no git deps)
            Tier 4 [web,mcp,cron,cli,messaging,dev]
            Tier 5 .

  After:    Tier 1 [all]
            Tier 2 [all] minus broken
            Tier 3 .

Tier 3 (PyPI-only) and Tier 4 (dashboard+core) used to dodge the [rl]
git+sdist deps and the [matrix] python-olm build. Both are no longer
in [all] post-2026-05-12 lazy-install migration, so the carve-out
tiers had no remaining content. Tier 4 also referenced [messaging],
which is now lazy-installed — the hardcoded fallback was actually
inconsistent with the new policy.

Defensive fallback: if tomllib parse fails (corrupted pyproject,
unexpected schema), Tier 2 collapses to '.[all]' (same as Tier 1) so
the broken-extras path becomes a no-op rather than crashing.

* fix(gateway): hide Matrix from setup picker on Windows

Matrix is the one messaging platform that has no working install path
on Windows: [matrix] -> mautrix[encryption] -> python-olm, which has
Linux-only wheels and needs make + libolm to build from sdist. The
[all] cleanup in this PR keeps mautrix out of fresh installs, but a
user who picked Matrix in 'hermes setup gateway' would still walk
into the same sdist build failure when the wizard tried to install
the extra.

Hide the option at the picker so users never get the chance to try.
The gate lives in _all_platforms() — single source of truth for the
setup wizard, the curses gateway-config menu, and any future picker.

Adapter loading at runtime is intentionally NOT gated: users who
already have MATRIX_* env vars set (e.g. config copied from a Linux
install) keep working if they somehow have python-olm available.
This is the lowest-friction fix — picker visibility only.

Tests cover linux/darwin/win32 and verify other platforms aren't
collateral damage.